Annuaire de skills
Chaque recommandation reste clairement reliée à son dépôt, son audit et son chemin d’installation.
TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.
Fast computer vision library for SFM, calibration, fiducials, tracking, image processing, and more.
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
Classify BIM elements using AI and standard classification systems. Map elements to UniFormat, MasterFormat, OmniClass, and CWICR codes.
Simultaneous localization and mapping using fiducial markers.
Hold every response to the ISO 24495 plain-language rules, and route to the sector skills. Codex has no output style, so these rules are a skill.
Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. Symptom of the underlying failure: elaborate theory accumulates to explain why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.
Raise real concurrency in asyncio LLM batch scorers built on the OpenAI SDK (AsyncOpenAI, including OpenAI-compatible providers like DeepSeek). Use when: (1) raising an asyncio.Semaphore above ~100 produces no throughput gain, (2) a batch pipeline saturates near 100 in-flight requests despite a larger semaphore, (3) planning a high-concurrency campaign against a provider with no hard rate limit (DeepSeek v4-flash tolerates 2000+ in flight). Root cause: AsyncOpenAI's default httpx pool caps max_connections at 100, silently bottlenecking any larger semaphore — you must pass a custom http_client with httpx.Limits sized to the semaphore.
>-
Pick an AI slide-deck skill and a concrete visual style from a curated registry, filtering on the requirements that decide it — editable in PowerPoint, speaker notes, a mandated corporate template, offline, PDF — with sample imagery and the style ids each project actually uses. Use when the user wants to make a presentation, deck or slides and has not already chosen a tool; asks which slide skill to use or what the difference between them is; wants to know what a style looks like before committing; or names a style id such as soft-editorial or swiss-grid. This skill routes to the skill that makes the deck — it does not make decks itself.
Research, diagnose, and draft Amazon Ads ASIN and category product-targeting plans that complement keyword targeting, including audience expansion, competitor and category traffic, cross-sell, upsell, self-defense, negative targeting, placement analysis, and single-variable experiments. Use for 商品投放, ASIN 定向, 品类定向, Product Targeting, 关键词引流遇到瓶颈, 关联流量, 互补品/替代品, 竞品详情页抢流量, 自家 ASIN 防御, Best Sellers/New Releases 候选, 自动与手动广告联动, or the local file named 如何提升关键词引流效率. Default to research and draft; verify current marketplace capabilities and never mutate live campaigns without explicit human approval.
Investigate and reduce SigNoz telemetry ingestion cost and metric cardinality across metrics, logs, and traces. Find what drives SigNoz spend (via the Cost Meter), which metrics have runaway or unbounded label cardinality, and safe, dashboard-, alert-, and Infra-page-aware ways to cut volume. Make sure to use this skill whenever the user asks "why is my SigNoz bill so high", "what's driving my ingestion cost", "reduce telemetry volume", "which metrics cost the most", "cardinality health check", or "what can I safely drop" — or otherwise asks about telemetry spend, ingestion volume, or metric cardinality, even if they don't say "cost" or "optimize" explicitly.
Annuaire de skills
Chaque recommandation reste clairement reliée à son dépôt, son audit et son chemin d’installation.
TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.
Fast computer vision library for SFM, calibration, fiducials, tracking, image processing, and more.
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
Classify BIM elements using AI and standard classification systems. Map elements to UniFormat, MasterFormat, OmniClass, and CWICR codes.
Simultaneous localization and mapping using fiducial markers.
Hold every response to the ISO 24495 plain-language rules, and route to the sector skills. Codex has no output style, so these rules are a skill.
Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. Symptom of the underlying failure: elaborate theory accumulates to explain why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.
Raise real concurrency in asyncio LLM batch scorers built on the OpenAI SDK (AsyncOpenAI, including OpenAI-compatible providers like DeepSeek). Use when: (1) raising an asyncio.Semaphore above ~100 produces no throughput gain, (2) a batch pipeline saturates near 100 in-flight requests despite a larger semaphore, (3) planning a high-concurrency campaign against a provider with no hard rate limit (DeepSeek v4-flash tolerates 2000+ in flight). Root cause: AsyncOpenAI's default httpx pool caps max_connections at 100, silently bottlenecking any larger semaphore — you must pass a custom http_client with httpx.Limits sized to the semaphore.
>-
Pick an AI slide-deck skill and a concrete visual style from a curated registry, filtering on the requirements that decide it — editable in PowerPoint, speaker notes, a mandated corporate template, offline, PDF — with sample imagery and the style ids each project actually uses. Use when the user wants to make a presentation, deck or slides and has not already chosen a tool; asks which slide skill to use or what the difference between them is; wants to know what a style looks like before committing; or names a style id such as soft-editorial or swiss-grid. This skill routes to the skill that makes the deck — it does not make decks itself.
Research, diagnose, and draft Amazon Ads ASIN and category product-targeting plans that complement keyword targeting, including audience expansion, competitor and category traffic, cross-sell, upsell, self-defense, negative targeting, placement analysis, and single-variable experiments. Use for 商品投放, ASIN 定向, 品类定向, Product Targeting, 关键词引流遇到瓶颈, 关联流量, 互补品/替代品, 竞品详情页抢流量, 自家 ASIN 防御, Best Sellers/New Releases 候选, 自动与手动广告联动, or the local file named 如何提升关键词引流效率. Default to research and draft; verify current marketplace capabilities and never mutate live campaigns without explicit human approval.
Investigate and reduce SigNoz telemetry ingestion cost and metric cardinality across metrics, logs, and traces. Find what drives SigNoz spend (via the Cost Meter), which metrics have runaway or unbounded label cardinality, and safe, dashboard-, alert-, and Infra-page-aware ways to cut volume. Make sure to use this skill whenever the user asks "why is my SigNoz bill so high", "what's driving my ingestion cost", "reduce telemetry volume", "which metrics cost the most", "cardinality health check", or "what can I safely drop" — or otherwise asks about telemetry spend, ingestion volume, or metric cardinality, even if they don't say "cost" or "optimize" explicitly.
Annuaire de skills
Chaque recommandation reste clairement reliée à son dépôt, son audit et son chemin d’installation.
TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.
Fast computer vision library for SFM, calibration, fiducials, tracking, image processing, and more.
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
Classify BIM elements using AI and standard classification systems. Map elements to UniFormat, MasterFormat, OmniClass, and CWICR codes.
Simultaneous localization and mapping using fiducial markers.
Hold every response to the ISO 24495 plain-language rules, and route to the sector skills. Codex has no output style, so these rules are a skill.
Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. Symptom of the underlying failure: elaborate theory accumulates to explain why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.
Raise real concurrency in asyncio LLM batch scorers built on the OpenAI SDK (AsyncOpenAI, including OpenAI-compatible providers like DeepSeek). Use when: (1) raising an asyncio.Semaphore above ~100 produces no throughput gain, (2) a batch pipeline saturates near 100 in-flight requests despite a larger semaphore, (3) planning a high-concurrency campaign against a provider with no hard rate limit (DeepSeek v4-flash tolerates 2000+ in flight). Root cause: AsyncOpenAI's default httpx pool caps max_connections at 100, silently bottlenecking any larger semaphore — you must pass a custom http_client with httpx.Limits sized to the semaphore.
>-
Pick an AI slide-deck skill and a concrete visual style from a curated registry, filtering on the requirements that decide it — editable in PowerPoint, speaker notes, a mandated corporate template, offline, PDF — with sample imagery and the style ids each project actually uses. Use when the user wants to make a presentation, deck or slides and has not already chosen a tool; asks which slide skill to use or what the difference between them is; wants to know what a style looks like before committing; or names a style id such as soft-editorial or swiss-grid. This skill routes to the skill that makes the deck — it does not make decks itself.
Research, diagnose, and draft Amazon Ads ASIN and category product-targeting plans that complement keyword targeting, including audience expansion, competitor and category traffic, cross-sell, upsell, self-defense, negative targeting, placement analysis, and single-variable experiments. Use for 商品投放, ASIN 定向, 品类定向, Product Targeting, 关键词引流遇到瓶颈, 关联流量, 互补品/替代品, 竞品详情页抢流量, 自家 ASIN 防御, Best Sellers/New Releases 候选, 自动与手动广告联动, or the local file named 如何提升关键词引流效率. Default to research and draft; verify current marketplace capabilities and never mutate live campaigns without explicit human approval.
Investigate and reduce SigNoz telemetry ingestion cost and metric cardinality across metrics, logs, and traces. Find what drives SigNoz spend (via the Cost Meter), which metrics have runaway or unbounded label cardinality, and safe, dashboard-, alert-, and Infra-page-aware ways to cut volume. Make sure to use this skill whenever the user asks "why is my SigNoz bill so high", "what's driving my ingestion cost", "reduce telemetry volume", "which metrics cost the most", "cardinality health check", or "what can I safely drop" — or otherwise asks about telemetry spend, ingestion volume, or metric cardinality, even if they don't say "cost" or "optimize" explicitly.
Annuaire de skills
Chaque recommandation reste clairement reliée à son dépôt, son audit et son chemin d’installation.
TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.
Fast computer vision library for SFM, calibration, fiducials, tracking, image processing, and more.
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
Classify BIM elements using AI and standard classification systems. Map elements to UniFormat, MasterFormat, OmniClass, and CWICR codes.
Simultaneous localization and mapping using fiducial markers.
Hold every response to the ISO 24495 plain-language rules, and route to the sector skills. Codex has no output style, so these rules are a skill.
Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. Symptom of the underlying failure: elaborate theory accumulates to explain why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.
Raise real concurrency in asyncio LLM batch scorers built on the OpenAI SDK (AsyncOpenAI, including OpenAI-compatible providers like DeepSeek). Use when: (1) raising an asyncio.Semaphore above ~100 produces no throughput gain, (2) a batch pipeline saturates near 100 in-flight requests despite a larger semaphore, (3) planning a high-concurrency campaign against a provider with no hard rate limit (DeepSeek v4-flash tolerates 2000+ in flight). Root cause: AsyncOpenAI's default httpx pool caps max_connections at 100, silently bottlenecking any larger semaphore — you must pass a custom http_client with httpx.Limits sized to the semaphore.
>-
Pick an AI slide-deck skill and a concrete visual style from a curated registry, filtering on the requirements that decide it — editable in PowerPoint, speaker notes, a mandated corporate template, offline, PDF — with sample imagery and the style ids each project actually uses. Use when the user wants to make a presentation, deck or slides and has not already chosen a tool; asks which slide skill to use or what the difference between them is; wants to know what a style looks like before committing; or names a style id such as soft-editorial or swiss-grid. This skill routes to the skill that makes the deck — it does not make decks itself.
Research, diagnose, and draft Amazon Ads ASIN and category product-targeting plans that complement keyword targeting, including audience expansion, competitor and category traffic, cross-sell, upsell, self-defense, negative targeting, placement analysis, and single-variable experiments. Use for 商品投放, ASIN 定向, 品类定向, Product Targeting, 关键词引流遇到瓶颈, 关联流量, 互补品/替代品, 竞品详情页抢流量, 自家 ASIN 防御, Best Sellers/New Releases 候选, 自动与手动广告联动, or the local file named 如何提升关键词引流效率. Default to research and draft; verify current marketplace capabilities and never mutate live campaigns without explicit human approval.
Investigate and reduce SigNoz telemetry ingestion cost and metric cardinality across metrics, logs, and traces. Find what drives SigNoz spend (via the Cost Meter), which metrics have runaway or unbounded label cardinality, and safe, dashboard-, alert-, and Infra-page-aware ways to cut volume. Make sure to use this skill whenever the user asks "why is my SigNoz bill so high", "what's driving my ingestion cost", "reduce telemetry volume", "which metrics cost the most", "cardinality health check", or "what can I safely drop" — or otherwise asks about telemetry spend, ingestion volume, or metric cardinality, even if they don't say "cost" or "optimize" explicitly.