113 plugins issus de marketplaces Claude Code publiques. Chacun regroupe des skills, des commandes slash, des agents, des hooks ou des MCP servers qui s'installent ensemble.
113 plugins correspondent à ces filtres.
90n-skillspolar-bear-org/claude-skills2
agricidaniel-claude-obsidianAgriciDaniel/claude-obsidian1
dockerdocker/skills1
awesome-journal-skillsbrycewang-stanford/Awesome-Journal-Skills1Soumettez le dépôt avec .claude-plugin/marketplace.json et nous listerons chaque plugin.
Soumettre une marketplaceInternal BizOps domain. v2.8.0 ships 7 skills: orchestrator + process-mapper (BPMN/bottleneck/cycle-time, Lean+TOC) + vendor-management (scorecard+SLA+3rd-party risk, NIST SP 800-161/ISO 27036) + capacity-planner (Erlang-C queueing math for ops teams, NOT engineering) + internal-comms (ADKAR+Kotter 8-step, NOT marketing) + knowledge-ops (SOP+runbook+KB hygiene with 5W2H, context: fork) + procurement-optimizer (UNSPSC spend categorization + supplier consolidation). Orchestrator uses context: fork to route inquiries via Matt Pocock grill discipline (one question per turn, recommended answer, canon-cited challenge). Every SKILL.md ships a Forcing-question library section. 18 stdlib Python tools, 24+ reference docs. Distinct from business-growth (external sales) and c-level-advisor (strategic).
A second brain for Claude Code + Obsidian inspired by Karpathy's LLM Wiki gist. Turn any LLM CLI into a disciplined wiki maintainer: incrementally ingest sources into a persistent, interlinked markdown vault; update entity/concept/source pages; flag contradictions; maintain index and append-only log. Knowledge compounds instead of being re-derived by RAG on every query. Ships 3 sub-agents (wiki-ingestor, wiki-librarian, wiki-linter), 5 slash commands (/wiki-init, /wiki-ingest, /wiki-query, /wiki-lint, /wiki-log), 8 Python tools (stdlib only: init_vault, ingest_source, update_index, append_log, wiki_search BM25, lint_wiki, graph_analyzer, export_marp), 8 reference docs, full vault templates (CLAUDE.md, AGENTS.md, cursorrules, 5 page templates), and a worked example vault. Cross-tool compatible with Claude Code, Codex CLI, Cursor, Antigravity, OpenCode, and Gemini CLI.
Local-first Agent Skills package and Claude Code plugin for source-cited Obsidian knowledge bases. Includes recoverable transactions, deterministic lint and retrieval, provenance ledgers, explicit vault adoption, offline-first capture foundations, and methodology modes.
Learning & mastery skills: build a roadmap for any skill, remember what you read and study (spaced repetition, active reading), learn by doing, break plateaus, and map your knowledge gaps.
100 cowork skills for the AI-coworker era: inbox and email ops, files and folders, spreadsheets, documents, meetings, team collaboration, research, presentations, personal work ops, and office admin — the office knowledge work an AI coworker actually does
Docker-authored knowledge skills for AI coding agents across Dockerfiles, Compose, Docker Agent, Docker Sandboxes, and safe Docker workflows.
Twelve CIKM-specific skills for the ACM International Conference on Information and Knowledge Management, grounded in the official CIKM 2026 site (35th edition, Rome), per-track CFPs, submission policies, ACM Digital Library records, and dblp.
academicCompany Architect: builds a business from scratch as an OKF (Open Knowledge Format) bundle — a tree of versionable .md files with a frontmatter type, links forming a graph, and reserved index.md/log.md, readable by humans and agents alike. Guides the founder through a 12-phase interview (foundation, strategy, market, financial, sales, marketing, product, operations, tech, people, legal, governance), one phase at a time, and generates conformant markdown concepts. 3 stdlib tools: scaffold_bundle (bundle scaffold), okf_linter (validates type/reserved files/links), index_generator (regenerates the index.md files). Standalone-installable; also bundled in c-level-skills. In English.
Knowledge base compiled from OpenAI's Spinning Up in Deep RL (MIT, Joshua Achiam) by engineering/book-to-skill. A resident core carries the RL optimization problem, the model-free taxonomy, the policy-gradient template with its five valid weights, the safe-step family (VPG to TRPO to PPO) and the overestimation family (DDPG to TD3 and SAC); 20 on-demand chapters cover key concepts and MDPs, the algorithm taxonomy and model bias, the policy gradient derivation with the log-derivative trick and EGLP lemma, Achiam's researcher essay, the key-papers topic map, the exercises including the silent DDPG broadcasting bug, the benchmark parity disclosure, one chapter per algorithm, and the logger/MPI/ExperimentGrid utilities. Ships a glossary, a patterns file with 16 techniques, a decision cheatsheet with thresholds, a cs-spinning-up-deep-rl agent and /cs-spinning-up-deep-rl. Structured study notes, not a reproduction of the source.
23 skills for founders and indie operators. Meta (skillify / toolify / loopify), decision + strategy (decide / business-brainstorm / deep-research / domain / unstuck / maker-council), knowledge (second-brain / company-brain / read-book / watch-video / radar / ingest), output (jab-hook / slide-deck), operations (pm / personal-cfo / company-cfo / paste / social-fetch / castmate). Sibling to marketingskills.
HADS (Human-AI Document Standard) — semantic tagging convention for docs that work for both humans and AI models — plus the grounded-vault pattern for provenance-linked, drift-checked knowledge stores.
147 skills marketing toan dien (78 VN + 69 Global) — tu lap ke hoach, brief chien dich, viet script TikTok, copy quang cao, slogan hai lop, hop tac KOC/affiliate, van hanh san TMDT, den phan tich hieu suat, email marketing, personal brand strategy, AI avatar production, dropshipping mastery, design master, offer design, SEO/GEO growth, B2B lead generation, AI Marketing OS, va 4 role SOP packs (Leader 58-67, Content 35-40, Designer 41-50, Performance 51-57) day du o ca hai ngon ngu + knowledge base nen tang. Ho tro 4 regions (US/EU/SEA/LATAM) + VN. Tich hop voi Claude Code, Claude Pro, ChatGPT, Gemini, Copilot, Cursor. Dung foundation skills `product-marketing-context`, `22-personal-brand-context` (VN) va `product-marketing-context-global`, `22-personal-brand-context-global` (Global) de tranh lap lai thong tin.
32 skills for running a support desk, from the hard reply to the bot handoff: hard conversations, workload and staffing, roles, metrics and coaching, escalations and incidents, learning from tickets, answers and knowledge, service design, and AI and bots, safely.
productivityThe Complete Claude Guide for L&D: 40 Claude skills for the whole L&D job, in eight stages: diagnose the need with the request triage, the performance gap and the action map; work with the experts through the interview, the task breakdown and the review plan; design the learning with objectives, an evaluation plan, a design document and a curriculum map; build and test scenarios, a storyboard, a knowledge check, the check of an AI draft and a learner walkthrough; run the room with a session plan, slides, a facilitator guide and a pilot; carry it into work with a job aid, spaced practice and a manager briefing; measure what changed with a feedback form, an ROI estimate and the one-page report; and lead L&D through the year plan and the business case. For L&D managers and specialists, instructional designers, trainers and facilitators, and L&D leaders. Claude drafts and checks, people decide: nothing a learner does in training is used to grade, rank or build a case against them.
productivityComplete GRACE methodology: semantic markup, knowledge graphs, module contracts, testing, and log-driven verification for AI-driven engineering
Unified AI-native Vibe Coding plugin: PRD generation, digging analysis, screen-spec (IA / User Flow / Wireframe HTML / Dev Handoff), team-based parallel implementation, quality-gated auto-commit, 20 design styles, frontend (React/Next.js), backend (NestJS/Prisma), mobile (React Native/Expo), AI integration (STT/LLM), DevOps (Docker/CI-CD). 11 agents, 5 commands, 8 skills, team knowledge wiki (auto-collect + recall for WIGTN repos).
Multi-agent application-security review. An offensive-security pipeline: map a codebase with Graft, hunt vulnerabilities with a per-class knowledge base, chain findings for escalation, verify real impact, and report (README/JSON/SARIF/doc/PDF).
securityCyber Threat Intelligence skills pack — threat actor profiling, IOC investigation, detection engineering, intelligence writing, and self-updating knowledge cells.
Loops (a file-based knowledge base) + a codebase harness (dev-local, e2e, crabbox cloud boxes, verify-before-ship) so agents can run, test, and ship code autonomously.
engineeringDynatrace observability skills and knowledge packages for AI coding agents.
