Recently added
Plugins grouped by the day they were added to the directory, newest first.
Sep 21, 2026
- demir-bot-pilot0stars
Private skills-only pilot of the Demir Bot coordinator and 21 specialist skills.
Codex22 skills - vulngate2stars
VulnGate — a Codex-native source-audit pipeline for ANY codebase: libraries (parsing/serialization), web frameworks (Spring/Struts), middleware/servers (Tomcat/Jetty), logging libraries (Log4j/Logback), expression engines, message/RPC stacks, and applications. Runs the S1→S8 audit loop (attack-surface map → candidates → source audit → PoC matrix → novelty gate → CVSS → disclosure-ready report) with hard evidence gates (G0–G5) driven by the host agent. Aliases: @vulngate, @vg, 漏洞审计, 源码审计, 审计管线, vuln audit. Coverage-driven auditing: full source inventory, heuristic call graphs and flows, security control gaps, sibling differentials, candidate scheduling, and macOS/Electron/native application reconstruction.
Codex1 skill - ai-jury7stars
Convene a cross-vendor multi-agent review jury (Claude Code + Codex + Antigravity + an optional free local model) on a diff, PR, or issue: independent review, cross-examination, verification, and one verdict — a chair's synthesis or a panel vote.
CodexClaude Code1 skill - commerce-builder0stars
Skills and scaffolding commands for building shopping and merchant agents on Claude, covering architecture, prompt caching, UI tools, trust and safety, evals, and merchant operations.
Claude Code6 skills - govhub-lablivre1stars
Skills da marca Lab Livre (Laboratório de Software Livre da UnB, dono dos projetos Gov Hub): identidade visual oficial com a mesma arquitetura da skill do Gov Hub (PDF, slides, posts, tokens). (1 skills)
Claude Code - govhub-docs1stars
Geração de documentos e relatórios: docx, xlsx, PDF, planilhas, README, changelog, diagramas Mermaid e conversão de web para Markdown. (7 skills)
Claude Code - govhub-qualidade1stars
TDD, testes em Python, depuração sistemática, clean code, arquitetura (ADR, DDD, padrões), performance, segurança e gestão de segredos. (18 skills)
Claude Code - govhub-infra1stars
Docker, IaC, GitHub Actions, shell scripting e observabilidade com Prometheus e Grafana. (8 skills)
Claude Code - govhub-backend1stars
Python e FastAPI, design de APIs REST/GraphQL, documentação, integração com APIs de terceiros e segurança de APIs. (6 skills)
Claude Code - govhub-dados1stars
Engenharia e ciência de dados, Postgres (schema, boas práticas, otimização), SQL, BigQuery, Jupyter e extração de PDF para banco. (9 skills)
Claude Code - govhub-core1stars
Skills específicas do GovHub BR: guia de implementação de pipelines (Airflow + dbt + Postgres), identidade visual oficial e relatório de prestação de contas a partir do git. (3 skills)
Claude Code - govhub-skills1stars
Coleção completa de skills do GovHub BR / lablivre — as 52 skills de todas as categorias em um único plugin.
Claude Code - xungen0stars
Trace Your Roots — Shang Dynasty Identity Engine. Maps Chinese surnames and hometowns to ancient Shang Dynasty (1600-1046 BCE) clans, totems, officials, and fiefdoms. Generates humorous 'Shang Dynasty Identity Certificates' with historically-sourced clan affiliations, Old Money Index ratings, and vivid ancient persona descriptions.
Claude Code2 skills - elite-ts1stars
Shared lint/format hooks and formatting-setup/verification skills for TypeScript projects
Claude Code2 skills - elite-dev1stars
Generic dev-workflow skills for git worktrees, GitHub issues, and pull requests
Claude Code5 skills - staff-engineer1stars
Make your coding agent work like a staff engineer: interview before building, preview before tests, gated lifecycle, plain-language handoffs. Stack-agnostic, zero dependencies.
Claude Code10 skills - co-dev0stars
Cloud Officer development workflow tools for PR management, issue tracking, code quality, cloud infrastructure and cost optimization (AWS, GCP), deployment (Heroku), payments (PayPal), observability (New Relic), design (Figma), app stores (App Store Connect, Google Play), and database management
Claude Code32 skills13 MCP servers - symphony0stars
Context-free agents that write the documents around code — issues, pull request bodies, feature plans, code reviews and repo audits — each to a fixed set of rules, and each stamped with the versions that produced it.
Claude Code - tmux-og8stars
Claude Code integration for tmux-og: status-bar state hooks and issue self-report skill
Claude Code2 skills - fresh-dev0stars
Deno Fresh specialist for Claude Code: read-only semantic analysis MCP (routes, islands, components, middleware, server/client boundaries, request tracing, impact), Fresh reasoning skills, a structural validator with a headless CLI, hooks that keep the index fresh, and deno lsp wiring. Designed to sit under vise (orchestration) and beside livespec (symbol graph).
Claude Code14 skills1 MCP server - fixture-plugin0stars
fixture-plugin is an open-source Claude Code plugin indexed from GitHub with 1 skill. Review its manifest and source before installing.
Claude Code1 skill - night-watchman0stars
Unattended-operations engine for Claude Code: tickets as dispatch contracts, an owner decision profile that reduces questions over time, a capability ladder (script beats agent beats skill), and the orchestrator/cheap-executor split. The ticket contract comes from the work-order plugin dependency; file-mode tickets by default.
Claude Code10 skills2 MCP servers - quiver1stars
One arrow, one skill. Design-first brainstorming + multilingual session handovers + relay ignition + catch-up briefs, across AI coding agents.
CodexClaude Code5 skills - ppt-agent2stars
PPT slide generation workflow: requirement research → material collection → outline planning → planning draft → design draft (SVG 1280x720 Bento Grid) with Claude draft + Gemini review
Claude Code2 skills - steer2stars
An always-on engineering operating manual plus spec-workflow skills and templates. Org standards centralized so every product repo picks up changes via /plugin update.
Claude Code26 skills2 MCP servers - ts-quality0stars
TypeScript PostToolUse quality checks registered into the toolu hook engine.
CodexClaude Code - toolu0stars
Dual-host engineering discipline for Claude Code and Codex: workflow skills, agents, commands, and registry-driven quality hooks.
CodexClaude Code12 skills - toolu-review0stars
Project-tuned pre-push code review mirroring the CI review bot's checklist (correctness, security, perf, test coverage, doc accuracy), writing the toolu push-review state so the gate passes. Standalone.
CodexClaude Code1 skill - statusline0stars
Host-native project status: a persistent Claude Code statusline plus an explicit Codex status skill for repository, gate, git, comemory, and Jev readiness. Standalone, no dependencies.
CodexClaude Code1 skill - rust-quality0stars
Rust PostToolUse quality checks registered into the toolu hook engine.
CodexClaude Code - python-quality0stars
Python PostToolUse quality checks registered into the toolu hook engine.
CodexClaude Code - pr-babysit0stars
Babysit a PR until review threads, the review-bot verdict, and CI are clear, using Claude cron or a durable Codex goal with isolated worktrees.
CodexClaude Code1 skill - jira0stars
Jira issue search and workflow from the session via a REST wrapper (skill + bash). Cloud + Server/DC, read and safe writes. Standalone, no dependencies.
CodexClaude Code1 skill - jev0stars
Typed judgments from TypeSafe's Jev model at runtime (skill + REST wrapper) — yes/no probabilities, choices, and scores a script can branch on. Standalone, no dependencies.
CodexClaude Code1 skill - exa-search0stars
Web, code, and URL search plus deep research via Exa (skill + REST wrapper). Standalone, no dependencies.
CodexClaude Code1 skill - context70stars
Library documentation & code-example lookup via Context7 (skill + REST wrapper). Standalone, no dependencies.
CodexClaude Code1 skill - ast-grep0stars
Structural code search & rewrite (ast-grep): skill, wrapper, and a PreToolUse Grep→ast-grep nudge registered into the toolu hook engine.
CodexClaude Code1 skill - agent-browser0stars
Efficient, token-lean browser automation for agents via agent-browser (skill + CLI wrapper) — accessibility-tree snapshots with @eN refs instead of HTML/screenshots. Standalone, no dependencies.
CodexClaude Code1 skill - proudhuman1stars
Map the human's role in a merged pull request from Claude Code session transcripts: who the accountable human is, which turns framed, constrained, verified or rescued the work, which added lines have no origin in AI-emitted text, and which prompts were verbatim earlier AI output. Developer-facing self-review, not a scorecard.
Claude Code1 skill - valcraft19stars
Valcraft is a software factory in your repository: it coordinates the work, keeps the requirements and decisions in ordinary files, and checks the code before shipping so you can see what was built and how it was verified. Skills: tune (repository configuration), cast (project framing), spec (feature and quick contracts), draft (task plans with MSW), forge (reviewed-task implementation and authorized task PRs), review (report-only plan, code, and evidence review), land (authorized finalization and tracker closure), foreman (named-state delivery coordination), temper (local retrospective production), hone (prompt refinement), distill (prompt distillation), and msw (MSW Kernel document judgment).
CodexClaude CodeAgent Plugins12 skills - bearing-lite1stars
Skills-first portable planning, routing, bounded execution, and independent assurance for repository work.
CodexClaude CodeAgent Plugins17 skills - 10c-dev0stars
A shareable software-delivery workflow for Claude Code: ticket-driven build cycle with an explicit prototype-to-production rung, a one-question interview, verification on the live app, self code-review, an adversarial critic, and a session board so parallel sessions on one machine do not collide.
Claude Code8 skills2 MCP servers - agent-team-kit0stars
Reusable software team: business-analyst, architect, test-manager, developer, tester and perf-tester agents, a team workflow (TDD by vertical slice) tracked on an Ordna board (one card per user story, one column per agent), baseline requirements, stack packs (FastAPI or Quarkus backend, React or Angular frontend) and document templates.
Claude Code5 skills - idea-autopsy0stars
A four-skill plugin for honest, decision-shaped idea review: stress-test-idea, iterate-to-v2, evaluate-proposal-harsh, strategize-from-verdict.
Claude Code4 skills - wheel70stars
Engineering standards for .NET and React, plus the skills that apply them: setting up a project, adding a feature, building a component.
Claude Code3 skills - heavyskill2stars
Heavy Thinking as the Inner Skill in Agentic Harness — spawns K independent parallel reasoning agents then performs critical sequential deliberation. Implementation of arXiv:2605.02396v1.
Claude Code1 skill - loop-eng2stars
Loop Engineering for Claude Code: /autoloop drives bounded tasks to completion via a builder/checker cycle with six stop rules; /polish iteratively raises code quality via multi-lens review, adversarial verification, and dry-round convergence. A Stop hook mechanically prevents quitting while a loop contract is unsatisfied, and a PreToolUse evidence gate ensures completion claims are machine-written, never typed.
Claude Code1 skill - furi-toolbox0stars
Ferramentas avulsas do Furihata — /brain (o parecer: entender o problema e decidir), /blind (a sessão que não vê nada: só o texto que você mandou), /ask, /chat, /save, /sync, /make-dev, /make-skill, /ctt, /video-teams e mais. Cada uma funciona sozinha, sem depender de outra skill.
CodexClaude CodeAgent Plugins11 skills - furi-ship0stars
Skills de entrega do Furihata — uma escada só: os alvos /work, /pull-request, /homolog e /prod levam o trabalho de onde estiver até o próprio estágio, cada um invocando o anterior quando falta algo atrás; os modificadores /repro e /card compõem com qualquer alvo, em qualquer ordem; /infra mapeia a infra do projeto; o processo mora em .claude/ship/setup.md, uma seção por skill. Funciona sozinho, sem depender de outro pacote.
CodexClaude CodeAgent Plugins7 skills - furi-build0stars
Skills de construção do Furihata — /solve, /principles, /front, /method e /proto: do problema ao commit local, com QA. Funciona sozinho, em qualquer repositório.
CodexClaude CodeAgent Plugins5 skills