AI Agent Skills

Use the notebook knowledge base (the local SQLite RAG /agy:notebook builds from a folder of documents) to do precise, grounded, cited work — total amounts by category, f…

Build human adjudication / hand-labeling sheets from LLM-pipeline data without evidence truncation. Use when: (1) preparing a CSV/Excel sheet for a human to rule on case…

Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human l…

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…

Use when building ML/AI apps in Rust. Keywords: machine learning, ML, AI, tensor, model, inference, neural network, deep learning, training, prediction, ndarray, tch-rs,…

Vector search with SurrealDB using HNSW indexes, KNN queries, and similarity scoring. Use when creating vector indexes, querying vectors with KNN distance operators, bui…

Official Cohere TypeScript SDK patterns -- CohereClientV2, chat, embeddings, rerank, RAG with citations, tool use, streaming, and model selection

Attacker's-eye test of LLM/agent defenses: instruction hijacking, data exfiltration and tool abuse through untrusted content; verifies whether the defense actually holds.

Use when a task depends on tech you don't actually know, an unfamiliar library, a fast-moving framework, a tricky API, an unfamiliar codebase: or whenever "I think it wo…

Review public site content for editorial quality, source support, prompt residue, duplicate blocks, translation drift, hidden filler, and human usefulness before SEO or…

Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural langu…

Use when running or configuring `xmake ai` — the terminal coding agent provided by the xmake-harness addon. Covers installing it, setting an llm provider and api key, se…

Theoretical foundations of Working, Semantic, and Episodic memory systems for autonomous agents.

Best practices for dataset preparation and PEFT/LoRA fine-tuning.

Use a shadow knowledge base to understand any codebase. The .shadow/ directory mirrors the source tree with markdown files containing behavioral insights — know

Update the shadow knowledge base after code changes and from conversational insights. Detects what changed via git diff, refreshes per-file shadows, captures kn