Context & AI engineering
25,729 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
m190/usefulapi-mcp/io.usefulapi/dnsimple MCP server
1★ repoMCP server for DNSimple — domains, DNS zone records, availability, pricing and contacts.
m190/usefulapi-mcp/io.usefulapi/easypost MCP server
1★ repoMCP server for EasyPost — rate shipments, buy & refund labels, track packages, verify addresses.
m190/usefulapi-mcp/io.usefulapi/healthie MCP server
1★ repoHosted MCP server for the Healthie EHR & telehealth API: patients, appointments, charting, tasks.
m190/usefulapi-mcp/io.usefulapi/lemonsqueezy MCP server
1★ repoMCP server for Lemon Squeezy — stores, products, orders, subscriptions, license keys.
m190/usefulapi-mcp/io.usefulapi/maxmind-minfraud MCP server
1★ repoMCP server for MaxMind minFraud — score transactions for fraud risk from your AI assistant.
m190/usefulapi-mcp/io.usefulapi/modern-treasury MCP server
1★ repoMCP server for Modern Treasury — payment orders, transactions, counterparties and ledgers.
m190/usefulapi-mcp/io.usefulapi/recurly MCP server
1★ repoMCP server for Recurly — accounts, subscriptions, invoices, plans; cancel & pause subs.
m190/usefulapi-mcp/io.usefulapi/quaderno MCP server
1★ repoMCP server for Quaderno — tax-rate calculation, invoices, contacts, products, receipts & expenses.
m190/usefulapi-mcp/io.usefulapi/sendbird MCP server
1★ repoMCP server for Sendbird — chat users, channels, members, and messages from your AI client.
m190/usefulapi-mcp/io.usefulapi/nylas MCP server
1★ repoMCP server for Nylas — read email, calendars, events and contacts, and send email or create events.
twzrd-sol/twzrd-trust/xyz.twzrd.intel/twzrd-agent-intel MCP server
1★ repoTrust + receipt layer for x402 agents on Solana: free preflight + paid signed V6 trust receipt.
erenisci/acta/skills/design-prompt Skill
0★ repoTurn the design docs into paste-ready Claude Design prompts plus the real copy — scope-locked and on-brand. Trigger on /acta:design-prompt, "claude design prompt", "generate a design prompt".
mnox/mnox-ai/plugins/config-chunks/skills/ai-setup Skill
0★ repoFirst-run guided onboarding that sets up an agent for a less-technical user — leads with a one-shot recommended set of guidance "chunks" (or 2–3 plain-language questions to tailor), confirms, applies them by driving the config-chunks engine into CLAUDE.md / AGENTS.md, then offers safe permission setup. Use when the user says "/ai-setup", "set up my agent", "set up my agent guidance", "onboard me to chunks", "configure my CLAUDE.md guidance", "first-run setup", "recommend chunks for me", "help me get started with config-chunks", "which chunks should I use", or otherwise wants a guided walkthrough to subscribe to guidance chunks. Re-runnable any time; for piecemeal management afterward use /chunks, for permissions use /permission-setup, and to author new chunks use /chunk-review.
mnox/mnox-ai/plugins/config-chunks/skills/chunks Skill
0★ repoManage guidance chunks — toggle subscription to chunk groups and standalone chunks in `~/.claude/config/chunks.yaml`, set which host files receive the bundle, or run a doctor check on the config. Use when the user says "/chunks", "list my chunks", "what chunks am I on", "add a chunk group", "opt into a chunk", "subscribe me to <group/chunk>", "unsubscribe from <group/chunk>", "set chunk targets", "diagnose my chunks config", "fix my chunks.yaml", or otherwise wants to change which guidance chunks land in their CLAUDE.md / AGENTS.md bundle. The skill drives the engine script — it never hand-edits YAML.
mnox/mnox-ai/plugins/config-chunks/skills/permission-setup Skill
0★ repoRecommend safe, conservative agent permission settings for a less-technical user, then delegate the write — never mutate security config directly. Detects the provider (Claude Code / Codex / Cursor / others) and surface (CLI / Desktop-IDE / Cloud), explains permissions in plain language, recommends the "Cautious" least-privilege posture as behavior then concrete config, names that provider's bypass footgun by name, and shows the exact config + location for the user (or a platform config skill) to apply. Use when the user says "/permission-setup", "set up permissions", "set up my agent permissions", "is my agent safe", "make my agent safe", "what permissions should I use", "lock down my agent", "are my settings secure", "review my agent permissions", or finishes /ai-setup. Re-runnable any time; reads references/permission-profiles.md live.
mnox/mnox-ai/plugins/create-skill/skills/create-skill Skill
0★ repoAuthor a Claude Code or cross-host Agent Skill end-to-end — scaffold the directory, write the body against a portable authoring contract, structurally validate, and design-score it. Use when creating a new skill, "make a skill for X", "scaffold a SKILL.md", "write a skill", "turn this into a skill", or improving/grading an existing skill's design. Emits a spec-pure portable skill by default; Claude-only features are opt-in.
mnox/mnox-ai/plugins/retrieval-review/skills/retrieval-review Skill
0★ repoUse when reviewing or auditing a retrieval / vector-index / RAG pipeline for quality before it silently feeds wrong or missing context to a generator. Triggers — /retrieval-review, 'review my RAG pipeline', 'audit this vector index', 'why is retrieval bad', 'check my hybrid search', 'review my embeddings retrieval', 'is my RRF/reranker configured right', 'audit my vector DB setup'. Runs a structured seven-axis review (eval foundation, corpus & chunking, embedding geometry, index & ANN fidelity, retrieval composition, rank fusion, reranking) in a fixed load-bearing order, grounded in BEIR/MTEB evaluation methodology, the anisotropy & alignment/uniformity geometry literature, ANN-index recall theory, and the rank-fusion (RRF) and cross-encoder reranking research. Produces a severity-ranked findings list led by the issues that make the right document structurally unretrievable — each with the smell, the offending layer, why it's a problem, the metric that proves it, and a concrete fix.
mnox/mnox-ai/plugins/util-review/skills/util-review Skill
0★ repoReview Agent Skills, hooks, AGENTS.md/CLAUDE.md files, scripts, MCP configs, or workflow configurations for design flaws, unclosed loops, stale references, side effects, security risks, and portability issues. Use when: 'review this skill', 'audit this hook', '/util-review', 'check this config', or when evaluating any supplementary agent artifact for quality and correctness.
puretechnyc/purebrain-skills/skills/content/image-generation Skill
0★ repoGenerate images for blog banners, social posts, LinkedIn graphics, and marketing materials using AI image generation APIs. Multi-platform sizing, compression workflows, and prompt engineering patterns.
searayca/claude-skills/skills/claude-suggestion Skill
no license0★ repoSearch Claude Code GitHub issues for duplicates, then auto-fill a new issue form with the suggestion. User reviews and submits manually.
giovicordova/skills-gc/skills/philosophier Skill
no license0★ repoCompresses verbose text into the shortest precise phrasing that preserves every constraint and leaves zero ambiguity. Use whenever the user wants to shorten, compress, tighten, distill, or cut down any text — CLAUDE.md sections, README files, AGENTS.md personas, CONTRIBUTING.md, commit messages, error messages, package descriptions, or any prose that says too much with too many words. Also use when writing new documentation content from scratch that should be maximally concise. Trigger phrases: 'philosophier', 'distill this', 'make this shorter', 'compress this', 'tighten this up', 'cut it down', 'too wordy', 'too verbose', 'every line should carry weight', 'say more with less'. If a user pastes a paragraph and asks for it shorter — this is the skill. If they link a file and say it's too long — this is the skill.
thinkyou0714/claude-lab-skills/lab-communication-translation/skills/llm-portability-review Skill
0★ repoドキュメント・プロンプト・スキル定義が、Claude 以外のLLM(GPT-4o / Gemini / Codex 等)でも意図通りに動作するかを評価する。Claude 固有の解釈・暗黙前提・スタイル依存を検出し、移植耐性を高める改善案を提示する。他LLMへ移植する前に使う。
thinkyou0714/claude-lab-skills/lab-implementation-flow/skills/cursor-handoff Skill
0★ repoimplementation-gate 通過後の情報を、施工AI(Cursor 等)が実行可能な指示書形式に変換する。ゲート通過前には使わない。
nakane1chome/claude-skills/skills/dev-record Skill
0★ repoRecord agent activity during Claude Code sessions. Captures plans, human input, agent decisions, and deviations via hooks and agent self-reporting.
nakane1chome/claude-skills/skills/sandbox Skill
0★ repoScaffolds a Docker "sandbox" harness into a repo so Claude Code can run in `--dangerously-skip-permissions` (YOLO) mode inside an Ubuntu container, with the project bind-mounted at /workspace and the host's ~/.claude bind-mounted for auth and session continuity. Use when the developer wants an isolated filesystem for agent writes but still wants host-visible builds, logs, and session history.
Obra superpowers subagent driven development
zjy1020/claude-code-skills/skills/obra-superpowers-subagent-driven-development Skill
0★ repoUse when executing implementation plans with independent tasks in the current session
alexe-ev/product-plugins/ux-research/skills/manage-design-handoff Skill
0★ repoStructure the product-to-design and design-to-engineering handoff process and iteration workflows. Use this skill when a team needs to improve collaboration quality at handoff points.
Pawel-Kica/skills-that-ship/skills/implement-handoff Skill
0★ repoFind a handoff from a loose description and continue the work.
deokjinlog/intent-locked-workflow/skills/auto-executing-plans Skill
0★ repoauto-flow 4단계 (마지막) — implementation-plan.md 읽기 + Entry Guard (preflight.subagent_task_entry_check) + DAG 자동 build + 무조건 wave-parallel subagent 강제 (Gate #14 override) + failure isolation 그대로 + End-of-run consolidator 자동 + finishing-a-development-branch 자동 호출. AskUserQuestion 호출 X — clarifying Q 는 prose 질의다 (본문 Anti-Patterns 와 CLAUDE.md 정본). generating-html 은 Step 4.5 fire-and-forget dispatch (v2.3.2+ — v1.1.17 '호출 부재' 룰이 반전됨).
deokjinlog/intent-locked-workflow/skills/subagent-driven-development Skill
0★ repoUse when executing implementation plans with independent tasks in the current session
deokjinlog/intent-locked-workflow/skills/subagent-driven Skill
0★ repo서브에이전트 실행 경로 (1인 개발 + 사전 검증 게이트 가정). v1.1.14+ wave-parallel — 메인이 plan 분석으로 DAG 추론 → wave 단위 pair-parallel dispatch (implementer + spec reviewer). 메인이 wave 끝에서 직렬 commit + post-hoc 충돌 검출. quality reviewer는 사전 verifying-spec + TDD + RISK + 변경이력으로 분산 흡수.
clever-cc-plugins/cc-concept/plugins/cc-concept/skills/cc-concept-orchestrator Skill
0★ repoUse this skill when the user states a broad marketing goal without naming a specific skill — "help us launch this product", "we need to grow our LinkedIn presence", "reposition us against this new competitor" — and needs to know which order of cc-concept and cc-content skills to run, not a single deliverable. Recommends and sequences skills; never invokes them automatically. Defers to cc-concept-marketing-advisor for open-ended questions that aren't goal-shaped.
azadmotala/claude-code-team-builder/skill Skill
0★ repoBuilds a complete AI development environment for a software project — agents, custom skills, CLAUDE.md project context, orchestration layer, and routing rules. Triggers when someone says 'set up a new project', 'build a team for [project]', 'create project setup', 'scaffold my AI team', or describes a client project and wants Claude Code configured for it. Produces a full .claude/ configuration with project context, agent routing, autonomous execution support, and slash commands tailored to the project's domain and workflow.
bokuwalily/claude-code-skills/skills/claude-headless-p-invocation Skill
0★ repoclaude -p ヘッドレス実行で system prompt 全ロード + macOS perl alarm timeout + token 制限考慮した実行パターン。発火: 非対話的に claude を呼ぶ自動化スクリプト / cron で claude を回す時 / シェルから 1-shot 実行する時
bokuwalily/claude-code-skills/skills/claude-plugin-context-audit Skill
0★ repoセッション開始が重い/応答が直近指示を取りこぼす/context bloatが疑われるとき、SessionStartで注入される全ソース(プラグイン・rules/ecc・obsidian文脈・auto-memory・remember)のトークン内訳を測定して刈り込み候補を特定したいとき
bokuwalily/claude-code-skills/skills/claude-session-log-to-kb Skill
0★ repoStop hook 経由で Claude Code セッションの会話ログを Markdown 化してナレッジベースに追記するパターン。新規プロジェクトでセッション長期記憶を設けたいとき、または extract_conversations.py 相当の仕組みを構築・デバッグするときに使う。
bokuwalily/claude-code-skills/skills/codesign-keychain-prompt-fix Skill
0★ repofastlane/xcodebuild の iOS署名中に codesign のキーチェーン許可ダイアログ(「codesignがキー…へアクセスしようとしています」)が出る・固まって消えない時。特に複数ビルド同時実行でダイアログが競合してハングした時に発火。
bokuwalily/claude-code-skills/skills/codex-delegation-handoff Skill
0★ repo実装タスクをCodex(codex exec)へ委譲する時に毎回使う「投げ方+検証」の固定型。Codexが空振り(timeout/空出力/的外れ実装/別dir書込み)する根本原因=別プロセスで文脈非共有+指示が緩い、を構造的に潰す。ChatGPT Pro枠を活かしてClaude Codeトークンを節約したい時。何をCodexに振るかの判断は、bridge常駐会話は、CLI疎通は。
bokuwalily/claude-code-skills/skills/discord-bot-image-to-claude Skill
0★ repo自作Discord gateway bot(claude -p 連携)で、Discordに貼った画像をClaudeに認識させたい時。添付をローカルDL→パスをプロンプトに添えてReadさせる。
bokuwalily/claude-code-skills/skills/hook-latency-wrap Skill
0★ repoClaude Code の任意 hook (PostToolUse / Stop / UserPromptSubmit 等) の実行時間と失敗率を観測したいとき、bash $EPOCHREALTIME ベースの透過 wrapper で計測する手順。
bokuwalily/claude-code-skills/skills/hook-log-append-pattern Skill
0★ repoClaude Code の Stop/PostToolUse フックから構造化データを JSONL ログに追記する汎用パターン。stop_cost_log.sh / post_audit_log.sh / stop_agent_tracker.sh のような「stdin → parse → append」ループを新規で書くときに参照する。
Llm content pipeline quality gate
bokuwalily/claude-code-skills/skills/llm-content-pipeline-quality-gate Skill
0★ repoLLMでコンテンツを自動生成し、品質スコアが閾値未満なら棄却・再生成するパイプラインをシェルスクリプトで組むとき。claude -p による1コール生成→スコア抽出→閾値ゲート→型/テーマローテーションログまで一連を含む。
bokuwalily/claude-code-skills/skills/local-llm-slow-diagnosis Skill
0★ repoローカルLLM(ollama等)がMac/ノートPCで異常に遅い(eval rate 1-2 t/s等)時の原因切り分け。"100% GPU"表示なのに遅い場合に発火。
bokuwalily/claude-code-skills/skills/macos-hook-path-timeout Skill
0★ repomacOSでClaude Codeのhookやlaunchdジョブが `node: command not found` / `timeout: not found` で失敗する時に使う。GUI起動アプリの最小PATH問題と、macOSにGNU coreutils(timeout)が無い問題の、検証済み回避策。
bokuwalily/claude-code-skills/skills/phaser-mcp-verify-throttled Skill
0★ repoブラウザMCP(claude-in-chrome等)でPhaser3ゲームを自動検証する際、対象タブが非フォアグラウンドでRAFスロットリングされゲームループが止まり、delayedCall/シーン遷移が発火しない/待っても進まないとき
bokuwalily/claude-code-skills/skills/session-handoff Skill
0★ repo長時間/大規模 autonomous モード中に context 限界が近づいた時の次セッション引継ぎパターン。snapshot + improvement-log + dashboard.md + 次やる候補リストを残して中断する。発火: 改善 phase が 5+ 進んだ時、token 5h block が残量 <100k になった時、ユーザーから「続けて」「永遠に」等の長期指示を受けて 60分以上経過した時
cskwork/claude-minimal-plugin/skills/claude-hud Skill
0★ repoClaude Code의 statusline HUD 플러그인. context 사용량, tool 활동, agent 추적, todo 진행상황을 실시간으로 표시한다. statusline 설정, HUD 커스터마이징, 또는 context 모니터링이 필요할 때 사용한다.
cskwork/claude-minimal-plugin/skills/mcp-builder Skill
0★ repoGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
The same file is in 10 other repositories
cskwork/claude-minimal-plugin/skills/skill-creator Skill
0★ repoGuide for creating effective skills. Use 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.
The same file is in 10 other repositories
opendatadiscovery/odd-team/.claude/skills/retrieve Skill
0★ repoRun the graph-retriever subagent — intelligent, iterative retrieval over the derived graph query layer. The maintainer asks a free-form information-need question ("where is X", "what depends on Y", "which findings concern Z"); the agent constructs a strong query, runs a bounded retrieve→read→judge→refine loop (≤10 iterations) with adaptive traversal, and returns a cited answer set. Emits substrate-refinement suggestions to lineage/{repo}/retrieval-feedback/ without ever mutating the graph. Supersedes the grep-based registry-search. Per adrs/drafts/agentic-graph-retriever.md.
gordon1210/agent-goodies/skills/handoff Skill
0★ repoPortable agent plugins for Codex/ChatGPT and Claude Code/Desktop.
kennyolofsson23-netizen/claude-code-config/skills/claude-ads Skill
no license0★ repoPaid advertising audit and optimization across Google, Meta, YouTube, LinkedIn, TikTok, and Microsoft Ads. 186 weighted audit checks with 12 sub-skills and 11 industry templates.
kennyolofsson23-netizen/claude-code-config/skills/llm-docs-optimizer Skill
no license0★ repoOptimize documentation for AI coding assistants and LLMs. Improves docs for Claude, Copilot, and other AI tools through c7score optimization, llms.txt generation, question-driven restructuring, and automated quality scoring. Use when asked to improve, optimize, or enhance documentation for AI assistants, LLMs, c7score, Context7, or when creating llms.txt files. Also use for documentation quality analysis, README optimization, or ensuring docs follow best practices for LLM retrieval systems.
kennyolofsson23-netizen/claude-code-config/skills/owasp-llm-top10 Skill
no license0★ repoSecurity audit for LLM and GenAI applications using OWASP Top 10 for LLM Apps 2025. Assess prompt injection, data leakage, supply chain, and 7 more critical vulnerabilities.
kennyolofsson23-netizen/claude-code-config/skills/reflexion/memorize Skill
no license0★ repoCurates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
kennyolofsson23-netizen/claude-code-config/skills/sdd Skill
no license0★ repoSpec-Driven Development (SDD) Plugin: Continuous Learning + LLM-as-Judge + Agent Swarm
kennyolofsson23-netizen/claude-code-config/skills/skill-creator Skill
no license0★ repoCreate 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.
hsnuhow/how-skills/plugins/skill-tools/skills/skill-RCM Skill
no license0★ repoRecommend skills worth installing for THIS project, grounded in its development memory, CLAUDE.md, product/requirement docs, and codebase. One-shot recommendation report in Traditional Chinese. RCM = recommend. Trigger ONLY on /skill-RCM or an explicit request for skill recommendations. Do NOT auto-activate, and do NOT install anything without confirmation.
hsnuhow/how-skills/plugins/taiwan-biz-research/skills/biz-case-workflow Skill
no license0★ repoRun a full Taiwan business case end-to-end as a hypothesis-driven multi-agent workflow — frame the question as 2-4 mutually exclusive strategic options, reverse-engineer what-would-have-to-be-true conditions per option, surface the key debates with bull and bear both argued, run skeptic-designed tests in a lazy-man loop that kills options early and expands the search when evidence runs dry, build a driver-tree market model with analog-market parameterization, profile competitors symmetrically, then choose the option with the fewest unresolved barriers and ship a monitoring plan. Use when someone asks for a Taiwan market-entry, sizing, competitor, investment or timing case, an evidence-backed strategic recommendation, or "研究一下台灣的 X 市場" — anything where the answer must be a defensible choice among options. Not for a single lookup; use tw-data directly for that.
Zrzzzz/agent-codebase-skills/init-session-notes Skill
0★ repo为项目初始化「会话归档」自动化基础设施: 1. SessionEnd hook:每次会话结束自动用 claude -p 提炼对话要点追加到 docs/session-notes.md, 含超阈值自动压缩(默认 45KB)。 2. docs/session-notes.md:长期决策与踩坑沉淀(hook 维护,模板由本 skill 初始化)。 本 skill 只管「会话归档」:不写 CLAUDE.md / AGENTS.md 分层约定——那些归 [`init-agents-md`](../init-agents-md/SKILL.md);不初始化 docs/TASKS.md 任务管理—— 那些归 [`init-agent-task-md`](../init-agent-task-md/SKILL.md)。 使用:/init-session-notes;或当用户说「给项目装会话归档」「我想要自动整理对话要点」时也命中本 skill。