全部能力

Plan and optimize resource allocation. Trigger with "resource planning", "capacity", "utilization", "staffing plan", "who should work on what", "we're…

Clarify ambiguous or conflicting requests by researching first, then exhaustively interrogating assumptions, constraints, dependencies, trade-offs, edge cases, and failure modes before any planning or implementation. Use when prompts say "$grill-me" or "grill me", ask hard questions, request relentless interrogation, pressure-test assumptions, clarify scope or requirements, define success criteria, or request product/system-design decisions before implementation. Respond in the user's language. Stop before implementation.

Use this skill when designing help center architecture, writing support articles, or optimizing search and self-service. Triggers on knowledge base, help center, support articles, self-service, article templates, search optimization, content taxonomy, and any task requiring help documentation design or management.

Search ClinicalTrials.gov with natural language queries. Find clinical trials, enrollment, and outcomes using Valyu semantic search.

Converts documents into clean, chunked datasets suitable for embeddings and vector search. Produces chunked JSONL files with metadata, deduplication logic, and…

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

Compile a LaTeX project and run basic QA (missing refs, bib errors, broken citations), producing `latex/main.pdf` and a build report. **Trigger**: latex compile, build PDF, LaTeX errors, missing refs, 编译PDF, 引用错误. **Use when**: 已有 `latex/main.tex`（通常来自 `latex-scaffold`），需要确认可编译并输出失败原因报告。 **Skip if**: 还没有 LaTeX scaffold（先跑 `latex-scaffold`）。 **Network**: none. **Guardrail**: 编译失败也要落盘 `output/LATEX_BUILD_REPORT.md`；不做“内容改写”，只做编译/QA。

Expert knowledge for Azure Monitor development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas,…

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

Knowledge management skill for capturing, classifying, searching, and syncing project knowledge. Use when storing learnings, syncing BKD issue outcomes, or…

Document undocumented public APIs in PyTorch by removing functions from coverage_ignore_functions and coverage_ignore_classes in docs/source/conf.py, running…

Research and extract an engineer's coding style, patterns, and best practices from their GitHub contributions. Creates structured knowledge base for…

当用户要求“头脑风暴研究想法”、“使用5W1H框架”、“识别研究空白”、“进行差距分析”、“开始…

Use when text embeddings are needed from Alibaba Cloud Model Studio models for semantic search, retrieval-augmented generation, clustering, or offline…

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)。

Generate comprehensive equity research snapshots combining analyst consensus estimates, company fundamentals, historical prices, and macroeconomic context. Use…

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

Use when invalid data causes failures deep in execution - validates at every layer data passes through to make bugs structurally impossible rather than…

Read TradingView desktop app for market data, news, alerts, watchlists, and screener results using opencli (read-only). Use this skill whenever the user wants quotes, options chains, options expiries, screener results across stocks/crypto/forex/futures/bonds, gainers/losers/movers, news headlines or full story bodies, alerts (active list, fire log, offline fires), watchlists including colored flag lists, symbol search/autocomplete, chart state, or screenshots from their local TradingView.app. Triggers include: "options chain for X", "IV on Y", "show me SNDK puts", "TV screener for Y sector", "screen oversold stocks", "TV gainers", "crypto by market cap", "TradingView news on AAPL", "show my watchlists", "red flag list", "list my alerts", "what alerts fired", "search TV for nvidia", "what symbol is on my chart", "screenshot NVDA chart", "TradingView IV skew", "TV expiries for X". This skill is READ-ONLY — it does NOT place trades, modify watchlists, or change chart layouts.