Agent Plugins Marketplace

Recently added

Plugins grouped by the day they were added to the directory, newest first.

Sep 15, 2026

  1. misakanet492stars

    Failure-memory network for AI coding agents: search evidence-rated failure lessons, submit new failures, and turn crashes into reusable knowledge.

    Codex
  2. nt-share0stars

    Share artifacts as branded unguessable links on share.notambourine.com: upload, then generate and revoke from a private working page.

    Claude Code1 skill
  3. gw-runtime0stars

    GW セッション専用。スレッド ID を鍵に worker セッションを確保するツールと、中継が一言一句そのままであることを検査するフック

    Claude Code1 MCP server
  4. gw-control0stars

    Discord スレッド中継の GW セッションを起動・確認・停止・再起動する。判断はすべて bin/ のスクリプトに閉じ込めてあり、スキルは呼ぶだけ

    Claude Code4 skills
  5. centaur1.3kstars

    Use an authenticated Centaur deployment from Codex.

    CodexClaude Code1 skill
  6. clawbio1.1kstars

    Bioinformatics-native AI agent skill library: pharmacogenomics, clinical variant interpretation, GWAS and polygenic scores, ancestry, RNA-seq and single-cell, metagenomics, proteomics and nf-core pipeline wrappers. 97 Agent Skills, 50 with a deterministic CLI entry point and demo data, every runnable skill writing a SHA-256 reproducibility bundle. Local-first.

    Claude Code50 skills
  7. prisant-utilities1stars

    General-purpose agent skills for the work around the work: session continuity, structured analysis, guide authoring, cross-LLM peer review, and the specification and release-planning documents that sit between an idea and a tag. Use when wrapping or resuming a coding session, turning raw thinking into a decision-ready brief, generating a guide bundle, getting a second-model review of a document, writing a feature spec, managing a version-scoped release plan, or scaffolding agent infrastructure into a repository.

    CodexClaude Code8 skills
  8. rf-reviewer0stars

    Motor determinístico para revisar entregáveis de Requisitos Funcionais (Excel): extrai a planilha, deixa o agente preencher a análise cruzada com a memória do projeto, e INJETA a análise de volta na MESMA planilha do cliente de forma mecânica e não-destrutiva (colunas anexadas, original 100% preservado, versionado). Perfis de coluna trocáveis por assunto. Escopo: arquivos TABULARES (xlsx/csv); documentos (pdf/docx/pptx) seguem outro fluxo.

    Claude Code1 skill1 MCP server
  9. claude-code-boss0stars

    Semantic knowledge base (Brain) + curated shell execution + lightweight learning for Claude Code. Auto-indexed KB with vector search, anti context-bloat curation, and advisory pattern/correction capture. Relies on native Agent/Workflow tools for orchestration.

    Claude Code8 skills1 MCP server
  10. cairn-memory8stars

    Lightweight cross-session memory with a source receipt for every inference.

    Claude Code3 skills
  11. maipai0stars

    MaiPai org shared skills: release ceremony, docs refresh, verification contract, platform package scaffolding, standards pin check, screenshot verification, build status dashboard, the coordinator role for directing coder sessions, and duplicate-safe issue filing. Hooks: a blind-staging gate, a review-before-commit gate, and session-start repo context. Agent: design-resolver, an opus subagent for resolving design/spec ambiguities.

    Claude Code9 skills
  12. routemux0stars

    Agent Skills for the RouteMux AI gateway: generate images and video, look up models and pricing, and point a coding agent at RouteMux.

    Claude Code4 skills
  13. bg0stars

    B.Galy project-management kit, invoked as /bg:<skill>: read the strategy, briefs and specs you manage in Galy, then plan, implement and ship inside your own repository. Galy never sees your code.

    Claude Code21 skills
  14. xyne-claw150stars

    Log in to Xyne Claw and invoke remote agents from Claude Code

    Claude Code5 skills1 MCP server
  15. dsh-skills-anywhere6stars

    Discover and load Agent Skills from configured local directories, plugin marketplaces and Git sources through a local stdio MCP server.

    Claude CodeAgent Plugins1 MCP server
  16. deepr-research10stars

    Bounded research and persistent expert discovery through an Agent Skill and a local read-only MCP capability profile.

    Agent Plugins1 skill1 MCP server
  17. golf2stars

    Golf Intelligence, by Stracka. The highest-quality proprietary golf course dataset for developers building a golf app. Continuously updated mapped course data — not a scrape. Search is free. Scorecards, GPS, and 3D greens via API.

    Claude CodeAgent Plugins1 skill1 MCP server
  18. housecarl32stars

    Comprehensive data-layer access to your Skyrim SE load order — read any record, author patches into a new plugin, look mods up on Nexus, and look up record schemas, Papyrus signatures, performance reviews, and distributor grammars — in plain English.

    Claude Code1 MCP server
  19. shunt2.3kstars

    Shunts I/O-heavy work to AiKA modes to save tokens. Hooks block large file reads and redirect to bulk-reader/code-writer scripts backed by the Portal CLI.

    Claude Code2 skills
  20. portal2.3kstars

    Set up, diagnose, search, and operate Spotify Portal through focused workflows and the Portal CLI.

    CodexClaude Code6 skills
  21. blunt0stars

    Injects blunt, outcome-first communication guidelines at session start.

    Claude Code
  22. dgnengine0stars

    엔솔 지식 그래프(Neo4j) 읽기 전용 조회 — ensol-kg 스킬 + MCP 접속 + /kg-doctor 연결 점검

    Claude Code1 skill
  23. aaron-marketing0stars

    120 marketing skills and 8 commands as an AI marketing staff — one plugin, portable skills on 70+ hosts, or an 8-bot team — and as a four-layer operating system: Narrative strategy; SEO/GEO, Organic Social, Email, Paid Ads, and Influencer channels; Product Launch orchestration; and a Protocol layer with seven append-only truth registries plus non-canonical working memory. Eight typed advisory frameworks (TALE, CORE-EEAT, CITE, STAR, ECHO, SEND, ROAS, RAMP) use machine-checkable auditor artifacts and immutable standalone runtime contracts. Keyless-first and zero-dependency.

    Claude Code
  24. yandex-wordstat2stars

    Анализ поискового спроса (Wordstat). ⚠️ Доступ к scope требует ручной заявки в поддержку Яндекса.

    Claude Code1 skill
  25. yandex-webmaster2stars

    Управление сайтами в Вебмастере: индексация, поисковые запросы, сайтмапы, переобход, ссылки.

    Claude Code1 skill
  26. yandex-tracker2stars

    Трекер задач: задачи, очереди, комментарии, статусы, отчёты.

    Claude Code1 skill
  27. yandex-telemost2stars

    Видеовстречи Яндекс.Телемост: создание встреч, расписание, ссылки.

    Claude Code1 skill
  28. yandex-metrika2stars

    Аналитика Яндекс.Метрики: трафик, конверсии, цели, UTM, источники, e-commerce, расходы Директа. Cache-first, 30-строчный лимит stdout.

    Claude Code1 skill
  29. yandex-messenger2stars

    Яндекс.Мессенджер: чаты, сообщения, поиск (бот-API).

    Claude Code1 skill
  30. yandex-mail2stars

    Почта Яндекс 360: чтение, отправка, поиск через IMAP/SMTP с OAuth-токеном.

    Claude Code1 skill
  31. yandex-forms2stars

    Конструктор форм: создание форм, чтение ответов, экспорт результатов.

    Claude Code1 skill
  32. yandex-disk2stars

    Облако Яндекс.Диск через REST API: файлы, папки, публикация ссылок. Также fallback на WebDAV.

    Claude Code1 skill
  33. yandex-direct2stars

    Контекстная реклама Яндекс.Директ: кампании, объявления, отчёты, ставки, ОРД-документы.

    Claude Code1 skill
  34. yandex-calendar2stars

    Календарь Яндекс 360 через CalDAV: события, расписание, напоминания.

    Claude Code1 skill
  35. yandex-bot-platform2stars

    Ботоплатформа Яндекс.Диалогов: навыки Алисы, голосовые скиллы, аналитика.

    Claude Code1 skill
  36. yandex-auth2stars

    Unified OAuth flow for all Yandex APIs (single token covering all scopes the user enabled in their Yandex OAuth app)

    Claude Code1 skill
  37. yandex-audience2stars

    Аудитории Яндекса: создание сегментов, lookalike, использование в Директе и VK Ads.

    Claude Code1 skill
  38. yandex-360-admin2stars

    Админ-API Яндекс 360: пользователи, домены, аудит, настройки организации.

    Claude Code1 skill
  39. clauterbox0stars

    Flags overly verbose comments / JSDoc-TSDoc in TS/JS files using a configurable comment-to-subject length ratio, plus opt-in structural checks, and pushes back to Claude to fix them.

    Claude Code
  40. uroshcs-skills0stars

    Uros's personal workflow skills. Includes 18 skills.

    Claude Code18 skills
  41. tools0stars

    Werkzeuge mit ausschließlich expliziter Auslösung: /tools:ask und /tools:execute (die jeweils andere CLI non-interaktiv fragen bzw. beauftragen), /tools:unslop (KI-Muster aus Text entfernen), /tools:grimm (Sachverhalte ins Verwaltungs- und Anordnungsdeutsch überführen), /tools:orchestrator[-review|-cross] (Rollen-Prompt: steuern statt arbeiten, in drei Stufen bis zur anderen CLI als Arbeiter). Nachfolger der Plugins ask, unslop und grimm.

    CodexClaude Code7 skills
  42. philharmonie0stars

    Projektaufträge mit Spec, getrenntem Generator und Evaluator sowie dauerhaftem Zustand bearbeiten; Cross-CLI-Fragen und begrenzte Schreibaufträge auch einzeln ausführen.

    CodexClaude Code4 skills
  43. ask0stars

    [VERALTET – final, Nachfolger: tools] Cross-CLI-Zweitmeinung: fragt non-interaktiv die jeweils andere CLI (Codex aus Claude Code, Claude aus Codex) mit dem Flaggschiffmodell der installierten Version — /ask read-only (ohne Argument: Review des Projektstands), /execute mit Schreibrechten im Workspace. Der Host schreibt ein Handover, die andere CLI antwortet.

    CodexClaude Code1 skill
  44. daikenja0stars

    Not an assistant -- a sage you consult. It reads the threads, documents, meetings and code you are buried in, asks what you are actually trying to do, and hands back something you can act on: a verdict on a draft, a review of how you handled a thread, a plain markdown ledger of what a project decided and what is still open. It never sends, never publishes, and never writes a word you did not ask for. The writing and remembering side of a working week.

    Claude Code18 skills
  45. claude-context-optimizer111stars

    Claude 5-aware context optimization (Fable 5.1 / Opus 5 / Sonnet 5 pricing, 1h-cache-aware real costs & cache-break detection), SKILL.state-style task state that survives /compact, session baseline audit (/cco-overhead), auto .contextignore, self-calibrating estimates, delegation advisor, ru/en prompt coach, per-language token estimation, tunable thresholds via /cco-config, self-learning tool costs, team pattern sharing

    Claude Code22 skills
  46. stackwich1stars

    Delivery discipline for AI coding agents. Writes the five-layer Stackwich policy (Prompt / Context / Harness / Loop / Graph) into CLAUDE.md and scaffolds advisor, executor and verifier subagents.

    Claude Code1 skill
  47. plan-staged-rollout1stars

    Run big projects as many small sessions — not one huge one.

    Claude Code1 skill
  48. sbrodol-ai1stars

    Ultra-verbose, deeply analytical, didactic and architectural communication mode (Anti-Caveman Protocol). Use when the user asks to "sbrodolare", wants maximum detail, a didactic walkthrough, an architectural justification, a paranoid security audit, or pure verbose entertainment.

    Claude Code1 skill
  49. rk0stars

    Rk's Claude Code kit — skills, agents, hooks, rules for all repos

    Claude Code50 skills
  50. foreman0stars

    Run Claude Code as a software team: architect, implementer, reviewer, and qa roles under a lead that reports to you.

    Claude Code1 skill