Claude Code プラグイン
公開されている Claude Code marketplace からの 114 件のプラグインです。それぞれにスキル、スラッシュコマンド、エージェント、フック、MCP サーバーがまとめてインストールされます。
これらのフィルターに一致するプラグインを 114 件表示しています。 フィルターをクリア
Expose the plugin-safe Claude Code subset of Agentic Awesome Skills through a single marketplace entry.
Complete Cursor integration skill pack with 30 skills covering AI code editing, composer workflows, codebase indexing, and productivity features. Flagship+ tier vendor pack.
Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI configuration. Joins protect-mcp and signed-audit-trails in the governance category; composes with protect-mcp for runtime enforcement.
Docker-authored knowledge skills for AI coding agents across Dockerfiles, Compose, Docker Agent, Docker Sandboxes, and safe Docker workflows.
228 battle-tested traps mapping the footguns of Kotlin, Compose Multiplatform and desktop JVM development, in ten area skills plus a scanner — mined from a production codebase, every claim verified against the real tree.
engineering
Workflow-builder skill: design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool (CLAUDE_CODE_WORKFLOWS=1, /workflows). Every session opens with an intake question set; when the user is vague, a stdlib recommendation engine infers and proposes a topology with rationale instead of stalling. Ships 3 stdlib Python tools (intake recommendation engine, .js validator enforcing pure-literal-meta / no-non-determinism / guarded-loop / parallel-thunk rules, topology scaffolder), 3 references citing 7-8 authoritative sources each (API surface, orchestration patterns, decision + intake guide), templates + a runnable example, cs-workflow-architect persona agent + /cs-workflow-build slash command. Use when building, scaffolding, or running a custom Claude Code workflow or orchestrating sub-agents (fan-out, pipeline, loop, judge-panel).
Grade an agent setup from real conversation history — a rebuild of warpdotdev/common-skills' skill-doctor (MIT). Harvests recent local Claude Code and Codex sessions scoped to one repo, condenses and secret-redacts transcripts (12-pattern redactor, chmod-0600 artifacts, nothing uploaded), has the agent judge each transcript against two verbatim-preserved rubrics (efficiency, code quality — labels only), then runs a deterministic aggregation gate that derives every number from the label tables, refuses scores for unsampled sessions and suggestions that cite no scored session, and renders one self-contained zero-JS HTML report (dark-mode, print-to-PDF). Proposed skill edits stay staged as diffs until an explicit per-skill yes; zero suggestions is a valid, reportable success. Ships cs-skill-retro agent, /cs-skill-retro command, 3 stdlib tools, 3 references citing 7 sources each.
Research orchestrator (hybrid router + fallback). Deterministic SIGNALS classification routes to 6 specialists (pulse/litreview/grants/dossier/patent/syllabus) at >=2 signals, else runs own 8-step plan-decompose-search-synthesize-cite fallback. Routing transparency mandatory. Path-B from megaprompt 13.
Content creator skills: Content Repurposer, Hook Writer, Short-Form Script, Newsletter Writer, Creator Brand Kit, Creator Media Kit. Atomize one piece into a multi-platform pack (thread, LinkedIn, newsletter, carousel, Reel), write scroll-stopping hooks, script TikToks/Reels/Shorts, draft newsletter issues, define your niche/voice/pillars, and land sponsorships. The craft layer of the creator stack — pairs with the ContentGoldMine app for one-click automation.
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).
Claude for Trainers and Facilitators: 32 Claude skills for one session or programme, from the first brief to the follow-up weeks later, in seven stages: frame it with the purpose brief, the sponsor call and the participant survey; design the session plan, the agenda, the time budget, the activities, the role plays and the virtual version; prepare the invitation, the run sheet, the facilitator guide, the slides and the handout; run it with openers, agreements and consent, a difficult moments plan, debrief questions and the wall capture; make it stick with the action plan, the practice task, follow-up messages, spaced recall and two skills for managers; review it with the feedback form, the summary, the retro and the sponsor debrief; then the proposal, the programme and the handover. For corporate trainers, facilitators and independent consultants who run workshops. Claude prepares the session and the follow-up; you read the room and decide what happens in it, no participant is ever grad
productivityClaude for Account Executives: 32 Claude skills for working named accounts, from account research to win/loss review, in eight stages: know the account with a research brief, a stakeholder map and an account plan; find a true reason to call with a buying signals brief and a talk track; prepare and run the meeting with a call plan and discovery questions; write it up the same day in call notes and a recap email; propose with a brief, the proposal and a quote check; negotiate and close with a negotiation plan and a mutual action plan; run the pipeline and forecast on written evidence; review the deal with MEDDPICC and a win/loss review. For account executives, key account managers and the sales and business development leaders who run them. Claude prepares from public sources and your own notes and you have the conversation; it never invents a contact, a signal, a number or a customer quote, never rates a buyer or a seller, and never contacts anyone for you.
productivityDocker and container development — Dockerfile optimization, docker-compose orchestration, multi-stage builds, security hardening, and CI/CD container pipelines.
End-to-end chaos engineering discipline: design experiments with hypothesis + steady-state metric + blast radius + abort criteria, calculate risk score against error budget, and generate blameless postmortems. 3 stdlib Python tools (experiment_designer, blast_radius_calculator, experiment_postmortem), 4 references on chaos principles + experiment design + 7-attack taxonomy + tooling landscape (Chaos Toolkit/Mesh/Litmus/Gremlin/AWS FIS/DIY), templates, and /chaos-experiment slash command. Composes with feature-flags-architect (kill switches as abort triggers) and kubernetes-operator (chaos targets).
A disciplined coding pipeline that grounds code in verified structure before a line is written: Discuss -> Map -> Decompose -> Execute -> Verify, with a lazy-senior-dev YAGNI ladder that deletes unnecessary code first. No invented APIs, no assumed imports, no placeholder code. Opt-in for high-stakes, complex, or multi-file work; not for trivial edits. Synthesizes four MIT/open-source projects (Ralph atomic loop, GSD Core context engineering, Graphify KNOWN/INFERRED/UNKNOWN mapping, Ponytail lazy-senior hierarchy). Contributed via PR #854.
HIG Doctor bundles 14 Apple HIG skills (foundations, platforms, patterns, inputs, technologies, and 8 component categories), an MCP server (hig_list_skills / hig_lookup / hig_search / hig_audit / hig_audit_file / hig_explain_finding), and a Bun-based CLI auditor that detects 431 HIG rules across SwiftUI, UIKit, AppKit, watchOS, visionOS, React, Vue, Svelte, Angular, Compose, Android XML, React Native, Flutter, CSS, and HTML.
Scan Android APKs for Firebase security misconfigurations including open databases, storage buckets, authentication issues, and exposed cloud functions. For authorized security research only.
Compose repository baseline, safe refactoring and contributor onboarding through selected specialist owners.
Rigorous engineering process for AI coding agents: implement-spec, decompose-spec, orchestrate-build, build-memory, synthesize-spec, reconcile-build, self-review, review-pr, address-pr-comments, agent-docs, refresh-repo-docs
Rank higher and grow organic traffic with programmatic SEO, technical audits, and Search Console optimization. Create email sequences that convert, build compelling case studies, and generate professional infographics. Repurpose YouTube content into LinkedIn posts, newsletters, GIFs, and visual diagrams.