Loading...
Loading...
Found 2,228 Skills
Create pull requests on GitHub using GitHub MCP, GitHub CLI (gh), or the GitHub REST API. Use this skill when the user wants to submit changes as a pull request, following repository standards and templates.
8-agent QA loop: browser exploration via Playwright MCP, then analyze, plan, test, audit, heal, expand, snapshot. Quality gate score >= 85 to pass.
Bootstrap new projects with curated settings.local.json permissions, CLAUDE.md, and .gitignore. Detects project type (cloudflare-worker, vercel-app, node-generic, python, ops-admin) and generates grouped, commented permission presets. Also tidies existing messy settings files (removes leaked secrets, shell fragments, deprecated MCP refs, duplicate entries). Trigger with 'kickoff', 'new project', 'bootstrap', 'setup claude', 'tidy permissions', 'clean settings', or 'init project'.
Executes browser-based user workflows from /workflows/browser-workflows.md using Claude-in-Chrome MCP. Use this when the user says "run browser workflows", "execute browser workflows", or "test browser workflows". Tests each workflow step by step, captures before/after screenshots, documents issues, and generates HTML reports with visual evidence of fixes.
[Tooling & Meta] Claude Code CLI setup, configuration, troubleshooting, and feature guidance. Triggers on claude code setup, hook not firing, MCP connection, context limit, skill creation, slash command setup.
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"call API", "check response", "query results", "find TODOs", "count lines", "codebase statistics", "security audit", "outdated packages", "dependency tree", "cloud resources", "CI/CD output".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.
Exchange listing tracker. Use this skill whenever the user asks about exchange listing, delisting, or maintenance announcements. Trigger phrases include: any new coins listed recently, what did Binance list, new listings, delisted. MCP tools: news_feed_get_exchange_announcements, info_coin_get_coin_info, info_marketsnapshot_get_market_snapshot.
General web search and content extraction skill. It supports multi-source parallel search (WebSearch, MCP search tools, ctx7, agent-browser), web page main content extraction (defuddle/WebFetch) and structured article analysis. This skill is used when users need to search for information, research topics, find materials, obtain web content, read articles, or analyze web pages. Trigger scenarios include: search, research, investigation, fetch, check for me, help me find, read this link, analyze this article. Even if the user doesn't explicitly say "search", this skill should be triggered as long as it involves information acquisition and web content processing.
Review existing Perses dashboards for quality: fetch via MCP or API, analyze panel layout, query efficiency, variable usage, datasource configuration. Generate improvement report. Optional --fix mode. 4-phase pipeline: FETCH, ANALYZE, REPORT, FIX. Use for "review perses dashboard", "audit dashboard", "perses dashboard quality". Do NOT use for creating new dashboards (use perses-dashboard-create).
Use after analyze-and-document has generated CLAUDE.md for an AI Studio project. Installs project-level Claude Code configuration — rules, skills, settings, and optionally agents, hooks, and MCP servers — into the .claude/ directory so that all future sessions have the right guardrails and workflows.
Analysis of Lanhu design drafts and Axure prototypes. Directly read prototype pages, design drafts, and slice resources of Lanhu projects via lanhu MCP Server. Trigger scenarios: - Need to obtain Axure prototype pages from Lanhu for requirement analysis - Need to view Lanhu UI design drafts and design parameters - Need to extract slice resources from Lanhu design drafts - Need to collaborate via Lanhu team message board - Need to parse Lanhu invitation links Trigger words: Lanhu, lanhu, design draft, prototype, Lanhu link, design image, slice
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for prompt-injection, retrieval poisoning, memory contamination, planner drift, MCP or tool-boundary abuse, and agent exfiltration challenges. Use when the user asks to analyze prompt injection, retrieval poisoning, memory contamination, planner drift, tool-argument corruption, or secret exposure caused by an agent chain. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.