Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 600 files from 1 763 authors, of which 61 947 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. Triggers on: 'create a skill', 'new skill', 'make a skill for', 'improve this skill', 'test this skill', 'skill eval', 'optimize skill description', or /hk-skill-creator.
Decide whether an Upwork job post is worth applying to before spending Connects. Use when the user pastes an Upwork job post (or invitation) and wants a verdict (apply, skip, or apply with caution). Triggers include "is this job worth it", "should I apply", "check this job post", "is this client legit", "worth my Connects", "red flags in this job". Screens for scams, bad-client patterns, and dressed-up low-tier work, then weighs the Connects economics. Companion to upwork-proposal-writer (after an apply verdict) and upwork-invitation-responder (after a skip verdict on an invitation).
Draft or review an Upwork proposal (cover letter) using the five-move method extracted from a Top Rated Plus freelancer's winning proposals, corrected for the AI era. Use when the user shares an Upwork job post and wants a proposal drafted, or shares an existing proposal draft and wants it reviewed. Triggers include "write a proposal", "apply for this job", "bid on this", "cover letter for this Upwork job", "review my proposal". Works for design, dev, and adjacent creative/tech freelance jobs.
Audit and improve an Upwork freelancer profile. Use when the user pastes their profile (title, overview, portfolio list, skills, stats) and wants it scored and fixed, or asks why they aren't getting invitations or search visibility. Triggers include "review my Upwork profile", "why am I not getting invites", "improve my profile", "profile title help", "optimize my overview". Returns a prioritized fix list, biggest lever first. Companion to upwork-proposal-writer (the proposal earns the profile visit; the profile closes it).
Draft mid-contract messages to a freelance client on Upwork or similar platforms. Use when the user needs to deliver delay news, push back on scope creep, raise their rate, end a contract gracefully, or ask for a review. Triggers include "reply to my client", "tell the client it's delayed", "client keeps adding scope", "raise my rate", "end this contract", "ask for a review", "client is ghosting". Input is the situation plus the relevant thread context, pasted. Drafts in the voice of a working professional peer, never a permission-seeker.
Respond to an Upwork "Invitation to Interview" fast and well. Use when the user pastes a job invitation they received on Upwork and wants to accept it, decline it, or decline it while referring another freelancer. Triggers include "got an Upwork invite", "decline this invitation", "reply to this invite", "client invited me", "should I take this invitation". Drafts the reply; helps triage borderline invitations first. Companion to upwork-proposal-writer (which handles the full proposal after an accept).
Use MagicPath through the magicpath-ai CLI to find, preview, inspect, install, export, create, and edit UI components and manage MagicPath skills. Trigger for MagicPath designs/components; personal or team projects; active canvases and selected components/images/revisions; themes/design systems; teams, members, ownership, attribution, installed-component audits, and share/view links. Use when exporting exact MagicPath components or revisions to local folders/apps; replacing, adapting, or translating local UI with 1:1 fidelity and explicit requested changes; installing React/TypeScript components with inspect/add; authoring responsive interactive canvas components with code start/submit; importing or recreating UI from local paths or GitHub/GitLab/Bitbucket repositories into MagicPath; or creating, retrieving, updating, importing, enabling, disabling, or deleting MagicPath skills. In hosts with an embedded browser, keep the project canvas open via share URLs for visual work.
Write or revise release blog posts for product releases. Use when the user asks to draft, polish, restructure, or adapt a release announcement.
Audit and modernize RstackJS/Rspack ecosystem repositories against current infrastructure baselines. Choose between the Rsbuild-style Rstack CLI monorepo lane and the standalone Rslib/Rslint/Rstest package lane; maintain package.json metadata, exports, dependency placement and version freshness; align ESM or dual output, Node/pnpm/TypeScript versions, formatter, CI action pins, release validation, docs, dependencies, and infra PR conventions. Use when updating rstackjs repositories, refreshing infrastructure or package manifest baselines, copying patterns from Rsbuild or maintained exemplars, or reviewing package and tooling consistency.
Debug Rstack ecosystem CI failures and attribute the real source PR or downstream change. Always use this skill when the user mentions Rspack eco-ci, rstack-ecosystem-ci, a suite turning red, a downstream regression, a green-to-red pivot, canary bisect, @rspack-canary/core, or daily eco-ci triage — even if they only ask "why is this suite failing", "which PR broke it", or "is this Rspack's fault". Use it to avoid over-blaming the first Rspack commit that appears red in status data.
Use when asked to create a pull request for this repository. It helps the PR follow the repository's branch safety rules, title convention, pull request template, and concise English writing style.
Create or update draft GitHub release notes, or output organized Markdown when draft creation is unavailable. Use for release notes, draft releases, release PR checks, npm staged publishing checks, and optional highlights.
Convert `.mdx` to portable `.md`, cleaning MDX components, anchors, code titles, table-of-contents links, and root-relative docs links.
Migrate webpack, Vite, create-react-app (CRA/CRACO), or Vue CLI projects to Rsbuild.
Benchmark agent skills by generating eval cases, comparing skill-guided vs baseline runs, and recording artifacts under skills-test/{skill-name}.
Rsbuild best practices for config, CLI workflow, type checking, bundle optimization, assets, and debugging. Use when writing, reviewing, or troubleshooting Rsbuild projects.
Migrate Jest or Vitest projects to Rstest. Use when asked to move from Jest/Vitest to Rstest, replace `jest`/`vi` APIs with `@rstest/core`, translate config into `rstest.config.ts`, update scripts/coverage/setup/mocks/snapshots/projects, or diagnose config-loading warnings, migration failures, and memory/performance regressions caused by Rstest's Rsbuild/Rspack execution model, DOM dependency bundling, runtime-mocked module build graphs, or version skew.
Migrate tsc or tsup library projects to Rslib.
Migrate ESLint or other linters to Rslint. Use when asked to replace ESLint flat config, lint scripts, VS Code ESLint settings, inline directives, rules, presets, plugins, or lint dependencies with Rslint equivalents.
Use when upgrading a Rsbuild 1.x project to v2, including dependency and configuration updates.
Use when analyzing Rspack/Webpack bundles from local `rsdoctor-data.json` and producing evidence-based optimization recommendations.
Rslib best practices for config, CLI workflow, output, declaration files, dependency handling, build optimization and toolchain integration. Use when writing, reviewing, or troubleshooting Rslib projects.
Opinionated Rslib recommendations for modern JS/TS npm package design covering pure ESM, strict TypeScript, explicit exports, small stable APIs, pragmatic dependencies, accurate sideEffects, correct declarations, package validation, provenance, README.md, and AGENTS.md. Use when the user wants to make a JS/TS package more modern, check whether the current package setup is healthy, review package.json/exports/types/dependencies/docs/release readiness, or apply a modern library baseline.
Helps Rspack users and developers debug crashes or deadlocks/hangs in the Rspack build process using LLDB. Use this Skill when users encounter "Segmentation fault" errors during Rspack builds or when the build progress gets stuck.
Rspack best practices for config, CLI workflow, type checking, CSS, bundle optimization, assets and profiling. Use when writing, reviewing, or troubleshooting Rspack projects.
Use when upgrading a Rspack 1.x project to v2, including dependency and configuration updates.
>- Diagnose and optimize Rspack `optimization.splitChunks` configuration. Use defaults, fewer duplicated modules, better long-term caching, `cacheGroups` design help, `maxSize` tuning, or debugging over-fetch caused by `name` and forced chunk merging.
Comprehensive guide and toolkit for diagnosing Rspack build issues. Quickly identify where crashes/errors occur, or perform detailed performance profiling to resolve bottlenecks. Use when the user encounters build failures, slow builds, or wants to optimize Rspack performance.
Rspress best practices for config, CLI workflow, content organization, frontmatter, MDX, themes, i18n, search, static assets, deployment, and debugging. Use when writing, reviewing, or troubleshooting Rspress documentation sites.
Customize Rspress themes using CSS variables, Layout slots, component wrapping, or component ejection. Use when a user wants to change the look and feel of an Rspress site, override theme components, add custom navigation/sidebar/footer content, inject global providers, or modify the default Rspress theme in any way. Also use when a user mentions theme/index.tsx, Layout slots, BEM class overrides, or rspress eject.
Generate and maintain description frontmatter for Rspress documentation files (.md/.mdx). Use when a user wants to add SEO descriptions, improve search engine snippets, generate llms.txt metadata, prepare docs for AI summarization, or batch-update frontmatter across an Rspress doc site. Also use when adding new documentation pages to an Rspress project — every new doc file needs a description.
Generate or maintain Rspress documentation for a project. Use whenever the user wants to create a new Rspress v2 docs site, add docs for user-facing feature work or PRs, maintain a dedicated Rspress docs project in a monorepo, or prevent stale Rspress v1 scaffolds/version drift before documentation work. For full v1-to-v2 migration, hand off to the rspress-v2-upgrade skill.
Rstest best practices for config, CLI workflow, test writing, mocking, snapshot testing, DOM testing, coverage, multi-project setup, CI integration, performance and debugging. Use when writing, reviewing, or troubleshooting Rstest test projects.
Migrate Rspress projects from v1 to v2. Use when a user asks to upgrade Rspress, follow the v1-to-v2 guide, update configs/themes, or validate the upgrade.
Debug Rstest issues systematically, including performance regressions. First determine whether the slowdown is in build startup or test execution, then run controlled config or code experiments and compare before/after timings.
Set up or migrate Storybook to use the Rsbuild builder. Handles fresh setup for React, Vue 3, HTML, Web Components, and React Native Web, migration from webpack5 or Vite frameworks, and integrations with Rslib, Modern.js, and Rspack. Use when asked to add Storybook, migrate Storybook to Rsbuild, configure rsbuildFinal, or integrate Storybook with Rslib/Modern.js/Rspack.
Creates a fully functional Drizzle ORM setup with a provisioned Neon database. Installs dependencies, provisions database credentials, configures connections, generates schemas, and runs migrations. Results in working code that can immediately connect to and query the database. Use when creating new projects with Drizzle, adding ORM to existing applications, or modifying database schemas.
Use this skill when the user asks to add documentation, add docs, add references, or install documentation about Neon. Adds Neon best practices reference links to project AI documentation (CLAUDE.md, AGENTS.md, or Cursor rules). Does not install packages or modify code.
Sets up the full Neon JS SDK with unified auth and PostgREST-style database queries. Configures auth client, data client, and type generation. Use when building apps that need both authentication and database access in one SDK.
Creates and manages ephemeral Neon databases for testing, CI/CD pipelines, and isolated development environments. Use when building temporary databases for automated tests or rapid prototyping.
Configures Neon Serverless Driver for Next.js, Vercel Edge Functions, AWS Lambda, and other serverless environments. Installs @neondatabase/serverless, sets up environment variables, and creates working API route examples with TypeScript types. Use when users need to connect their application to Neon, fetch or query data from a Neon database, integrate Neon with Next.js or serverless frameworks, or set up database access in edge/serverless environments where traditional PostgreSQL clients don't work.
Sets up Neon Auth for your application. Configures authentication, creates auth routes, and generates UI components. Use when adding authentication to Next.js, React SPA, or Node.js projects.
Manages md2wx CLI for converting Markdown to WeChat Official Account drafts. Use when working with WeChat article publishing, Markdown to HTML conversion, or WeChat media upload.
Safely audit and reduce CPU, load average, I/O wait, and Docker container resource pressure on macOS and Ubuntu/Linux hosts, especially remote production-like servers over SSH. Use when a host feels slow, load average is high, monitoring shows CPU spikes, Docker containers are suspected of consuming CPU, a service dashboard times out, or the user asks for a repeatable CPU optimization workflow.
Keep repository-level Claude and Codex agent instructions compatible by creating safe symlinks between CLAUDE.md and AGENTS.md, and between .claude/skills/* and .agents/skills/*. Use when a repository should work with both Claude and Codex, when one agent instruction file exists but the other is missing, when migrating agent skills between .claude and .agents directories, or when asked to improve Claude/Codex compatibility for a repo.
Route GPT-5.6 tiers, reasoning effort, and subagents to minimize accepted-result cost subject to an explicit quality floor.
Review, improve, organize, deploy, and verify Grafana dashboards, provisioned alert rules, and the Telegraf→InfluxDB→Grafana monitoring stack. Use when working on Grafana dashboards, dashboard folders, tags, legends, panel readability, Flux/InfluxDB query correctness or performance, Prometheus/Telegraf dimensions, Telegraf JSON/HTTP scraping, anonymous access, dashboard/alert provisioning, Grafana Docker deployments, high CPU or memory caused by dashboard queries, InfluxDB cardinality and tag-vs-field modelling, provisioned alert rules and Flux alert conditions, contact points and Telegram/notification delivery, or requests like "review this dashboard", "optimize Grafana panels", "why is this dashboard slow / using CPU", "fix legends", "move dashboards into a folder", "add tags", "set up Grafana alerting", "alert won't fire / won't deliver", "fix Telegram alerts", "route alerts to a Telegram topic/thread (message_thread_id)", "bump/upgrade the Grafana version", "deploy and verify dashboards", "InfluxDB is OOM-killed / restart-looping / won't start", "series cardinality explosion", "should this be a tag or a field", or "Grafana best practices".
> Daily English expression coach for intermediate software engineers. Use this skill whenever the user wants to improve their spoken or written English in a software engineering work context — especially for standups, small talk with teammates. Trigger this skill when the user says things like "teach me English", "practice English", "how do I say X at work", "daily English", "help me sound more natural", "English for standups", "how should I phrase this in Slack", or any similar request about sounding more natural or professional in English at a tech job. Also trigger when the user gives you a draft message or spoken phrase and asks you to improve it or make it sound more natural.
Route Claude 5 tiers (Haiku/Sonnet 5/Opus 5/Fable 5), effort, and subagents for cost-effective accepted results, and handle Claude 5 prompting, long-running execution, API behavior, refusals, and fallback.
Safely audit and reclaim disk space on macOS and Ubuntu/Linux hosts, including remote servers over SSH. Use when the user says their Mac, Linux box, VPS, or server disk is full, asks what can be safely deleted, wants to clean caches, developer artifacts, Docker storage, apt/Homebrew/npm/pnpm/yarn/pip/uv caches, journal/log files, Xcode data, editor extensions, node_modules, Trash, crontab/systemd timer disk checks, or asks for a repeatable free-space cleanup workflow.
Audit and clean the persistent context that feeds a recurring autonomous agent loop — memory files and indexes, scheduled-task / automation prompts, and CLAUDE.md / AGENTS.md — so the loop stops degrading into a self-reinforcing echo chamber. Works for Claude Code /loop crons and Codex automations.
This skill should be used when the user wants to install or configure Pi Agent (@earendil-works/pi-coding-agent) with DeepSeek (built-in), Ant-Ling Ring-2.6-1T (single-model custom provider), and ZenMux (multi-model OpenAI-compatible aggregator including Gemini 3.5 Flash, inclusionAI Ling-3.0-flash, Claude, GPT), including auth, models.json, settings.json, a curated extension set, and known-pitfall fixes. Triggers on "配置 pi"、"setup pi agent"、"pi 装一下"、"配 ring/deepseek/gemini/zenmux/ling 到 pi".
Find Agent Skills on skills.sh and adopt only the ones that pass a security audit. Use when the user wants to discover, search for, evaluate, or install a third-party skill ("find a skill for X", "is this skill safe to install", "search skills.sh", "what skill should I use for Y"). Always runs the skills.sh security audit before recommending or installing anything, and refuses to adopt skills that fail the audit.
Download YouTube videos with yt-dlp and post-process them with ffmpeg — fetch best-quality video/audio, convert formats, extract audio, and burn in translated (e.g. Chinese) subtitles with a translator watermark. Covers cross-environment tool installation (macOS-focused) including the ffmpeg-full / libass gotcha. Triggers on "youtube 视频下载处理".
将具体执行委派给 pi coding agent + ZenMux 便宜执行模型（默认强档 deepseek/deepseek-v4-pro：1M 上下文、推理型；廉价快档 inclusionai/ling-3.0-flash：256K、非思考、更省），Claude 负责任务-模型匹配判断、任务书编写、驱动（一次性 pi -p 或 tmux 交互长程）、硬超时重试、独立验收与失败裁决。含双模型选型、3D 素材来源、Spec-Driven、强类型可验证节点、推理档位开关等最佳实践。触发词：pi 委派、把执行外包给便宜模型、deepseek、deepseek-v4-pro、v4 pro 执行、ling、ling-3.0-flash、ling flash 执行、pi sub agent
Build, launch and drive wayfinder-maps to verify a change end-to-end (server + headless browser).
Turn the current conversation into a spec, saved to `.plan/` — no interview, just synthesis of what you've already discussed.
Compact the current conversation into a handoff document so a fresh agent can continue the work.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
A relentless interview to sharpen a plan or design, which also creates docs (ADRs and glossary) as we go.
Claude Skills — questions
Answers built from the skills we actually parsed.