全部能力

Generate type scales, color palettes, spacing systems, WCAG contrast checks, and dark mode derivations with math. Use when setting up a design system, creating…

Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review. Use when…

Extracts procedural content from project docs into slash commands. Use when docs contain deploy, test, or troubleshoot procedures.

Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a…

Autonomously improve a generated paper via GPT-5.4 xhigh review → implement fixes → recompile, for 2 rounds. Use when user says \"改论文\", \"improve paper\",…

Launches RFC and debate discussions on GitHub. Use when proposing changes that need community input or voting.

Use when searching academic papers, looking up citations, finding authors, or getting paper recommendations using the Semantic Scholar API. Triggers on queries…

Produces prioritized triage report from open GitHub issues, PRs, and discussions. Use when reviewing community backlog.

Search, summarize, and synthesize economics literature

Autonomous iterative research loop. Takes a topic, runs web searches, fetches sources, synthesizes findings, and files everything into the wiki as structured pages. Based on Karpathy's autoresearch pattern: program.md configures objectives and constraints, the loop runs until depth is reached, output goes directly into the knowledge base. Triggers on: "/autoresearch", "autoresearch", "research [topic]", "deep dive into [topic]", "investigate [topic]", "find everything about [topic]", "research and file", "go research", "build a wiki on".

Prepares meeting materials by gathering context from Notion, enriching with Claude research, and creating both an internal pre-read and external agenda saved…

Creates slash commands from procedural doc sections. Use when transforming documentation prose into executable commands.

Composes and publishes announcements to GitHub Discussions. Use when sharing releases, updates, or news with the community.

Generate a structured paper outline from review conclusions and experiment results. Use when user says \"写大纲\", \"paper outline\", \"plan the paper\",…

百度网盘(Baidu Drive)文件管理 — 上传、下载、转存、分享、搜索、移动、复制、重命名、创建文件夹。 同时支持 Agent 记忆备份/恢复（kimiclaw/maxclaw/qclaw/openclaw）。 TRIGGER: 用户提及"百度网盘/bdpan/网盘/云盘/baidu drive/Baidu Drive"并涉及文件操作； 或用户提及"备份记忆"、"恢复记忆"、"查看记忆备份"等记忆相关操作。 DO NOT TRIGGER: 非文件存储操作，或使用其他云盘服务时；本地记忆整理/清理操作；PPT 生成操作（已独立为 baidu-wenku-aippt skill）。

Cross-session learning system that extracts insights from session transcripts and injects relevant past learnings at session start. Uses simple keyword matching for relevance. Complements DISCOVERIES.md/PATTERNS.md with structured YAML storage.

Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). **Trigger when user asks to:** - Combine keyword and semantic search - Implement hybrid search or multi-modal retrieval - Use BM25/pg_textsearch with pgvector together - Implement RRF (Reciprocal Rank Fusion) for search - Build search that handles both exact terms and meaning **Keywords:** hybrid search, BM25, pg_textsearch, RRF, reciprocal rank fusion, keyword search, full-text search, reranking, cross-encoder Covers: pg_textsearch BM25 index setup, parallel query patterns, client-side RRF fusion (Python/TypeScript), weighting strategies, and optional ML reranking.

Find, organize, and manage files on the user's computer. Search by name, type, size, or date. Move, rename, compress, and clean up files.

Strategic job application planning and Resume SEO optimization. Approaches applications like marketing campaigns with market research, opportunity…

Responds to unanswered GitHub discussions and issues with codebase-informed replies. Use when clearing community question backlog.