Recently added

Sep 16, 2026

1. frontend1stars

   Design and build beautiful web UI that doesn't look generic

   CodexClaude Code2 skills
2. contribute1stars

   Contributions to repositories you do not control: /upstream, /open-upstream-pr, /manage-upstream-pr, /open-upstream-issue, /manage-upstream-issue, /sync-fork

   CodexClaude Code8 skills
3. coding-agents1stars

   Coding-agent environments and coordination: /operate-prowl, /message-agents, /coordinate-agents, /recover-prowl-agents

   CodexClaude Code5 skills
4. harnie0stars

   개발 체인 스킬 허브 — 요구사항 → 설계 → 설계리뷰 → 구현 → 구현리뷰 → 검증 6단계 스킬과 간단한 작업을 한 지시로 끝까지 돌리는 dev(Claude Code · Codex 공용, 크로스모델 리뷰는 orca 대화형 세션), PR 리뷰·댓글 해결·배포 승인·문서 발행 스킬. 구독 auth.

   Claude Code13 skills
5. xdg-base-directory66stars

   When an application needs to store config, data, cache, or state files. When designing where user-specific files should live. When code writes to ~/.appname or hardcoded home paths. When implementing cross-platform file storage with platformdirs.

   CodexClaude Code1 skill
6. verification-gate66stars

   Enforce mandatory pre-action verification checkpoints to prevent pattern-matching from overriding explicit reasoning. Use this skill when about to execute implementation actions (Bash, Write, Edit) to verify hypothesis-action alignment. Blocks execution when hypothesis unverified or action targets different system than hypothesis identified. Critical for preventing cognitive dissonance where correct diagnosis leads to wrong implementation.

   CodexClaude Code1 skill
7. twelve-factor-app66stars

   Reference guide for the Twelve-Factor App methodology — 15 principles (12 original + 3 modern extensions) for building portable, resilient, cloud-native applications. Use when evaluating architecture, reviewing codebases for methodology compliance, or advising on configuration, scaling, observability, security, and deployment patterns.

   CodexClaude Code1 skill
8. rwr66stars

   Portable documentation workflows for audit, synchronization, and freshness review; user-facing authoring and summaries; citation-driven writing; docs-to-skill conversion; and AI-instruction optimization.

   CodexClaude Code6 skills
9. summarizer66stars

   Faithful information summarization with fidelity preservation, structured output, and anti-hallucination methodology. Provides skills for file, URL, and image summarization; agents for autonomous summarization tasks; and hooks for validating agent output structure.

   CodexClaude Code6 skills
10. scientific-method66stars

    Use when debugging, investigating root causes, designing experiments, or performing scientific analysis — enforces hypothesis-driven reasoning, evidence-first observation, causality validation, and structured output templates. Use when facing unknowns, repeated failures, or complex investigations requiring rigorous methodology.

    CodexClaude Code3 skills1 MCP server
11. rtfp66stars

    Read The Fucking Prompt — mines Claude Code session transcripts to surface the strongest user reactions to assistant instruction-following failures and renders the exchange as a terminal-style PNG

    CodexClaude Code1 skill
12. python3-development66stars

    Python 3.11+ development workflows including CLI apps with Typer/Rich, script writing, test development, code review, linting troubleshooting, and pyproject.toml configuration. Provides TDD patterns, modern type hints, PEP 723 metadata, and solutions for common Python errors.

    CodexClaude Code32 skills2 MCP servers
13. python-engineering66stars

    Opinionated Python 3.11+ engineering system. Establishes strong defaults (SOLID, typing policy, testing standards, code smell detection) and routes to specialist skills for TDD, CLI, web, data/science, and constrained environments.

    CodexClaude Code43 skills
14. process-siren66stars

    Analyzes, improves, validates, and concisely represents processes and systems using a canonical semantic model and claim-level validation.

    CodexClaude Code3 skills1 MCP server
15. acme-tools66stars

    Fixture plugin declaring a dot-prefixed output-style directory

    Claude Code
16. plugin-creator66stars

    Complete plugin development toolkit for creating, refactoring, and validating Claude Code plugins and agents. Use when creating new plugins/skills/agents, refactoring existing plugins/skills, validating frontmatter, or restructuring plugin components. Includes specialized agents for assessment, planning, execution, and validation workflows.

    CodexClaude Code48 skills1 MCP server
17. perl-development66stars

    Comprehensive Perl 5.30+ development plugin with modular skills for scripting, CPAN ecosystem, environment setup, testing, linting, and validation. Includes specialized agents for script development, code auditing, and CLI architecture.

    CodexClaude Code6 skills
18. orchestrator-discipline66stars

    Enforces orchestrator context window discipline via PreToolUse hooks and rules. Prevents the orchestrator from reading source files it will not edit, running diagnostic commands that should be delegated, and bypassing delegation with 'small change' rationalizations. Install to structurally prevent investigation escalation anti-patterns.

    CodexClaude Code2 skills
19. llamafile66stars

    When setting up local LLM inference without cloud APIs. When running GGUF models locally. When needing OpenAI-compatible API from a local model. When building offline/air-gapped AI tools. When troubleshooting local LLM server connections.

    CodexClaude Code1 skill
20. litellm66stars

    When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns.

    CodexClaude Code1 skill
21. holistic-linting66stars

    This skill should be used when the model needs to ensure code quality through comprehensive linting and formatting. It provides automatic linting workflows for orchestrators (format → lint → resolve via concurrent agents) and sub-agents (lint touched files before task completion). Prevents claiming "production ready" code without verification. Includes linting rules knowledge base for ruff, mypy, and bandit, plus the linting-root-cause-resolver agent for systematic issue resolution.

    CodexClaude Code3 skills
22. gitlab-skill66stars

    Source-backed GitLab CI/CD, glab CLI, automatic release, component, Function, GLFM, and gitlab-ci-local guidance.

    CodexClaude Code1 skill
23. frustration-analyzer66stars

    Find the strongest user reaction to an AI instruction-following failure in a Claude or Codex session or selected session range, then render a shareable terminal-style PNG.

    CodexClaude Code1 skill1 MCP server
24. fastmcp-creator66stars

    Build FastMCP 3.x Python MCP servers — covers provider/transform architecture (including CodeMode, Tool Search, and server-level transforms), component versioning, session state, authorization (MultiAuth, PropelAuth, connection-pooled token verifiers), evaluation creation, Pydantic validation, async patterns, STDIO and HTTP transports, nginx reverse proxy deployment, background tasks, Prefab Apps UI, security patterns, client SDK usage, testing, deployment, and migration from FastMCP v2. TypeScript is a legacy reference only and is not updated for v3.

    CodexClaude Code3 skills
25. dot-dash66stars

    Live multi-session dashboard for Claude Code — real-time visibility and control over every Claude Code session from a browser

    CodexClaude Code1 skill
26. dh66stars

    Language-agnostic development process harness implementing the Stateless Agent Methodology (SAM) 7-stage pipeline with ARL human touchpoint model and Voltron-style language plugin composition. Provides orchestration, workflows, planning, verification, and testing methodology that any language plugin can compose with.

    CodexClaude Code50 skills3 MCP servers
27. dasel66stars

    Query, transform, and convert structured data files (JSON, YAML, TOML, XML, CSV, HCL, INI) using dasel v3. Provides reference syntax, exploration workflows, transformation patterns, and cross-platform installation.

    CodexClaude Code9 skills
28. conventional-commits66stars

    When writing a git commit message. When task completes and changes need committing. When project uses semantic-release, commitizen, git-cliff. When choosing between feat/fix/chore/docs types. When indicating breaking changes. When generating changelogs from commit history.

    CodexClaude Code1 skill
29. commitlint66stars

    When setting up commit message validation for a project. When project has commitlint.config.js or .commitlintrc files. When configuring CI/CD to enforce commit format. When extracting commit rules for LLM prompt generation. When debugging commit message rejection errors.

    CodexClaude Code1 skill
30. clang-format-configuration66stars

    The model must invoke this skill when any trigger occurs - (1) user mentions "clang-format" or ".clang-format", (2) user requests analyzing code style/formatting patterns/conventions, (3) user requests creating/modifying/generating formatting configuration, (4) user troubleshoots formatting behavior or unexpected results, (5) user asks about brace styles/indentation/spacing/alignment/line breaking/pointer alignment, (6) user wants to preserve existing style/minimize whitespace changes/reduce formatting diffs/codify dominant conventions.

    CodexClaude Code1 skill
31. brainstorming-skill66stars

    This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.

    CodexClaude Code1 skill
32. bash-development66stars

    Comprehensive Bash 5.1+ and POSIX shell development plugin with modular skills for scripting, portability, testing, linting, logging, and version-specific features (5.1, 5.2, 5.3 changelogs with examples). Includes specialized agents for script development and code auditing.

    CodexClaude Code8 skills
33. agentskill-kaizen66stars

    Analyze Claude Code agent session transcripts to identify inefficiencies, anti-patterns, repeated mistakes, and missing tooling opportunities for continuous improvement

    CodexClaude Code4 skills2 MCP servers
34. agent-orchestration66stars

    Orchestrate sub-agents across harnesses: decompose work into phases, dispatch each phase with a specialist or generic prompt, adjudicate returned STATUS reports, and run fan-out, maker/checker, tournament, and loop-until-stop shapes with explicit caps. Use when delegating any implementation, investigation, fix, or review.

    CodexClaude Code2 skills
35. hzt0stars

    hzt_harness — Hazeltree's reference agentic harness: task tracking, planning, review, and verification skills for Claude Code

    Claude Code18 skills
36. stackpack5stars

    Stackpack v1.0.0 — generic tech-stack reference skills (Next.js, NestJS, API-gateway patterns, MySQL, PostgreSQL, Redis, Docker) spun out of Loomwright; 18 skills, no agents/commands/hooks. Install alongside loomwright@atelier.

    Claude Code17 skills
37. mysql-mcp5stars

    Mysql-mcp v1.0.1 — the read-only MySQL MCP server (vikashruhil-mysql-mcp via uvx) spun out of Loomwright, pinned to `==1.0.1`. Resolves DB_HOST/DB_USER/DB_PASS/DB_NAME(/DB_PORT) from the environment. No agents/commands/skills/hooks.

    Claude Code1 MCP server
38. loomwright5stars

    Loomwright is a plan-first, multi-agent development system for Claude Code. Launch Pad turns a goal into a reviewed brief; Supervisor executes it autonomously across parallel git worktrees with self-heal; dedicated agents cover code review, red-teaming, QA, and standalone PR review-and-heal. 14 agent roles, 24 slash commands, 42 skills, 39 quality gate hooks. Full history in CHANGELOG.md.

    Claude Code40 skills
39. short-io0stars

    Short.io link management under your own API key - create, edit, search and measure short links through Short.io's hosted MCP tools, plus a CLI that lists every link on a domain, checks what a slug really points at, bulk-creates from CSV with duplicate detection, and deletes. Activates for: (1) creating or editing a short link, (2) finding which slug points where, (3) bulk link creation from a spreadsheet, (4) auditing a short domain, (5) click and referrer statistics, (6) first-run key setup.

    Claude Code7 skills1 MCP server
40. solidforge1stars

    A Loop Engineering system for AI coding agents — one Claude Code plugin. Bundles the converge → specify → implement pipeline plus two additive outcome-axis layers (cited-source verification + uncited-prior-art collision): the cross-source-review, blueprint-crafting, parallel-development, primary-source-verification, and prior-art-search skills; 23 cascaded subagents (plugin-scoped as solidforge:<name>); and the deterministic convergence-loop hooks (fast-gate, blueprint read-only guard, breaker counters). Enable per-project (Layer 1); run /solidforge:arm-tools to provision gate tools + arch-configs + constitution (Layer 2).

    Claude Code3 skills
41. ruvex0stars

    Ruvex Factory workflow plugin: PROTOTYPER works on factory tasks from Claude Code via MCP. AI builds and syncs prototypes; the human submits with /ruvex:done.

    Claude Code3 skills
42. remote-plugin-dowoo0stars

    무해한 원격 플러그인 (모니터링 가시성 실험). 마커 스킬 + /remote-plugin-dowoo 명령을 제공. 원격 git 마켓플레이스에서 설치되어 local plugin과 대조된다.

    Claude Code
43. mcp-test-dowoo0stars

    Test MCP (dowoo) - minimal read/write note server at dowhub.org. OAuth 2.0, no credential stored. [v1.0.1 - auto-update probe]

    Claude Code1 MCP server
44. aas-plugin0stars

    AgentAutoSensing — 대상 SaaS/에이전트의 업데이트 페이지를 매일 읽어, 점검기준 33개에 걸리거나 보안상 중요한 변화를 잡아 AAR 리뷰 요청서를 만든다. 스킬 2개: /aas_scope(목표·범위 URL 자체를 탐색·갱신 — 랭킹 페이지에서 새 SaaS, 리뷰한 SaaS 마다 업데이트 페이지) · /aas_search(주어진 목표·범위를 서칭해 변화→선별→요청서). 판정은 안 한다(aar 의 몫). 기준 정본은 aar-mcp list_guidance('점검기준'). 상태는 자체 aas-mcp 저장소(aar 와 무관)·웹 https://dowmain.org/agentautosensing/.

    Claude Code1 MCP server
45. aar-plugin0stars

    AgentAutoReview — AI 앱 보안 리뷰 워크플로 스킬 7종 + 리모트 MCP(aar-mcp). /aar_review(적용 시나리오 전수 실증) · /aar_update(주간 SaaS 추적, 트리·보고서 델타 갱신) · /aar_fix(대화에서 배운 걸 규범에 반영) · /aar_explain(리뷰 결과를 큰그림·적은글씨 HTML 아티팩트로) · /aar_menu(원천 트리 항목 하나만 조사해 그 노드에 보고서를 붙임) · /aar_menutoy(SaaS 웹 메뉴를 크롤러 코드로 재현·git 이력, 주간) · /aar_sensing(Agent Auto Sensing 랭킹 세션을 가져와 리뷰하고 카드마다 완료 표시, 매주). 리뷰 발행 직전 독립 검증 서브에이전트 aar-reviewer(대상 드리프트·tier 귀속 정직성·커버리지·증거 게이트)와 대전제 감사 aar-compounder. 스킬은 한 트리(skills/)에서만 관리하고 MCP `skill('get', …)` 로 원문을 받아 쓴다. 도구는 서버측 자동 업데이트.

    Claude Code1 skill1 MCP server
46. adzviser0stars

    Analyze marketing, analytics, ecommerce, and CRM data with Adzviser. Includes workflows for performance reviews, budget pacing, SEO, ecommerce reporting, and public competitor ad research, connected to Adzviser's remote MCP server through OAuth.

    Claude Code7 skills1 MCP server
47. claude-cortex0stars

    Persistent memory that makes Claude Code smarter across sessions

    Claude Code4 skills1 MCP server
48. sharingan0stars

    Cataloga, replica e transplanta funcionalidades de um projeto autorizado, com skills especializadas, subagentes e comandos $sharingan.

    Claude Code6 skills
49. nao-grita0stars

    Impede que o agente assine commits, merge requests ou qualquer texto com o próprio nome, mencione uso de IA ou deixe rastros de ferramenta.

    Claude Code1 skill
50. estou-cansado-chefe0stars

    Quando o uso está alto, a cota perto do fim ou o contexto perto do limite, toca o áudio e chama o subagente John Coffey.

    Claude Code1 skill