Find plugins

by Victor Ryabov

Turn the current directory into a teaching workspace - a mission, curated sources, short interactive lessons, and a record of what you have actually learned

团队 AI 编程标配：编码规范（含安全红线）与架构规范（Go）、Go 开发规范（godev）、后端/前端测试规范、规格 skills（techspec、sddspec、tech-diagram-design）、团队知识库（kb skill + kb-reviewer + /kb-health）、提测命令、SDD 交付循环（/devloop + test-writer/reviewer/implementer 三角色，contract 按行为编号逐条收敛）

by alan-oliv

A live browser console for Claude Code agent teams — every teammate's transcript, tasks, mail and status in one window. Starts itself the first time a team is spawned.

by Jung Jiwon & Lee Jongkwan

The technical-writing role on contract v3: 독자가 알아야 할 것을 어떻게 구조화할지. use_when: 외부 공개 문서가 필요할 때. Hand-off: 개발자 대상 온보딩이면 → devrel.

by Teknesyum

Counts touched files, shows them on the statusline, speaks once at a threshold, hands the next session a machine-written handoff. Zero tokens on an ordinary turn.

by Teknesyum

One token file, every interface: generated themes, a scanner and hooks that keep each project on your UI layout. Off until a teknesyum-ui.json exists.

by fateLiang

Telegram channel for Claude Code — messaging bridge with built-in access control. Durable inbound store so messages survive a disconnected session (replayed on restart with a structured replay flag), forward/reply attribution, the sender's highlighted quote, and ask_decision buttons. Manage pairing, allowlists, and policy via /telegram:access.

by Minh

A minimal working example plugin. Copy this directory to start a new plugin in this marketplace.

by Vivswan Shah

Replace with a short description of the skill.

by Ivan-WG

Chat-message brevity as a shape contract, not a word filter: prose-line budgets per turn kind, a fixed work-done skeleton (verdict → artifacts → max 5 findings → blocker → next), and a named cut list. Levels lite/full/ultra plus wenyan (classical-Chinese novelty) variants, hook-reinforced each turn. Out of scope: code, files written, subagent prompts, and how much work a turn does. Ships /terse:commit, /terse:compress, /terse:check, three compressed-return agents, and an opt-in MCP catalog shrinker.

by David Kim

Authoring gate and evidence-first audit workflow for tests: junk patterns, retention bar, containment before pruning, and preservation proof before any deletion, with an always-on nudge. Adapted from OpenClaw (MIT).

by Jung Jiwon & Lee Jongkwan

The test-authoring role on contract v3: 테스트 코드 자체가 격리성·fixture 전략 면에서 좋은 설계인가. use_when: 신규/기존 테스트 스위트를 설계·리뷰할 때. Hand-off: 실제 실행 결과 관찰은 → execution-observation.

by test-autoevermation-harness-plugin maintainers

Spring 기반 테스트코드 생성 하네스 (Spring Boot 2.0–4.x 버전 인식). 환경 세팅 전용 명령(setup-harness — MCP 런타임·JavaParser jar·JDT LS·상태줄) 선행 → 버전 프로파일 감지 → 인터랙티브 설정 → 빌드 능력 프로비저닝(JaCoCo XML)·캐시 프라이밍 → AST/소스/스펙 분석 → 리팩토링 권고 게이트(복잡도·비효율·테스트 저해 코드 판정, test_docs/refactoring/ 권고 문서 + 포함/제외 결정) → 시나리오 → 사용자 승인 게이트(test_docs/ 저장) → 테스트 생성(javax/jakarta·JUnit4/5·@MockBean/@MockitoBean 자동 분기, 시나리오 target 호출 자가 검증 게이트) → 실행 → 보정 → near-100% 커버리지 게이트(JaCoCo) → 시나리오 적합성 검증(target 호출 기계 대조) → 적합성 자동 보정 루프 파이프라인을 11개 에이전트와 Python 기반 공유 MCP 3종(JavaParser AST 포함)으로 오케스트레이션하며, 파이프라인 종료 후 사용자 지시로 기존 테스트를 편집하는 test-editor(edit-tests)를 별도로 제공한다.

by Ivan-WG

Testing best practices: test pyramid and what to actually test, Pest/PHPUnit and Vitest/Jest idioms, Playwright/Dusk e2e discipline, factories and fixtures, mocking boundaries, flaky-test causes, coverage traps — plus the TDD workflow (red-green-refactor, red-green regression proof for bug fixes). Includes /testing:flake-hunt and a test-engineer worker agent; the test rubric reaches any diff through /code-review:review.

by Fixture Author

Ties each test to the requirement it covers and writes analysis/tether/coverage.json. Writes only that directory.

by cjthompson

Reference skills for the Textual TUI framework — CSS properties and widget API

by claude-contrib

Sequential thinking MCP server for structured problem analysis

by ziyilam3999

The 3-role development model as a Claude Code plugin: planner -> plan-review -> executor -> execution-review, each a separate subagent, never self-review. Also ships Autonomous Pipeline Mode — a Stop hook that catches stopping to ask permission for an already-approved step, plus a post-compact resume sequencer (ELI5 + 3-tier re-sequence + one approve-gate) and its doctrine. Bundles the role-enforcing hooks, the orchestration skills, a memory-search shim, the standalone doctrine, and a scaffolding command that makes the model the default for new skills, agents, hooks, and commands.

by tickadoo Inc.

Discover and book theatre, tours, attractions, and live experiences worldwide. Search, compare, check live availability, plan itineraries, and get direct tickadoo booking links. No API key required.

by Casey Bisson

Exploratory and reactive-investigation skills for Grafana incidents via the timebuddy-incident-investigator MCP server.

by Kyle Tabor

Tmux session control for Claude Code — launch test sessions, send commands, read output with multi-agent safety

by Alexander Kurganov

Goldratt's Theory of Constraints Thinking Processes, applied to software systems and their architecture. The skill answers three questions in order. What to change: the Current Reality Tree. To what to change: the Evaporating Cloud, then the Future Reality Tree with negative-branch reservations. How to cause the change: the Prerequisite Tree, then the Transition Tree. Every link in a sufficiency tree is scrutinised with the Categories of Legitimate Reservation, and the user confirms the core problem before the cloud is built. The skill carries the procedure. The depth behind each tool and the categories sits in references beside it, each with its source. No script, no network, no credentials.

by Hamza Siddiq

A live forecast of the context window, in the band above the prompt. /token-weather turns it on or off.

by TokenLab

TokenLab model selection, API integration, native endpoints, cost routing, and OpenAI-compatible migration skills with optional TokenLab MCP servers.