Loading...
Loading...
Found 298 Skills
Combines search results from multiple sources into coherent, deduplicated answers with source attribution. Handles confidence scoring based on freshness and authority, and summarizes large result sets effectively.
Summarize recent compound-engineering plugin releases, or answer a specific question about a past release with a version citation. Use when the user types `/ce-release-notes` or asks "what changed in compound-engineering recently?" or "what happened to `<skill-name>`?".
Summarize the last N agent sessions for the current project, grouped by date. Use when the user asks "recap", "what have we been doing", "this week", "today", or wants a rollup of recent work.
Preserve critical session state when compacting context. Use when context window is filling up and you need to summarize/reduce while keeping essential debugging information.
Search and summarize papers from ArXiv. Use when the user asks for the latest research, specific topics on ArXiv, or a daily summary of AI papers.
This skill should be used when the user asks to maintain an Obsidian knowledge base for a research project, import an existing research repository into Obsidian, keep project memory or daily notes synchronized, summarize project context into durable notes, or update experiments, results, papers, writing, and plans in an Obsidian vault without requiring MCP.
Turn a completed experiment iteration into an honest, evidence-backed analysis — a markdown report and a portable data dump. Pulls run data via the tpc CLI, scores each task, clusters friction by root cause (with a transcript example per claim), compares arms, and closes on agent-readiness gaps. The natural companion to setup-experiment: setup → run → analyze. Trigger when users say: "analyze my experiment", "write the report", "experiment report", "analyze the results", "summarize the runs", "what happened in this iteration", "friction report", or "report gen".
Use when structuring app entry points, managing authentication flows, switching root views, handling scene lifecycle, or asking 'how do I structure my @main', 'where does auth state live', 'how do I prevent screen flicker on launch', 'when should I modularize' - app-level composition patterns for iOS 26+
Git workflow helper for conventional commits, confidence-scored code review, and pull request management. Use when: committing changes, reviewing code, creating PRs, generating PR descriptions, analyzing diffs. Triggers on "commit", "review", "push", "create PR", "PR description", "summarize changes".
Robust URL-to-Markdown extraction for OpenClaw workflows. Use this when the user needs to "extract/summarize/convert a webpage to Markdown" (especially for WeChat official accounts at mp.weixin.qq.com) and web_fetch or browser access is blocked or returns messy content. It first uses a low-cost probe via web_fetch, then falls back to the official MinerU API (through the local mineru-extract skill), and returns a traceable result contract with source links.
Feishu chat browsing, message interaction and group chat management. View chat history, obtain group chat historical messages, search group chats, get message details, Reaction emoji responses, Pin pin/unpin, delete messages, group chat information query and management (obtain/update/dissolve/member management). Supports two modes: regular groups and topic groups, with automatic thread reply retrieval for topic groups. All commands require a User Token. Use this skill when users request "view chat history", "check messages with someone", "group chat history", "group messages", "search group chats", "check group information", "group members", "recent messages", "chat history", "Reaction", "emoji response", "pin message", "Pin", "delete message", "get message", "message details", "what was talked about with whom", "what was discussed in the group", "summarize group messages", "topic replies", "thread replies", or "thread replies". It also applies to scenarios where users provide a group chat name or chat_id and want to browse its messages, even if they don't explicitly say "chat history". This skill should be used when users want to know what a group has been discussing recently, find conversation content with someone, or perform interactive operations on messages.
Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl) and per-user profiles across runs, with privacy guardrails baked in. Use when the user asks to "总结群聊", "群聊精华", "群聊摘要", "summarize group chat", "group chat digest", mentions a WeChat group name with a time range, says "帮我看看 XX 群最近聊了什么", "XX 群有什么值得看的", or asks to "回溯画像" / "初始化画像" / "backfill profiles". Adds the roast version when the user says "毒舌版", "roast 版", "再来个毒舌的", or similar.