594 плагинов из публичных маркетплейсов Claude Code. Каждый объединяет навыки, слэш-команды, агентов, хуки или MCP server, которые устанавливаются вместе.
Показано 594 плагинов, соответствующих фильтрам.
coalwashTheColliery/CoalWash1
english-exam-coachOleksiiDotsenko/english-exam-coach1
pmstackRyanAlberts/pmstack1
aipom-skillsdeanpeters/ai-product-operating-model-skills1Отправьте репозиторий с .claude-plugin/marketplace.json, и мы перечислим каждый плагин.
Отправить marketplaceCoordination layer for multi-agent repositories. Gives task-pipeline runs leases with a TTL, race-free ID reservation, a cross-repo signal feed, an append-only run journal and a machine-generated read-only board. A lease is decided by a primitive that genuinely has compare-and-swap — an atomic file create on one machine, a pushed git ref across machines — never by the knowledge base, which loses concurrent writes; the store carries the record and the ID allocation, which is positional over the merged log. The knowledge backend is a pluggable adapter (Outline, filesystem) declaring its own capabilities and degrading out loud. Ships Claude Code hooks that deny edits to guarded registry files without a live lease.
developmentHelper skill and commands for installing and using the full Overdrive CLI skill system.
developer-toolsMemory-defragment/cleanup engine for agent memory, TWO lanes: class-B (memory + governance files) gets the semantic wash — a free mechanical Quick pass plus a code-enforced fidelity gate blocking any STRUCTURED-token drop by diff (links, dates, versions, frontmatter; prose fidelity is the paid semantic layer's job), consent-gated Full pass, every cut snapshot-backed (whole-run rollback); class-A (transcripts — the estate) gets byte-identity ULTRA archiving, never semantic-edited. Honest frame: slows how fast memory-overhead grows — it does not eliminate memory cost. Zero-dependency, offline, no API keys.
Exam coach for IELTS, TOEFL iBT and Cambridge B1-C2: original practice with criteria-based feedback, mistakes re-tested on fresh items, full-test reviews with an error catalog, and printable practice sheets. Local files only, original content only.
Error discovery for AI products: read real traces, name failure modes and success modes by stage, and turn the ones that matter into code checks and AI judges you can trust. Includes Eval Studio and a zero-dependency command-line tool.
Assess, design, and improve organizational practices for AI-powered products and AI-assisted product work.
productivitySelf-contained agentic development harness: one command runs the full feature pipeline with double review and security gates.
Coverage, security and code quality for coding agents.
Apache Magpie — adversarial review: runs other models' CLIs (Codex, Copilot, Antigravity, Pi, Grok, Goose, Claude) read-only over a change before its PR is created, and merges their findings. Runs from the installed plugin, so no repository needs a copy.
Deploy and manage GPU instances, move models into /vault, and debug the GPUtw API in natural language — a knowledge skill plus 22 MCP tools.
deploymentFind and verify current repository/news topics and prepare voice-matched drafts.
Version control system for Claude Code agent skills — git for SKILL.md files.
productivitySearch, discover, and install AI agent skills from 7 registries with quality scoring and cross-platform support
3 skills for reference-first Blender modeling, image-to-textured-3D generation, and safe AI 3D scene assembly.
161 agent skills, 63 slash commands, 6 subagents for Claude Code, effort-routed for Opus 5.5. Install: /plugin install kenji@kenji
Model/effort router: delegate a task you CAN do but is large+cheap DOWN to a lower tier to save tokens; escalate a task beyond the current tier UP for quality — up to the fable rung, the top of the ladder (a consent-gated, real-money spawn). Two-knob routing (tier × effort, effort-before-tier), an alias-floor tier ranking (haiku<sonnet<opus<fable + modelTiers pins) the platform resolves at spawn-time, a validity-gated ranking Lock that never routes on broken state, and git-optional damage control. Advise-only Phoenix-pure hook; the model performs the routing. Claude Code only.
The product-manager OS that gets better the more you use it: a CLAUDE.md operating brain, a memory that learns your product and team (3-min /setup), and a self-improving loop that watches the work you repeat and builds you custom skills for it. Plus 53 book-grounded skills across discovery → strategy → execution → launch — every one scored in CI and gated against regression — a workspace your artifacts land in, two isolated workers (critic + researcher), live connectors that write your work back to Linear/Notion/Slack, 5 chained workflows, ready-to-wire automations, and bundled getprompts + getskills libraries.
productivityA resume builder and job finder for Claude Code: merge the resumes you already have into one experience bank, score roles against goals you set, build a tailored ATS-safe resume per job, and prove a machine can still read it. It never applies for you.
Design, generate, and run multi-agent AI pipelines — scope-aware, multi-pipeline, spec-driven, write/review-isolated, with step-level create/update/delete and integrated audit
development50+ consulting frameworks used by McKinsey, BCG, Bain, and Accenture
