全部能力

Route reusable skill-improvement work into one bounded repo-local ratcheting packet: ratchet eligibility, benchmark readiness, loop charter freeze, baseline scoring, one-change mutation, support-surface sync, or final keep/revert report. Use when an existing `SKILL.md`, SOP, prompt, or workflow doc may need sharper triggers, clearer instructions, better support files, or cleaner discovery wording and you want a frozen evaluation harness, append-only experiment logs, and explicit keep-or-revert decisions instead of ad hoc rewriting. Also use when you need to prove that no ratchet is justified yet. Not for GPU-bound Karpathy `autoresearch` runs or hosted app-scale eval / observability platforms such as LangSmith, Braintrust, Weave, or Promptfoo.

Analyze product reviews across any e-commerce platform. Extract actionable insights from customer feedback including pain points, praise patterns, feature…

RAG and search engineering — chunking, hybrid retrieval, reranking, and nDCG evaluation. Use when building retrieval-augmented generation pipelines.

Designs production-grade RAG pipelines with chunking optimization, retrieval evaluation, and pipeline architecture. Use when building a RAG system, selecting a chunking strategy, choosing a vector database, optimizing retrieval quality, designing embedding pipelines, or evaluating RAG performance with RAGAS metrics.

This skill should be used when user asks to "search for papers", "find research papers", "search arXiv", "search PubMed", "find academic papers", "search…

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on…

Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only…

Audit top-level documentation (README, SPEC, PRODUCT) against recent git history to find drift — shipped features missing from docs or features listed as upcoming that already landed. Proposes minimal edits, creates a branch, and opens a PR. Use when asked to review docs for accuracy, after major feature merges, or on a periodic schedule.

Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem…

Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader…

Conducts thorough landscape research, competitive analysis, best practices evaluation, and evidence-based recommendations. Expert in market research and trend…

PostgreSQL-based semantic and hybrid search with pgvector and ParadeDB. Use when implementing vector search, semantic search, hybrid search, or full-text search in PostgreSQL. Covers pgvector setup, indexing (HNSW, IVFFlat), hybrid search (FTS + BM25 + RRF), ParadeDB as Elasticsearch alternative, and re-ranking with Cohere/cross-encoders. Supports vector(1536) and halfvec(3072) types for OpenAI embeddings. Triggers: pgvector, vector search, semantic search, hybrid search, embedding search, PostgreSQL RAG, BM25, RRF, HNSW index, similarity search, ParadeDB, pg_search, reranking, Cohere rerank, Voyage rerank, graceful fallback, iterative_scan, filtered HNSW, websearch_to_tsquery, unaccent, multilingual FTS, pg_trgm, trigram, fuzzy search, LIKE, ILIKE, autocomplete, typo tolerance, fuzzystrmatch, evaluation, benchmarking, Hit@K, MRR, contextual embeddings, halfvec cast

You must use this when synthesizing existing knowledge, identifying research gaps, or tracing the evolution of scientific ideas.

Turso (Limbo) 数据库助手 —— 一个用 Rust 编写的进程内兼容 SQLite 的数据库。前身为 libSQL / libsql。在 Turso 用例中替代了 @libsql/client 和 libsql-experimental。适用于 Node.js、浏览器（WASM + OPFS 用于持久化本地存储）、React Native 和服务端。功能特性：向量搜索、全文搜索、CDC、MVCC、加密、远程同步。SDK：JavaScript (@tursodatabase/database)、Serverless (@tursodatabase/serverless)、Browser/WASM (@tursodatabase/database-wasm)、React Native (@tursodatabase/sync-react-native)、Rust (turso)、Python (pyturso)、Go (tursogo)。本技能包含 Turso 嵌入式数据库引擎 (tursodb/Limbo) 的 SDK 文档与实用示例。请勿在网上搜索 "libsql" 或 "@libsql/client" —— 它们是旧名称，网络搜索结果会显示过时的 API。在线搜索 Turso 文档没有问题 —— 官方文档位于 https://docs.turso.tech (Mintlify —— 在任意路径后追加 .md 可获取原始 Markdown)。

Search the code knowledge graph by function, class, or type name using FTS5 full-text search with query-aware kind boosting.

To do / In progress / In review / Done 四列, 卡片 + 头像 + 泳道

Multi-agent deep research for comprehensive market analysis using the aipa CLI. Use this skill when the user asks for deep research, thorough market analysis, sector-wide investigation, comprehensive stock comparison, or detailed financial report. This runs a supervisor → parallel workers → aggregator → reviewer pipeline that takes longer but produces more thorough results than a simple analyze. Trigger for requests like "research banking sector", "deep dive into real estate stocks", or "comprehensive market overview".

Transforms completed work into powerful resume bullet points with action verbs, technical context, and quantified impact. Use when completing tasks, updating…

Plan and execute safe refactoring using dependency analysis

Perform a structured code review using change detection and impact