Loading...
Loading...
Found 304 Skills
Compress long conversation histories, large code files, research results, and documents by 70% without losing critical information. Triggers when context window fills up, when summarizing previous steps in multi-step tasks, before loading large files into context, or on "summarize", "compress", "reduce context", "save tokens".
Summarize current work, commit, push, and create or update a PR. Automatically write conversation context into the PR description to ensure reviewers can quickly understand the background.
Email Gazette: Transform unread inbox emails into a beautiful newspaper-style HTML front page. Use this skill whenever the user asks for an email briefing, inbox summary, email digest, morning briefing, 'what happened in my inbox', 'catch me up on emails', 'summarize my emails', or anything about turning emails into a readable overview. Also trigger when the user mentions 'gazette' or asks for a newspaper-style view of their emails, daily digest, or email newspaper.
Use context-mode tools (ctx_execute, ctx_execute_file) instead of Bash/cat when processing large outputs. Triggers: "analyze logs", "summarize output", "process data", "parse JSON", "filter results", "extract errors", "check build output", "analyze dependencies", "process API response", "large file analysis", "page snapshot", "browser snapshot", "DOM structure", "inspect page", "accessibility tree", "Playwright snapshot", "run tests", "test output", "coverage report", "git log", "recent commits", "diff between branches", "list containers", "pod status", "disk usage", "fetch docs", "API reference", "index documentation", "call API", "check response", "query results", "find TODOs", "count lines", "codebase statistics", "security audit", "outdated packages", "dependency tree", "cloud resources", "CI/CD output". Also triggers on ANY MCP tool output that may exceed 20 lines. Subagent routing is handled automatically via PreToolUse hook.
💰 Save Token | Token 节省器 TRIGGERS: Use when token cost is high, conversation is long, files read multiple times, or before complex tasks. Guiding skill that helps agents identify and avoid sending duplicate context to LLM APIs. Teaches agents to recognize repeated content and summarize instead of re-sending. 触发条件：Token 成本高、对话长、文件多次读取、复杂任务前。 指导 Agent 识别重复内容，避免重复发送，从而节省 Token。
Interact with GitLab via the glab CLI. Supports five MR workflows — Read (summarize), Review (full code/security/QA review), Fix (review + implement), CI Fix (fix pipeline failures), and Feedback (address review comments). Trigger whenever the user provides a GitLab MR URL or says anything like "อ่าน MR", "ดู MR", "check MR", "review MR", "ช่วย review MR นี้", "ตรวจ MR", "แก้ตาม MR", "fix MR", "fix CI", "fix pipeline", "แก้ pipeline", "แก้ตาม comment", "แก้ตาม feedback", "address feedback", or just pastes a GitLab MR URL. Also supports listing MRs, viewing MR status, checking CI/CD pipelines, approving MRs, and other glab operations. Trigger on "check pipeline", "list open MRs", "pipeline failed", or any GitLab-related task.
Transform dense technical communication into clear, structured business formats using proposition extraction and deterministic templates. Use when user needs to convert technical updates, debugging narratives, status reports, or dependency discussions into executive-ready summaries. Use for "transform this update", "make this executive-ready", "summarize for my manager", "professional format", or "status report". Do NOT use for writing new content from scratch, creative writing, or generating documentation that doesn't transform an existing input.
General Technical Design Document Summarization Skill: Scan documents and diagrams in the current execution directory (Markdown, PlantUML/Mermaid, drawio, images, etc.), extract system objectives, module boundaries, core processes, sequences and states, and output structured technical design documents. Use this skill when users mention "technical design documents", "solution sorting", "summarize design based on existing documents", "summarize documents and diagrams in the directory", or "complete sequence diagrams/state diagrams".
Summarizes very long texts (books, handbooks, biographies, codebases) using hierarchical multi-pass extraction with cheap model armies. Produces structured knowledge maps, not just summaries. Use when processing 50+ page documents, professional handbooks, career biographies, or any text too large for a single context window. Activate on "summarize book", "summarize handbook", "long document", "extract knowledge", "distill text", "professional biography". NOT for short text summarization (<10 pages), real-time chat summarization, or code documentation (use technical-writer).
Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.
This skill analyzes meeting transcripts to extract decisions, action items, opinions, questions, and terminology using Cerebras AI (llama-3.3-70b). Use this skill when the user asks to analyze a transcript, extract action items from meetings, find decisions in conversations, build glossaries from discussions, or summarize key points from recorded meetings.
Use when the user wants to continue work from one agent in another agent, inspect recent sessions, or summarize a saved session or checkpoint for handoff