114 плагинов из публичных маркетплейсов Claude Code. Каждый объединяет навыки, слэш-команды, агентов, хуки или MCP server, которые устанавливаются вместе.
Показано 114 плагинов, соответствующих фильтрам.
claude-code-skillsalirezarezvani/claude-skills2
potetos-for-everyoneTheOnlyFusionCube/potetos-for-everyone2
awesome-journal-skillsbrycewang-stanford/Awesome-Journal-Skills1
trailofbitstrailofbits/skills1Отправьте репозиторий с .claude-plugin/marketplace.json, и мы перечислим каждый плагин.
Отправить marketplaceComprehensive codebase cleanup across 11 quality dimensions — dead code, duplication, weak types, circular deps, defensive cruft, legacy code, AI slop, type consolidation, security, performance, and async patterns. Confidence scoring and build verification gates.
Portable operating method: session lifecycle agents, pre-ship code review, deploy with live verification and state doc update, and production log health check
Twelve CAV-specific skills for the International Conference on Computer Aided Verification and its Springer LNCS open-access proceedings, grounded in the CAV 2026 (FLoC, Lisbon) call, the LNCS proceedings, i-cav.org, and dblp.
academicTurn any domain folder of skills into a bounded agentic loop: a manifest builder inventories a domain's skills/tools/checks, a goal compiler turns a goal into a verifiable task plan (refusing vague goals with forcing questions), and a JSON-backed loop controller drives execute->verify->close with retry caps, controller-run verification (no verification theater), human escalation on exhausted budgets, and a close gate that refuses while any task is unverified or unwaived. Ships 3 stdlib Python tools, 18 committed per-domain harness manifests + JSON schema, 3 references citing the 2024-2026 agent-harness canon (Anthropic long-running harnesses, verifier's law, SWE-agent, Ralph loop, Cognition), harness-runner agent + /cs-harness command. Use when an agent or subagent should pick up a goal, define its tasks, complete and verify them, and close the loop.
Human-verification gate for an agent loop: builds a single-file review page (the page itself makes no network request; a reviewed HTML artifact's own https: assets still load), collects batched feedback as structured batch.v1 data instead of chat prose, and refuses to close while a BLOCKER is open, the reviewer is unnamed, or nobody has reviewed. Non-blocking, headless-guarded, round-capped. Stdlib-only.
Systematic false positive verification for security bug analysis with mandatory gate reviews
UI Kit skills for integrating CometChat across React v7, Angular v5, React Native v5, Android v6 (Kotlin/Compose), iOS v5 (Swift/UIKit, SPM) and Flutter v6. The /cometchat dispatcher detects your project — web (React on Vite/Next/CRA, or Angular) or mobile (React Native/Expo, Android, iOS, Flutter) — and routes to task-shaped skills (core, components, placement, customization, features, calls, push, migration; plus platform patterns). Headless Calls SDK skills cover calling without a UI Kit. Run `/cometchat add chat to my app` to start. Thin entry with progressive disclosure. Skills read always-current docs through the bundled CometChat Docs MCP, and a CI-gated verification pipeline backs them: every skill is checked against its pinned kit (symbol catalog + compile fence), and several families also pass a live simulator/emulator smoke (per-family status in peers.yaml).
The design taste pack: a five-stage UI pipeline (direction, system, motion, critique, verification) that stops generic AI-looking interfaces, plus pointers to five specialist design skills with install commands and author credit
Teaching skill: cookbook-style walkthrough for signed audit trails on every Claude Code tool call. Cedar policy, Ed25519 receipts, offline verification, CI/CD integration, SLSA composition. Pairs with the protect-mcp runtime plugin.
Complete GRACE methodology: semantic markup, knowledge graphs, module contracts, testing, and log-driven verification for AI-driven engineering
Product strategy skills: find-your-moat front door, 6-step strategy framework, competitive analysis, VRIO, strategic moats, ecosystem strategy, pre-mortem risk analysis, verification, stakeholder alignment, decision log, and prioritization
Lauren Tan's pstack & Poteto Mode engineering workflow for Claude Code: evidence-first, minimal blast radius, TDD, and rigorous verification. Full v0.15.0+ upstream sync.
developer-toolsPoteto Mode workflow for Claude Code: disciplined engineering, systematic decomposition, and rigorous verification.
developer-toolsComprehensive guide and tools for writing frontend tests. 55 best practices, specialized agents for planning, analysis, verification, and healing.
Superpowers core skills plus a conservative ML-research layer (verification rungs, experiment design, result review). Fork of obra/superpowers.
요구 구체화부터 구현·검증·복구까지, 사전 합의 안에서 자율 진행하는 한국어 Claude Code·Codex 스킬 13개. 큰 흐름과 반드시 지킬 검증만 정하고 방법은 에이전트에게 맡긴다. / Korean agent skills for Claude Code & Codex: idea → PRD/TRD → architecture → plan → verification harness → autonomous loop, with up-front agreement, ordered quality gates and independent validation.
productivity
API contract testing with Pact, OpenAPI validation, and consumer-driven contract verification
Create secure webhook endpoints with signature verification and retry logic
Runs a substantial task through a mandatory built-in intake grill, then 10 gated stages (docs, brainstorm+decompose, spec, plan, subagent build, tests, lint/deploy, post-deploy, docs/wiki, acceptance). Every stage's doctrine is built into the skill — no companion plugin required — with typed auto/judgment/manual gates, a frozen requirement spine that closes with evidence, a work board and a verification ledger that outlive a run, an exposure line naming what shipped unconfirmed, a progress rail computed from the project's own config, a proportional short path for small changes, a loop guard whose ceilings stop and record a blocker, and stage-3 tracks for what a product does, how it sounds and how it looks. Two modes need no task: `checkup` (what is unverified) and `setup` (audit existing docs); a third, `waves`, takes the whole board and closes it in waves that each finish in one pass. Retro insights can publish upstream as issues, opt-in and redacted.
developmentPlan the work. Control the context. Ship with proof. Buddy is a coding companion for developers that carries engineering work from research and planning through implementation and verification.
development
