xurl
A CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.
youtube-transcript
Download YouTube video transcripts when user provides a YouTube URL or asks to download/get/fetch a transcript from YouTube. Also use when user wants to transcribe or get captions/subtitles from a YouTube video.
development-brainstorming
Use when planning software development tasks, before writing code or implementation plans - refines rough technical ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. For software architecture, components, data flow, and technical design decisions. Don't use during clear 'mechanical' coding processes
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
git-pushing
Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", "push this", "push to github", or similar git workflow requests.
github
GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.
supabase-postgres-best-practices
Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
nano-pdf
使用自然语言指令通过 nano-pdf CLI 编辑 PDF。支持修改标题、修复拼写错误等快速 PDF 编辑操作。
notebooklm
使用此技能直接从 Claude 中查询您的 Google NotebookLM 笔记本，以获取来自 Gemini 的基于来源、有引用支持的答案。支持浏览器自动化、库管理和持久身份验证。通过仅基于文档的响应大幅减少幻觉问题。
notion
使用 Notion API 创建和管理页面、数据库（数据源）和区块。支持 Notion 内容的增删改查，是知识管理工作流的核心集成。
trello
通过 Trello REST API 管理 Trello 看板、列表和卡片。支持任务追踪、协作和看板自动化，是项目管理工作流的核心工具。
weather
通过 wttr.in 或 Open-Meteo 获取当前天气和预报。适用于：用户询问天气、温度或任何地点的预报。不适用于：历史天气数据、极端天气警报或详细的气象分析。无需 API 密钥。
video-frames
使用 ffmpeg 从视频中提取帧或短视频片段。支持按时间戳截取图片，适用于视频预览和 UI 分析。
excalidraw-diagram
Generate Excalidraw diagrams from text content for Obsidian. Use when user asks to create diagrams, flowcharts, mind maps, or visual representations in Excalidraw format. Triggers on "Excalidraw", "画图", "流程图", "思维导图", "可视化", "diagram".
defuddle
Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.
Anthropic-brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
markdown-to-epub-converter
Convert markdown documents and chat summaries into formatted EPUB ebook files that can be read on any device or uploaded to Kindle.
md-to-pdf
Use this skill when users want to convert Markdown files to PDF. Handles workflows like "Convert this markdown to PDF", "转换为PDF", "批量转换MD文件". Supports single file and batch directory conversion with excellent CJK (Chinese) font support, image embedding, and clean typography.
nlm-skill
Expert guide for the NotebookLM CLI (`nlm`) and MCP server - interfaces for Google NotebookLM. Use this skill when users want to interact with NotebookLM programmatically, including: creating/managing notebooks, adding sources (URLs, YouTube, text, Google Drive), generating content (podcasts, reports, quizzes, flashcards, mind maps, slides, infographics, videos, data tables), conducting research, chatting with sources, or automating NotebookLM workflows. Triggers on mentions of \"nlm\", \"notebooklm\", \"notebook lm\", \"podcast generation\", \"audio overview\", or any NotebookLM-related automation task.
remotion-best-practices
Best practices for Remotion - Video creation in React
developer-growth-analysis
Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, generating a personalized growth report with actionable recommendations.
csv-data-summarizer
Analyzes CSV files, generates summary stats, and plots quick visualizations using Python and pandas.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
pm
Project management with PDCA cycles, confidence checks, and context persistence. Auto-activates at session start to restore context. Use for task planning, progress tracking, and structured development.
troubleshoot
Systematic troubleshooting with root cause analysis. Use when users report errors, bugs, or unexpected behavior. Never retry without understanding why.
Confidence Check
Pre-implementation confidence assessment (≥90% required). Use before starting any implementation to verify readiness with duplicate check, architecture compliance, official docs verification, OSS references, and root cause identification.
token-efficiency
Activate ultra-compressed output mode for maximum token efficiency. Use when context is running low, user requests brevity, or dealing with large-scale operations.
deep-research
Activate deep research mode for systematic investigation. Use when the user asks to research, investigate, explore, or needs current information with citations.
brainstorm
Activate brainstorming mode for collaborative discovery and creative problem-solving. Use when users have vague requests, want to explore ideas, or need requirements discovery.
pr-review
This skill processes unresolved GitHub PR review discussions. Activated when the user provides a GitHub PR link (github.com/.../pull/...) or mentions "PR review", "review PR", "process review comments", etc.
rename-branch
This skill should be used when the user asks to "rename branch", "change branch name", "update branch name based on changes", or wants to create a meaningful branch name based on the changes.
review-and-fix
Pre-push CodeRabbit review-fix loop. Runs local CodeRabbit review, fixes valid issues, and repeats until clean so the branch passes CodeRabbit review on push with no additional comments. Use when the user says "review and fix", "review loop", or wants to ensure the branch is CodeRabbit-clean before pushing.
session-handoff
List and resume previous coding agent sessions by loading their context into the current session. Use when the user wants to (1) see previous sessions for the current directory with summaries, (2) continue work from a previous session by loading its full conversation context, (3) recover work from an interrupted session, or (4) transfer context between sessions. Supports Claude Code and Codex sessions.
standup
Draft a daily standup from the current user's Slack, GitHub, Linear, and Google Calendar activity. Use when the user asks to create, prepare, or summarize a standup/status update from connected app activity; to collect a user's work for a date; or to verify whether Slack, GitHub, Linear, and Google Calendar connectors/MCP tools are available before drafting a standup.
tech-spec-review
Review a tech spec document written in the team's Notion template format (Summary, Background, Goals, Non-Goals, Plan, Measuring Impact, Security/Privacy/Risks, Other Considerations, Milestones, Open Questions). Use when the user asks to "테크 스펙 리뷰", "tech spec 리뷰", "스펙 문서 리뷰", "이 스펙 봐줘", or provides a Notion/Google Docs/Markdown tech spec link or file and asks for feedback, critique, or readiness check before sharing with the team.
commit
This skill should be used when the user asks to "commit changes", "make a commit", "commit staged files", "create a commit with conventional commit format", or mentions committing code following conventional commit convention.
hwp
This skill should be used when the user wants to view contents of HWP/HWPX files (Korean word processor documents), mentions ".hwp" or ".hwpx" file paths, asks to "read hwp", "read hwpx", "open hwp", "open hwpx", or needs to extract text from Korean word processor documents.
autofix
Fetch and fix CodeRabbit review feedback interactively or in a batch while preserving the latest user-agreed PR purpose. Review suggestions are evidence, not authority to change required behavior.
branch-review
Review the current Git branch against origin/main, including committed, staged, unstaged, and untracked changes. Use when the user asks to review a branch, inspect branch changes before merge, or perform a comprehensive code review of the current working branch.
code-review
Review code or PR diffs with CodeRabbit and repository evidence for correctness, quality, and security. Validate findings against the latest user-agreed purpose. Keep review-only requests read-only; fix only verified in-scope defects without changing the task contract.
create-pull-request
Create a GitHub pull request following project conventions. Use when the user asks to create a PR, submit changes for review, or open a pull request. Handles commit analysis, branch management, and PR creation using the gh CLI tool.
review-logging-patterns
Review code for logging patterns and suggest evlog adoption. Optionally use @evlog/cli (`evlog init` to wire evlog, `evlog agents` to write the conventions into AGENTS.md, `evlog map` to score entry-point coverage, `--baseline` to gate regressions in CI) on Nuxt, Nitro, Next.js, TanStack Start, and Hono. Guides setup on those plus SvelteKit, React Router, NestJS, Express, Fastify, Elysia, oRPC, Cloudflare Workers, AWS Lambda, Astro, and standalone TypeScript. Detects console.log spam, unstructured errors, and missing context. Covers wide events, structured errors, drain adapters (Axiom, OTLP, HyperDX, PostHog, Sentry, Better Stack, Datadog, Loki, ClickHouse, NuxtHub, Memory), sampling, enrichers, and AI SDK integration.
content-pass
The daily pass over evlog's written surfaces. Picks the files the scanner ranks worst across the docs, the landing, the package READMEs, the skills, and the AGENTS.md files, reviews them against the content doctrine, applies what holds, and opens one draft PR whose body is the report. Also covers the enrichment half, run when nothing scores badly enough to rewrite, such as the page an index promises and nobody wrote, the integration documented at half its contract, the correction that should have become a rule. Load this when the content-pass schedule fires, or when Hugo asks for a content pass, a docs review, a rewrite of a page, a README, a skill or an AGENTS.md, or what is worth writing next.
write-evlog-content
The evlog content doctrine, for anyone drafting or judging evlog prose: a docs page, the landing, a blog post, a package README, a skill, an AGENTS.md, a changeset. This skill is a pointer, not a copy: it says where the doctrine lives and what range it covers. Load it before writing or reviewing content; read the doctrine file itself in the repository checkout.
build-audit-logs
>-
analyze-logs
Analyze application logs from the .evlog/logs/ directory. Use when debugging errors, investigating slow requests, understanding request patterns, or answering questions about application behavior. Reads structured NDJSON wide events written by evlog's file system drain.
repo-health-sweep
Bi-weekly pass over the whole evlog repository, not just the agent's own surface. Checks every SKILL.md against the real package surface, the docs tree for stale or self-contradictory pages, the repo's own conventions, and the examples against the current API. Load this when the repo-health-sweep schedule fires, or when Hugo asks for a repo health sweep, a docs audit, a skills-vs-reality check, or a convention drift review.
Page 698 of 1652 · 82570 results