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. 86 696 files from 2 113 authors, of which 68 413 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.
> 🛒 E-commerce & Retail skill suite derived from ComposioHQ/awesome-claude-skills. Product catalogue optimisation, conversion rate, customer journey and retail analytics. Provides 10 specialised commands for ecommerce, retail, shopify workflows.
Convert AI conversation transcripts (Claude Code, Codex CLI, ChatGPT JSONL; Cursor IDE SQLite) to readable Markdown. Use when the user wants to: (1) convert .jsonl conversation transcripts to .md, (2) strip binary/base64 data from AI conversation logs, (3) make AI conversation history human-readable, (4) process session exports from ~/.claude/ or ~/.codex/, (5) batch-convert a folder of conversation JSONL files, or (6) list, search, or export Cursor IDE chat/composer conversations. Triggers on mentions of JSONL conversations, transcript conversion, conversation export, readable conversation logs, or Cursor chat history.
Export a claude.ai (Claude Desktop / web) conversation and convert it to a Claude Code CLI JSONL session so it becomes resumable via `claude -r <sessionId>`. Use when the user wants to: (1) continue a claude.ai/Claude Desktop chat in Claude Code CLI, (2) import a web conversation into CC, (3) archive a claude.ai conversation locally with images and attachments, (4) unfreeze a claude.ai chat that hit its context limit, or (5) convert conversation.json from the claude.ai API to CC's JSONL envelope format. Triggers on mentions of exporting/importing Claude Desktop chats, resuming a web chat in CLI, conversation.json → JSONL, or claude.ai chat archival.
Restart the current Claude Code CLI in its own terminal (iTerm2 window or tmux pane) and resume a session — the external relaunch step an agent cannot perform on itself. Use when: (1) the session's context is nearly full and was just stripped in place with session-stripper, so the CLI must restart to load the smaller transcript, (2) resuming a forked stripped session under a new session id, (3) the user or the agent says respawn, restart yourself, restart the CLI, reload the session, or resume after strip. Backends: iTerm2 (macOS) and tmux (works headless, e.g. Linux servers).
Manually trim, compact, persist, and repair Claude Code conversation sessions stored as JSONL files. Use when the user wants to: (1) fix a session hitting 'Prompt is too long' errors, (2) manually compact or strip a session to reduce context, (3) analyze a session's token usage and message chain, (4) strip tool call inputs and results from a session, (5) strip thinking blocks from a session, (6) compact part of a session before a specific message, (7) verify or repair a broken session chain, (8) persist and summarize tool results to reduce context intelligently, (9) perform any JSONL-level surgery on Claude Code sessions. Triggers on mentions of session surgery, session trimming, session stripping, context compaction, session repair, prompt too long, session compact, manual session manipulation, summarize tool results, or persist tool output.
Local peer-to-peer chat and remote control between Claude Code AND OpenAI Codex sessions running concurrently on the same machine (cross-CLI: setup-codex wires Codex 0.145+ hooks), with mIRC-style rooms: register under a name, broadcast to your project room or other rooms, DM other agents, get unread messages auto-delivered by hooks, wake idle peers (nudge), watch their terminals (screen), drive them with keys (escape/enter/...), and spawn brand-new agents into fresh iTerm windows or tmux sessions. Use when: (1) the user asks to message, notify, coordinate with, watch, stop, or control another running agent/session, (2) joining the agent chat ('register as summarizer'), (3) announcing schema/format changes or claiming work areas between parallel agents, (4) checking/reading agent chat messages or browsing rooms, (5) spinning up a new worker agent in a new window or headless tmux session, (6) rebinding an agent identity after a session fork/strip/restart, (7) installing agent-chat on a new machine. Triggers on agent chat, message the other agent, tell the other session, coordinate agents, nudge an agent, spawn an agent, register on chat, chat rooms. Backends: iTerm2 (macOS) and tmux (works headless, e.g. Linux servers).
Build a complete mental map of a project through phased exploration so you can work effectively without rediscovering things. Use when the user wants to: (1) Onboard onto a new or unfamiliar codebase, (2) Get a full project overview or briefing, (3) Understand project architecture, structure, and open work, (4) Initialize context at the start of a deep work session, (5) Explore and summarize a repository end-to-end. Triggers on requests like \"explore this repo\", \"get familiar with this project\", \"give me a project overview\", \"onboard me\", \"init context\", or any request to deeply understand a codebase before working on it.
Create hierarchical, bottom-up "layered summaries" by generating `AGENTS.md` files per directory in a subtree (e.g., `reth/crates/engine`). Deep directories summarize files and key APIs; parent directories roll up children. Also use to incrementally update an existing `AGENTS.md` subtree after content changes. No snippets; keep summaries navigational and checkable.
Pack repositories with Repomix for whole-codebase, cross-file analysis. Default to a whole-repo measurement pass, then a filtered whole-repo pack; if it fits under ~1M tokens, stop and hand off to Gemini. Only if it doesn’t fit after the initial noise filter, reduce scope at folder granularity (avoid file-by-file selection), then iterate based on Gemini feedback.
File-based task tracker for projects: tasks live as markdown files in a tasks/ folder, state = folder location (root = inbox, in-progress/, waiting/, done/, cancelled/, decisions/ for open choices), agents manage tasks by moving the files; plus a zero-dependency local board UI (tasx serve) where the user changes states, answers decisions, and leaves comments that are written straight back into the md files and nudge the owning agent via agent-chat. Use when: (1) the user asks to set up / init a task tracker or tasks folder in a project, (2) the user or agent needs to create, list, move, complete, cancel, or comment on tasks in a repo that has a tasks/ folder, (3) the user asks 'what's in progress', 'what needs me', 'what's stale', or wants a task board / dashboard served, (4) starting a work session in a repo with tasks/ (run tasx doctor and reconcile), (5) a task is blocked on the user's feedback or on a decision — file it as waiting/ or a decision instead of asking and losing the thread, (6) generalizing/migrating older ad-hoc task folders (myhdd-style) onto the shared convention. Triggers on: tasks folder, task tracker, task board, tasx, kanban, what's in progress, needs my feedback, stale tasks, task dashboard.
Create or refresh a `.changeset/<slug>.md` for the current branch, or report that none is required. Triggers on "/changesets create", "add a changeset", "create a changeset", "update the changeset", "refresh the changeset", "do I need a changeset", or any work that touches `packages/**` source files on a feature branch.
Audits the Clerk CLI source tree and proposes updates to the `clerk-cli` skill in clerk/skills so it stays in sync with the binary. Use when the user says "audit the clerk-cli skill", "update the clerk-cli skill", "check the skill against the code", "resync clerk-cli skill", or after adding/renaming/removing CLI commands, flags, or agent-mode behavior.
Convert Hugging Face transformers language models to MLX format for Apple Silicon inference. Use when asked to convert a model from transformers to MLX, port a model to MLX, create an MLX implementation of a model, or test/validate an MLX model conversion. Triggers include mentions of "convert to MLX", "MLX implementation", "port to MLX", "mlx-lm", or requests involving both transformers and MLX frameworks.
> Removes signs of AI generation from English text and prevents them from vocabulary and rhetoric, structure and epistemics. Use whenever the user asks to "humanize", "unslop", "de-AI", "make this sound human", "remove the AI style", "make it not sound generated". Also apply from the first draft when landing pages, product copy. Do not wait to be asked. If the text is in English and a person will read it, this skill applies.
Plan milestone slices from overview + narrative alone (no system GDDs required), create per-milestone directory skeletons and briefs, and write gat/milestone/milestone.md. Runs before per-system design. Stops before technical design, task breakdown, or implementation.
Brainstorm a game idea through one-question-at-a-time designer interviews. Produces game.md, systems-index.md, and art-direction.md, or runs as discussion-only.
Generate procedural 3D models from natural-language requests by writing a constrained buildModel(ctx) module that uses Three.js, bundled builders and helpers, deterministic validation and export scripts, PNG previews, and optional browser visual review. Use when needs to create, revise, export, or visually audit programmatic 3D assets in GLB, glTF, OBJ, or STL without Blender or another DCC tool.
READ this skill when implementing or configuring animation-style shaders (Toon/Cel Shaders) — including outlines, rim lighting, toon shading, MatCap, emission, dissolve, hatching, or any stylized rendering effect. Contains preset styles and feature-to-reference mappings for lilToon, Poiyomi, UTS2, RToon, SToon, and ToonShadingCollection. Works as a domain knowledge plugin alongside workflow skills (OpenSpec, SpecKit) or plan mode of an agent.
Develop game story and narrative through one-question-at-a-time writer interviews. Produces narrative docs under gat/narrative/ or runs as discussion-only. Use when the user wants story, plot, lore, worldbuilding, characters, quests, dialogue, narrative tone, or authored story content for a GAT game.
Inspect the repo state and show a status panel across all milestones, recommending the earliest actionable next step in the workflow.
Design one system within a specific milestone's scope: write the milestone-scoped system GDD, content data, and system art doc, and update the milestone brief's progress. Requires a mandatory milestone argument.
READ this skill when designing or planning any game system architecture — including combat, skills, AI, UI, multiplayer, narrative, or scene systems. Contains paradigm selection guides (DDD / Data-Driven / Prototype), system-specific design references, and mixing strategies. Works as a domain knowledge plugin alongside workflow skills (OpenSpec, SpecKit) or plan mode of an agent.
Comprehensive ImageMagick 7 command-line image processing for inspecting, converting, resizing, cropping, compositing, masking, drawing, annotating, color correction, quantization, filtering, morphology, distortion, animation, montage, comparison, metadata, batch automation, and advanced pixel analysis. Use whenever a task mentions ImageMagick, `magick`, `identify`, `mogrify`, raster image conversion or batch image manipulation, or when a reproducible CLI pipeline is preferable to a GUI or language binding. Also use for debugging ImageMagick commands, porting ImageMagick 6 `convert` syntax to version 7, choosing coder/delegate options, and safely processing untrusted or large images. Do not use merely to edit an existing SVG as vector source or when the user explicitly requests a different image tool.
Plan, generate, inspect, vision-evaluate, refine, and package images and visual assets for game development through a backend-agnostic production loop. Use for PNG or SVG props, icons, characters, environments, tiles, UI, VFX, transparent cutouts, concept sheets, sprite sheets, or animation frames; especially when the task needs batch generation, native prompts or ComfyUI/Stable Diffusion Danbooru tags, reference consistency, background removal, format validation, or iterative quality scoring. This skill orchestrates available image, image-edit, vision, SVG, MCP, local, and host-native tools without requiring a specific generator.
Generate images through OpenRouter's dedicated Image API. Use this skill whenever the user wants to create, render, generate, or save images with OpenRouter, including text-to-image, image-to-image/reference images, choosing OpenRouter image models, listing image models, setting resolution/aspect ratio/quality/output format, or passing provider-specific image options. Prefer the bundled Python script so API options are passed explicitly as command-line arguments instead of hand-written ad hoc curl requests.
Enforce OOP and DDD engineering constraints for C# and TypeScript game development. Use when implementing, refactoring, reviewing, or verifying gameplay systems, domain-controlled engine-view wrappers, domain models, aggregates, application services, repositories, public APIs, or Context-based shared dependencies. Preserve encapsulation, avoid test-only production hooks, unit-test only engine-agnostic leaf logic, and verify integrated behavior by running the real engine.
Generates professional AI images using Google Gemini. ALWAYS invoke this skill when building websites, landing pages, slide decks, presentations, or any task needing visual content. Invoke IMMEDIATELY when you detect image needs - don't wait for the user to ask. This skill handles prompt optimization and aspect ratio selection.
PDF converter powered by MinerU — convert PDF to Word, Markdown, HTML, LaTeX, or plain text. Also handles image-to-text OCR, scanned document recognition, and Office formats (DOCX, PPTX, Excel). Supports 80+ languages. Use this skill when the user wants to convert, extract, read, parse, or summarize any PDF or document. Also applies when the user shares a PDF file or link and asks about its content, needs tables or formulas extracted, wants PDF OCR, or says things like 'turn this into a doc' or 'what does this paper say'.
云备份方案
归档与压缩
备份策略设计
rsync 文件同步与备份
阿里云 CLI 操作
AWS CLI 操作
灾难恢复
快照管理
Azure CLI 操作
PostgreSQL 数据库管理
Elasticsearch 集群管理
Redis 数据库管理
SQL 优化与调优
Google Cloud CLI 操作
MongoDB 数据库管理
MySQL 数据库管理与运维
Ansible 自动化运维
Git 高级操作
CI/CD 流水线配置
Docker Compose 编排
Terraform 基础设施即代码
Docker 容器操作与管理
监控与告警
Dockerfile 编写最佳实践
Docker 镜像管理
Docker 容器网络
Kubernetes ConfigMap 与 Secret
Kubernetes Deployment 管理
kubectl 基础操作与常用命令
Helm 包管理
Kubernetes Pod 管理与调试
Kubernetes Service 与 Ingress
Claude Skills — questions
Answers built from the skills we actually parsed.