{"slug":"google-ai-edge-accuracy-safe-quantization","name":"accuracy-safe-quantization","description":"Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants.","long_description":"---\nname: accuracy-safe-quantization\ndescription: Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants.\n---\n\n# Accuracy-safe quantization\n\nA quantization is done when three things hold, in this order:\n\n1. it exports and the file shrinks by what the recipe predicts,\n2. **output parity with the float source holds on a task-level check**, not\n   just a smoke test,\n3. the quantized model still passes the deployment check on the target\n   runtime and device.\n\nQuantization rewrites the graph, so step 3 is a fresh obligation every time:\nre-run the same CompiledModel verification you used to accept the float\nconversion (see the `gpu-clean-conversion` skill), then the on-device\nnumerical check.\n\nAll recipes below are `ai-edge-quantizer` (`pip install ai-edge-quantizer`),\nplain Python, no build step. Worked examples live in this repo under\n`models/bonsai/bonsai_image_4b/converted/` and\n`models/qwen/qwen3_tts/converted/`.\n\n## Choosing a lane\n\nStart with the lightest recipe that meets the size budget, and move down\nonly on evidence:\n\n| Budget / model | Recipe |\n|---|---|\n| ~2× smaller, zero risk | **fp16 float-casting.** Weights cast to fp16, compute stays float. On a GPU that already computes in fp16 this is close to free numerically — verify anyway |\n| ~4× smaller — encoders, conv nets, diffusion blocks | **Dynamic-range int8 channelwise.** int8 weights, float activations; this shape rides the GPU delegate |\n| Dynamic int8 lost quality (conditioning, embeddings) | **Weight-only, same bits.** Inserts an explicit DEQUANTIZE so the matmul runs in float and activations are never quantized — more quality, some latency |\n| ~7× smaller — LLM / autoregressive decoders | **int4 blockwise-32 + OCTAV, embeddings int8.** Never channelwise for a decoder: it looks fine on short outputs and degenerates over long generations |\n| Data-free int4 still fails the task gate | **Calibrated ingest.** Take a GPTQ checkpoint and preserve its grid with `DEQUANTIZED_WEIGHT_RECOVERY` — see the routing table |\n\nFull-integer static quantization (`static_wi8_ai8` — quantized activations,\ncalibration data required) is a different lane aimed at NPU/AOT targets and\nis not covered here.\n\n## Recipes\n\nRecipes layer by regex: broad rule first, narrow overrides after — that is\nhow one file mixes lanes (bonsai's DiT puts everything at int8 channelwise,\nthen overrides `.*TransformerBlock_.*` to int4 blockwise).\n\nfp16 float-casting:\n\n```python\nfrom ai_edge_quantizer import quantizer, recipe_manager\nfrom ai_edge_quantizer.recipe import AlgorithmName, qtyping\n\nrm = recipe_manager.RecipeManager()\nrm.add_quantization_config(\n    regex=\".*\", operation_name=qtyping.TFLOperationName.ALL_SUPPORTED,\n    op_config=qtyping.OpQuantizationConfig(\n        weight_tensor_config=qtyping.TensorQuantizationConfig(\n            num_bits=16, dtype=qtyping.TensorDataType.FLOAT),\n        compute_precision=qtyping.ComputePrecision.FLOAT),\n    algorithm_key=AlgorithmName.FLOAT_CASTING)\nquantizer.Quantizer(\"model_fp32.tflite\", rm.get_quantization_recipe()) \\\n    .quantize().export_model(\"model_fp16.tflite\")\n```\n\nDynamic-range int (swap bits / granularity / algorithm per the table):\n\n```python\nfrom ai_edge_quantizer.qtyping import QuantGranularity as G\nfrom ai_edge_quantizer.qtyping import TFLOperationName as OP\n\nrm = recipe_manager.RecipeManager()\nrm.add_dynamic_config(regex=\".*\", operation_name=OP.FULLY_CONNECTED,\n                      num_bits=4, granularity=G.BLOCKWISE_32,\n                      algorithm_key=AlgorithmName.OCTAV)\nrm.add_dynamic_config(regex=\".*\", operation_name=OP.EMBEDDING_LOOKUP,\n                      num_bits=8, granularity=G.CHANNELWISE)\n```\n\nWeight-only uses the same signature via `rm.add_weight_only_config(...)` —\n`models/bonsai/bonsai_image_4b/converted/quantize_weight_only.py` wraps it\nas a reusable CLI.\n\n`ai_edge_quantizer.recipe` also ships these as presets\n(`dynamic_wi8_afp32()`, `dynamic_wi4b32_afp32()`, `weight_only_wi8_afp32()`,\n…). The litert-torch LLM exporter accepts a preset name as its\n`quantization_recipe` argument, and a custom recipe can be registered by\nassigning a callable onto the module — the qwen3_tts talker recipe\n(`models/qwen/qwen3_tts/converted/export_talker.py`) registers `BOCTAV4`\n(blockwise-32 OCTAV int4 + int8 embeddings) that way.\n\n## Verify after every step\n\n- **Size first.** fp16 ≈ ½, int8 ≈ ¼, int4 blockwise ≈ ⅐ of fp32 (block\n  scales add overhead). If the file did not shrink as predicted, the regex\n  did not match — fix that before measuring anything.\n- **Parity against the float reference.** Same inputs through the float and\n  quantized models; correlation on outputs plus the task-level check\n  (argmax match, token-for-token greedy decode, IoU).\n- **A smoke gate is a floor, not a parity verdict.** An LLM can pass most of\n  a handful of chat prompts and still score near zero on a real benchmark.\n  Before publishing an int4 decoder, run a task benchmark at real length\n  (e.g. GSM8K-style, n≥100) against the float baseline.\n- **Long generations, specifically.** Granularity problems do not show up\n  in short outputs.\n- **On the target device.** Host emulation of int kernels is pessimistic —\n  int8 graphs have scored visibly worse on host CPU than the same graphs on\n  the device GPU delegate. Never reject a recipe on desktop numbers alone;\n  never accept one without device numbers.\n\n## When it breaks or degrades\n\n| What you see | Knob to turn |\n|---|---|\n| Runtime refuses to load: `unsupported scale value (0.000000) … for INT4 tensor` | Sparse weights produced all-zero blocks, whose min-max scale is 0. Patch each zero scale to the tensor's smallest nonzero scale — dequantization is unchanged because those blocks are all zero. ⚠ Blockwise scales live in separate fp16 scale tensors, **not** `QuantizationParameters.scale` — patching the latter via the flatbuffer object API succeeds silently and changes nothing; edit the scale tensor's buffer directly. `models/bonsai/bonsai_image_4b/converted/fix_zero_block_scales.py` |\n| Dynamic-range int8 collapses a conv net outright (near-zero output correlation, every input misclassified) while the file loads and runs fine | Activation-quantization sensitivity — squeeze-excite and SiLU-family conv nets are the known class. **Weight-only int8 at the same size is typically near-lossless on the same model.** This collapse has shipped inside published artifacts, so parity-check any dynamic-int8 model you did not gate yourself before building on it |\n| Decoder is coherent for a while, then degenerates | Channelwise → `BLOCKWISE_32`; `MIN_MAX_UNIFORM_QUANT` → `OCTAV` |\n| Dynamic-range lost fidelity (prompt conditioning, embeddings) | Weight-only at the same bits |\n| int4 fails the task gate at block-128 | Block-32. Data-free block-128 can collapse outright on small models |\n| int4 fails the task gate at block-32 too | Data-free min-max/OCTAV has hit its limit for this family. Ingest a calibrated GPTQ checkpoint: dequantize it, then quantize with `algorithm_key=AlgorithmName.DEQUANTIZED_WEIGHT_RECOVERY` at the granularity matching the GPTQ group size (gs128 → `BLOCKWISE_128`). Symmetric checkpoints only, `desc_act=False` only |\n| Recovery raises `NOT dequantized (fake-quantized) weights` | That tensor was never on the GPTQ grid (`lm_head`, tied embeddings, first/last layers). The raise is a triage signal, not a bug: route the named tensor to a plain int8 entry by regex |\n| A specific head or block is the culprit | Exclude it by regex — keep it at int8 or float and leave the rest at int4 |\n| Everything above still degrades | fp16 float-casting is the floor. If fp16 fails parity, the problem is upstream of quantization — go back to `gpu-clean-conversion` step 5 |\n\nSome models are genuinely 4-bit sensitive — small reasoning-distilled\ndecoders (~1–2 B) often fail int4 quality gates that instruct-tuned peers\nand larger models pass. When int4 fails on quality, ship int8 as the\nquality row rather than forcing it; int4 becomes a speed reference.\n\n## Watch for\n\n- **Embeddings stay int8** even in int4 recipes — both shipped LLM-lane\n  recipes in this repo do this deliberately.\n- **Bytes are not speed.** int4's latency win depends on the backend's\n  kernel efficiency: the same model can gain ~1.5× on one device and\n  barely 1.1× on another. Measure on the target; don't project from\n  file size.\n- **Check whether the container is exact.** Ternary weights land in int4\n  blockwise as exactly {-7, 0, +7} — zero rounding error. When the weight\n  distribution matches the container, parity is free; verify it rather\n  than budgeting for loss that isn't there. For exact-container cases use\n  **min-max, not OCTAV** — OCTAV's clipping optimization can move a grid\n  that min-max reproduces exactly.\n- **int2 is a container without a consumer** (as of 2026-08): the schema\n  type and the blockwise packer exist (2.125 bits/weight at block-128),\n  but the CPU runtime refuses the tensor type at prepare — a hard load\n  failure, not degradation. Don't spend time there until a kernel ships.\n- **Auxiliary tables cast to fp16 need the same discipline.** Casting\n  host-side embedding/projection tables halves them; verify generated\n  outputs are unchanged before shipping (qwen3_tts did, and it held).\n- **Pin the toolchain.** Quantized-graph compatibility moves with the\n  runtime; a graph exported from a dev checkout can fail GPU kernel\n  initialization on a release runtime. Record `ai-edge-quantizer` /\n  `litert-torch` versions in the recipe README next to the numbers.\n\n## Output layout\n\nQuantization extends the model recipe from `gpu-clean-conversion`; it does\nnot get its own tree:\n\n```\nmodels/<family>/<model>/converted/\n  export_*.py              float export (existing)\n  quantize_*.py            one script per quantized variant\n  verify_*.py              parity checks, reused for every variant\n  README.md                recipe, sizes, parity numbers, gate results,\n                           device, toolchain versions\n```\n\nKeep each variant separately re-runnable. State which variant is the\nquality row and which is the speed row when they differ. Weights are not\ncommitted.\n","tagline":"Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task bench","category":"research","tags":["agent-skill"],"author":"google-ai-edge","verified":false,"attribution":{"status":"registry_indexed","statusLabel":"Registry indexed","shortLabel":"REGISTRY INDEXED","sourceLabel":"recursive skill source sync","sourceDetail":"google-ai-edge/litert-samples","creatorName":"google-ai-edge","creatorUrl":"https://github.com/google-ai-edge","sourceUrl":"https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/google-ai-edge-accuracy-safe-quantization#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":416,"forks":116,"verified_installs":0,"successful_runs":0,"total_outcomes":0,"rating":0,"review_count":0,"quality_score":41.74},"quality":{"score":73,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"416","tone":"neutral"},{"label":"Freshness","value":"3d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":["The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation."]},"trust":{"version":"trust-score-v5","score":57,"base_score":65,"outcome_confidence":0,"tier":"risk","label":"Do not auto-install","summary":"Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.","recommendedAction":"Choose a stronger alternative or inspect the source manually before any install attempt.","decision":{"install_policy":"sandbox_only","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["57/100 Trust Score v5","65/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"416 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"416 stars, 116 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"3d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":86,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":36,"weight":0.12,"status":"fail","detail":"command execution surface, credential or environment access"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":18,"weight":0.07,"status":"fail","detail":"secrets or environment access, shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"416 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"416 stars, 116 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3d since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"fail","label":"Dependency/runtime risk","detail":"command execution surface, credential or environment access"},{"status":"pass","label":"Install availability","detail":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"fail","label":"Permission surface","detail":"secrets or environment access, shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"pass","label":"OpenAgentSkill usage","detail":"5 views, 0 install copies"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Dependency/runtime risk: command execution surface, credential or environment access","Permission surface: secrets or environment access, shell or command execution","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"416 GitHub stars","repoActivity":"416 stars, 116 forks","lastPushed":"3d since push","license":"Apache-2.0","repository":"https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization","install":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, shell or command execution","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"sandbox_only"},"installReadiness":{"ready":true,"command":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization","policy":"sandbox_only","label":"Sandbox only","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Dependency/runtime risk: command execution surface, credential or environment access"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"sandbox_only","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["research","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization","trust_score":57,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Live brokerage, exchange, wallet, or payment credentials outside an explicitly approved sandbox"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Live brokerage, exchange, wallet, or payment credentials outside an explicitly approved sandbox"],"knownRisks":["The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Dependency/runtime risk: command execution surface, credential or environment access","Permission surface: secrets or environment access, shell or command execution"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":65,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection."}}},"trust_score_v5":{"version":"trust-score-v5","score":57,"base_score":65,"outcome_confidence":0,"tier":"risk","label":"Do not auto-install","summary":"Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.","recommendedAction":"Choose a stronger alternative or inspect the source manually before any install attempt.","decision":{"install_policy":"sandbox_only","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["57/100 Trust Score v5","65/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"416 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"416 stars, 116 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"3d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":86,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":36,"weight":0.12,"status":"fail","detail":"command execution surface, credential or environment access"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":18,"weight":0.07,"status":"fail","detail":"secrets or environment access, shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"416 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"416 stars, 116 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3d since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"fail","label":"Dependency/runtime risk","detail":"command execution surface, credential or environment access"},{"status":"pass","label":"Install availability","detail":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"fail","label":"Permission surface","detail":"secrets or environment access, shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"pass","label":"OpenAgentSkill usage","detail":"5 views, 0 install copies"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Dependency/runtime risk: command execution surface, credential or environment access","Permission surface: secrets or environment access, shell or command execution","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"416 GitHub stars","repoActivity":"416 stars, 116 forks","lastPushed":"3d since push","license":"Apache-2.0","repository":"https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization","install":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, shell or command execution","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"sandbox_only"},"installReadiness":{"ready":true,"command":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization","policy":"sandbox_only","label":"Sandbox only","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Dependency/runtime risk: command execution surface, credential or environment access"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"sandbox_only","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["research","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization","trust_score":57,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Live brokerage, exchange, wallet, or payment credentials outside an explicitly approved sandbox"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Live brokerage, exchange, wallet, or payment credentials outside an explicitly approved sandbox"],"knownRisks":["The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Dependency/runtime risk: command execution surface, credential or environment access","Permission surface: secrets or environment access, shell or command execution"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":65,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection."}}},"trust_score_v4":{"version":"trust-score-v4","score":65,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection.","recommendedAction":"Inspect the repository, license, and recent activity before connecting it to agent workflows.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"416 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"416 stars, 116 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"3d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":86,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":36,"weight":0.12,"status":"fail","detail":"command execution surface, credential or environment access"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":18,"weight":0.07,"status":"fail","detail":"secrets or environment access, shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"416 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"416 stars, 116 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3d since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"fail","label":"Dependency/runtime risk","detail":"command execution surface, credential or environment access"},{"status":"pass","label":"Install availability","detail":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"fail","label":"Permission surface","detail":"secrets or environment access, shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"pass","label":"OpenAgentSkill usage","detail":"5 views, 0 install copies"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Dependency/runtime risk: command execution surface, credential or environment access","Permission surface: secrets or environment access, shell or command execution"],"evidence":{"stars":"416 GitHub stars","repoActivity":"416 stars, 116 forks","lastPushed":"3d since push","license":"Apache-2.0","repository":"https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization","install":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, shell or command execution","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization","policy":"sandbox_only","label":"Sandbox only","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3d since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Dependency/runtime risk: command execution surface, credential or environment access"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"sandbox_only","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Live brokerage, exchange, wallet, or payment credentials outside an explicitly approved sandbox"],"knownRisks":["The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Dependency/runtime risk: command execution surface, credential or environment access","Permission surface: secrets or environment access, shell or command execution"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"outcome_stats":null,"safety":{"score":32,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"blocked","label":"Blocked for auto-install","badge":"BLOCKED","summary":"This skill should not be selected by an agent without explicit human security review.","recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first.","auto_install_policy":"block","reasons":["Audit risk exceeds the requested agent policy","Audit classified this skill as risky","Metadata combines secrets access with shell or command execution","Audit risk risky exceeds max_risk=medium"]},"auto_install_allowed":false,"human_review_required":true,"blocked":true,"audit_risk":"risky","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"},{"id":"secrets","label":"Secrets or environment access","reason":"Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.","severity":"high"},{"id":"database","label":"Database access","reason":"Skill may inspect schemas, query databases, or work with persistent stores.","severity":"medium"}],"policy_warnings":["Audit risk risky exceeds max_risk=medium","High-risk permission hints: Shell or command execution, Secrets or environment access","Dependency or permission surface needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"blocked","label":"Blocked for auto-install","badge":"BLOCKED","auto_install_policy":"block","auto_install_allowed":false,"blocked":true,"human_review_required":true,"recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first.","reasons":["Audit risk exceeds the requested agent policy","Audit classified this skill as risky","Metadata combines secrets access with shell or command execution","Audit risk risky exceeds max_risk=medium"]},"eval":{"version":"openagentskill-skill-eval-v1","status":"failed","score":64,"risk_level":"high","decision":{"recommendation":"do_not_auto_install","reason":"Audit score: Risky","auto_install_allowed":false,"policy":"block","human_review_required":true},"blockers":["Audit score: Risky","Agent safety gate: This skill should not be selected by an agent without explicit human security review.","Permission surface: secrets or environment access, shell or command execution"],"warnings":["Trust score: Potentially useful, but at least one trust signal needs human inspection.","Audit risk risky exceeds max_risk=medium","High-risk permission hints: Shell or command execution, Secrets or environment access","Dependency or permission surface needs review","Permission surface may require sandboxing","Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required","The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","SKILL.md references a separate skill (gpu-clean-conversion) without detailing its content, which may require the agent to have that context.","This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Dependency/runtime risk: command execution surface, credential or environment access"],"validation_plan":["Inspect repository, README/SKILL.md, license, and recent commits before production use.","Install in an isolated workspace or sandbox with no production secrets available.","Run the smallest representative task and record files touched, commands run, network access, and outputs.","Compare the selected skill against at least one alternative when the eval status is review or failed.","Promote only after the agent reports a successful verification result and unresolved warnings are accepted."],"checks":[{"id":"task_fit","label":"Task fit","status":"pass","score":84,"required_for_auto_install":true,"detail":"Task wording matches this skill metadata.","evidence":["Evaluate accuracy-safe-quantization before installing it in an agent workflow","research","Browser automation workflows; Claude Code teams; builders willing to evaluate younger projects"]},{"id":"install_path","label":"Install path","status":"pass","score":92,"required_for_auto_install":true,"detail":"Install handoff is available.","evidence":["npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization"]},{"id":"install_safety","label":"Install command safety","status":"pass","score":92,"required_for_auto_install":true,"detail":"standard package or runtime install path","evidence":["npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization"]},{"id":"trust_score","label":"Trust score","status":"warn","score":65,"required_for_auto_install":true,"detail":"Potentially useful, but at least one trust signal needs human inspection.","evidence":["Manual review","416 GitHub stars","Apache-2.0"]},{"id":"audit_score","label":"Audit score","status":"fail","score":76,"required_for_auto_install":true,"detail":"Risky","evidence":["Dependency or permission surface needs review"]},{"id":"agent_safety_gate","label":"Agent safety gate","status":"fail","score":32,"required_for_auto_install":true,"detail":"This skill should not be selected by an agent without explicit human security review.","evidence":["Do not auto-install. Inspect the source, dependencies, and permission surface first.","Audit risk exceeds the requested agent policy"]},{"id":"readme_skillmd_completeness","label":"README/SKILL.md completeness","status":"pass","score":86,"required_for_auto_install":false,"detail":"Metadata includes enough usage and workflow context","evidence":["Strong README/SKILL.md context"]},{"id":"license_clarity","label":"License clarity","status":"pass","score":86,"required_for_auto_install":true,"detail":"Apache-2.0","evidence":["Apache-2.0"]},{"id":"recent_maintenance","label":"Recent maintenance","status":"pass","score":100,"required_for_auto_install":false,"detail":"3d since push","evidence":["3d since push"]},{"id":"permission_surface","label":"Permission surface","status":"fail","score":18,"required_for_auto_install":true,"detail":"secrets or environment access, shell or command execution","evidence":["Shell or command execution: high","Network access: medium","Filesystem access: medium"]},{"id":"alternatives","label":"Alternatives available","status":"info","score":55,"required_for_auto_install":false,"detail":"No close alternatives were found in the current shortlist.","evidence":[]}],"endpoints":{"web":"https://www.openagentskill.com/skills/google-ai-edge-accuracy-safe-quantization/evals","api":"/api/agent/evals?slug=google-ai-edge-accuracy-safe-quantization","text":"/api/agent/evals?slug=google-ai-edge-accuracy-safe-quantization&format=text"}},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"google-ai-edge-accuracy-safe-quantization","name":"accuracy-safe-quantization","description":"Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants.","category":"research","url":"https://www.openagentskill.com/skills/google-ai-edge-accuracy-safe-quantization","repository":"https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization","github_repo":"google-ai-edge/litert-samples"},"suited_tasks":["Browser automation workflows","Claude Code teams","builders willing to evaluate younger projects","Navigate pages","Click and type safely","Check visual and DOM state","Search sources","Extract claims"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add google-ai-edge-accuracy-safe-quantization"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"accuracy-safe-quantization\" agent skill from https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"google-ai-edge-accuracy-safe-quantization\",\"task\":\"Install accuracy-safe-quantization\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"accuracy-safe-quantization\" as a Claude Code skill from https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"google-ai-edge-accuracy-safe-quantization\",\"task\":\"Install accuracy-safe-quantization\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"accuracy-safe-quantization\" from https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"google-ai-edge-accuracy-safe-quantization\",\"task\":\"Install accuracy-safe-quantization\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/google-ai-edge-accuracy-safe-quantization/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/google-ai-edge-accuracy-safe-quantization"},"trust":{"score":65,"label":"Manual review","version":"trust-score-v4","install_policy":"sandbox_only","evidence":{"stars":"416 GitHub stars","repoActivity":"416 stars, 116 forks","lastPushed":"3d since push","license":"Apache-2.0","repository":"https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization","install":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, shell or command execution","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"known_risks":["The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Dependency/runtime risk: command execution surface, credential or environment access","Permission surface: secrets or environment access, shell or command execution"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":76,"risk_level":"risky","risk_label":"Risky","warnings":["Dependency or permission surface needs review","Permission surface may require sandboxing","Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required","The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","SKILL.md references a separate skill (gpu-clean-conversion) without detailing its content, which may require the agent to have that context.","This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution"]},"safety_gate":{"tier":"blocked","label":"Blocked for auto-install","auto_install_policy":"block","auto_install_allowed":false,"human_review_required":true,"blocked":true,"recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first."},"quality":{"score":73,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"3d since push","risk":"Risky"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","Audit risk risky exceeds max_risk=medium","High-risk permission hints: Shell or command execution, Secrets or environment access","Dependency or permission surface needs review","Permission surface may require sandboxing","Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required"],"agent_contract":{"task_input":"Use accuracy-safe-quantization in an agent workflow","recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first.","install_policy":"block","minimum_review_before_use":["Trust: 65/100 Manual review","Audit: 76/100 Risky","Safety: 32/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"google-ai-edge-accuracy-safe-quantization (accuracy-safe-quantization)","install_command":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization","risk_summary":"Risky; Blocked for auto-install; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"google-ai-edge-accuracy-safe-quantization","task":"Use accuracy-safe-quantization in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/google-ai-edge-accuracy-safe-quantization","api":"https://www.openagentskill.com/api/agent/skills/google-ai-edge-accuracy-safe-quantization","audit":"https://www.openagentskill.com/skills/google-ai-edge-accuracy-safe-quantization/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=google-ai-edge-accuracy-safe-quantization&task=Use%20accuracy-safe-quantization%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20accuracy-safe-quantization%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20accuracy-safe-quantization%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/google-ai-edge-accuracy-safe-quantization/install","manifest":"https://www.openagentskill.com/api/registry/manifest/google-ai-edge-accuracy-safe-quantization"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"google-ai-edge-accuracy-safe-quantization","name":"accuracy-safe-quantization","description":"Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants.","category":"research","url":"https://www.openagentskill.com/skills/google-ai-edge-accuracy-safe-quantization","repository":"https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization","github_repo":"google-ai-edge/litert-samples"},"suited_tasks":["Browser automation workflows","Claude Code teams","builders willing to evaluate younger projects","Navigate pages","Click and type safely","Check visual and DOM state","Search sources","Extract claims"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add google-ai-edge-accuracy-safe-quantization"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"accuracy-safe-quantization\" agent skill from https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"google-ai-edge-accuracy-safe-quantization\",\"task\":\"Install accuracy-safe-quantization\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"accuracy-safe-quantization\" as a Claude Code skill from https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"google-ai-edge-accuracy-safe-quantization\",\"task\":\"Install accuracy-safe-quantization\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"accuracy-safe-quantization\" from https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"google-ai-edge-accuracy-safe-quantization\",\"task\":\"Install accuracy-safe-quantization\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/google-ai-edge-accuracy-safe-quantization/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/google-ai-edge-accuracy-safe-quantization"},"trust":{"score":65,"label":"Manual review","version":"trust-score-v4","install_policy":"sandbox_only","evidence":{"stars":"416 GitHub stars","repoActivity":"416 stars, 116 forks","lastPushed":"3d since push","license":"Apache-2.0","repository":"https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization","install":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, shell or command execution","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"known_risks":["The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Dependency/runtime risk: command execution surface, credential or environment access","Permission surface: secrets or environment access, shell or command execution"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":76,"risk_level":"risky","risk_label":"Risky","warnings":["Dependency or permission surface needs review","Permission surface may require sandboxing","Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required","The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","SKILL.md references a separate skill (gpu-clean-conversion) without detailing its content, which may require the agent to have that context.","This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution"]},"safety_gate":{"tier":"blocked","label":"Blocked for auto-install","auto_install_policy":"block","auto_install_allowed":false,"human_review_required":true,"blocked":true,"recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first."},"quality":{"score":73,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"3d since push","risk":"Risky"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","Audit risk risky exceeds max_risk=medium","High-risk permission hints: Shell or command execution, Secrets or environment access","Dependency or permission surface needs review","Permission surface may require sandboxing","Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required"],"agent_contract":{"task_input":"Use accuracy-safe-quantization in an agent workflow","recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first.","install_policy":"block","minimum_review_before_use":["Trust: 65/100 Manual review","Audit: 76/100 Risky","Safety: 32/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"google-ai-edge-accuracy-safe-quantization (accuracy-safe-quantization)","install_command":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization","risk_summary":"Risky; Blocked for auto-install; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"google-ai-edge-accuracy-safe-quantization","task":"Use accuracy-safe-quantization in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/google-ai-edge-accuracy-safe-quantization","api":"https://www.openagentskill.com/api/agent/skills/google-ai-edge-accuracy-safe-quantization","audit":"https://www.openagentskill.com/skills/google-ai-edge-accuracy-safe-quantization/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=google-ai-edge-accuracy-safe-quantization&task=Use%20accuracy-safe-quantization%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20accuracy-safe-quantization%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20accuracy-safe-quantization%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/google-ai-edge-accuracy-safe-quantization/install","manifest":"https://www.openagentskill.com/api/registry/manifest/google-ai-edge-accuracy-safe-quantization"}},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"research-agents","title":"Research agents"},{"slug":"testing-qa","title":"Testing and QA"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":416,"starsLabel":"416","forks":116,"license":"Apache-2.0","qualityScore":73,"trustScore":65,"auditScore":76},"maintenance":{"status":"fresh","label":"3d since push","daysSincePush":3,"lastPushedAt":"2026-09-03T21:51:36+00:00"},"risk":{"level":"risky","label":"Risky","requiresReview":true,"notes":["Dependency or permission surface needs review","Permission surface may require sandboxing","Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required","The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","SKILL.md references a separate skill (gpu-clean-conversion) without detailing its content, which may require the agent to have that context."]},"coverageTags":["Research","Research agents","agent-skill"]},"audit":{"audit_score":76,"risk_level":"risky","risk_label":"Risky","quality_score":73,"trust_score":65,"maintenance_score":100,"security_score":69,"install_score":92,"warnings":["Dependency or permission surface needs review","Permission surface may require sandboxing","Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required","The provided SKILL.md excerpt is truncated mid-sentence, but the complete content appears sufficient for evaluation.","SKILL.md references a separate skill (gpu-clean-conversion) without detailing its content, which may require the agent to have that context.","This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Dependency/runtime risk: command execution surface, credential or environment access","Permission surface: secrets or environment access, shell or command execution"]},"quality_signals":{"model":"v2","star_score":18.34,"usage_score":0,"review_score":5.4,"metadata_score":3,"freshness_score":15},"platforms":["Claude Code","OpenAI Agents"],"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"stacks":[{"slug":"browser-qa-agent","title":"Browser QA agent","url":"https://www.openagentskill.com/collections/browser-qa-agent"},{"slug":"research-report-agent","title":"Research report agent","url":"https://www.openagentskill.com/collections/research-report-agent"},{"slug":"frontend-product-ui","title":"Frontend and UI","url":"https://www.openagentskill.com/collections/frontend-product-ui"}],"install":"npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add google-ai-edge-accuracy-safe-quantization","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"accuracy-safe-quantization\" agent skill from https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"google-ai-edge-accuracy-safe-quantization\",\"task\":\"Install accuracy-safe-quantization\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"accuracy-safe-quantization\" as a Claude Code skill from https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"google-ai-edge-accuracy-safe-quantization\",\"task\":\"Install accuracy-safe-quantization\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"accuracy-safe-quantization\" from https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"google-ai-edge-accuracy-safe-quantization\",\"task\":\"Install accuracy-safe-quantization\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization","github_repo":"google-ai-edge/litert-samples","version":"1.0.0","license":"Apache-2.0","urls":{"web":"https://www.openagentskill.com/skills/google-ai-edge-accuracy-safe-quantization","repository":"https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization","api":"/api/agent/skills/google-ai-edge-accuracy-safe-quantization","install_api":"/api/skills/google-ai-edge-accuracy-safe-quantization/install"},"meta":{"created_at":"2026-08-26T20:35:22.99247+00:00","updated_at":"2026-09-04T03:47:53.855472+00:00","agent_friendly":true}}