Plugins

スキルベースの実装計画書レビュー＆ブラッシュアップの反復ワークフロー

Secure access to Miro boards. Enables AI to read board context, create diagrams, and generate code with enterprise-grade security.

Secure access to Miro boards. Enables AI to read board context, create diagrams, and generate code with enterprise-grade security.

Give Claude an honest self-model — behavioral tendencies built from evidence, not session memory. Mirror persists observations across every session, enforces a verification threshold before anything becomes a tendency, and separates claims from evidence at the protocol level. Ships as a bundled plugin with a companion methodology skill: the skill provides the discipline, the MCP provides the persistence. Neither works alone. Install: `/plugin install mirror@mctx`. Tendencies require ≥3 supporting observations across ≥2 distinct sessions. Training resistance is logged separately. Deliberate experiments stay distinct from passive evidence. All data is per-user, AES-256-GCM encrypted, and accumulates indefinitely.

Miscellaneous utility skills for common Claude Code tasks.

Miscellaneous workflow utilities - commit messages, session handover

Mise-en-place integration with Task Trellis for AI coding agents

mise dev environment management — tool versions, environment variables, tasks, and project configuration

Run mission workflows with Kimi and Codex behind a single command surface.

SDLC workflow manager for Infiquetra's Jeff Intent, Asgard, and CAMPPS boards. Adds prepared issue drafts, live schema sync, project fields, labels, metrics, milestones, and rollout helpers via Python CLI.

from flanksource/claude-code-plugin

Mission Spec core API + Claude Code skills (ms-init, ms-eval, ms-status, ms-report, ms-context, ms-decide) + CLI (npx mission-spec) + Living Asset Registry + Architecture Registry + Reconstruction verifier + Cross-platform adapters (Cursor, Codex, OpenCode, Cline, Continue, Aider)

from ahmedxx99/claude-code-elixir

MixShift AI skills for Amazon advertising and retail operations against MixShift's MySQL warehouse (legacy dashamazon schema): Sponsored Ads (SP/SB/SD), DSP, Seller / Vendor Central revenue, orders, inventory, catalog. Warehouse access is read-only; the live Amazon API surface adds SP-API reports, retail lookups, AMC and DSP analytics, and Amazon Ads reads plus audited preview-gated writes. Ships mx-data-explore (querying + CSV export), the mx-amazon-* skills, PPC optimization skills, brand-context management (cold-start + render + edit + enrich + delta-merge), per-skill OCL calibration confirm-on-run, design-system HTML rendering, and onboarding commands.

Local-login-node PBS job management and documentation search for Miyabi.

ML-engineering (MLOps) team — 4 agents (ml-platform-architect, training-pipeline-engineer, model-serving-engineer, ml-monitoring-engineer) for the PRODUCTION lifecycle of ML models: the platform/architecture (build-vs-buy, the stack, the train->register->serve->monitor loop), reproducible training pipelines + experiment tracking + a model registry, feature stores and train/serve consistency (avoiding training-serving skew and leakage), model serving (online vs batch, the right deployment with shadow/canary), and monitoring (data + concept drift, performance decay, retraining triggers). 6 skills, a decision-tree knowledge bank (serving-pattern + retraining-trigger trees + a dated 2026 map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Seams: 'is the result significant?' -> applied-statistics, data pipelines -> data-platform/data-streaming, LLM/agent apps -> claude-app-engineering, deploy infra -> devops-cicd/cloud-native-kubernetes. Requires ravenclaude-core@>=0.7.0.

Autonomous ML research agent: HF ecosystem tools, ML-shaped GitHub search, research-first workflow discipline. Runs training on your HPC.

Cost-tiered subagents (explorer/implementer/test-runner/architect), haiku-powered git and quick-task commands, and a bash safety guard hook.

Auto-captures ML experiment runs via Stop hook. Provides /mllog (manual capture) and /logbook (report generation) commands.

Extract MLS property listings from PDF reports into professionally formatted Excel spreadsheets with subject property highlighting

from mconcat/mastermind

Software development planning workflow with requirements, ADRs, design specs, tech specs, and task decomposition

Vault-native memory for Claude Code. Markdown is ground truth. Hybrid retrieval, temporal knowledge graph, zero LLM cost on Stop, token-aware adaptive context.

Mo — winded.vertigo's chief marketing officer. Persistent memory across conversations.

Mixture-of-Agents for Claude Code: fan a task out to configurable opencode models (read-only over your repo), coordinated by a subagent, then let Claude aggregate, act, and have the experts review its plan and diff.

MoAI-ADK SPEC plan/run/sync 개발 방법론 무설치 플러그인 — moai CLI 없이 Claude Code/Desktop에서 DDD/TDD·품질 게이트·문서 동기화. 비개발자와 개발자 모두 /moai로 개발.

재무·세무 전담 AI 직원 — 재무제표 분석·결산 관리·차이 분석·IR, 개인 세금 절약·가계 예산·투자 입문·보험 적합성 스킬 11종. OpenDART 전자공시 MCP 연동. 이런 분께 추천: 사업자·재무 담당자·개인 재테크 입문자. ※ 세무사·회계사 자문 대체가 아닌 참고 자료입니다.

데이터·공공데이터 분석 전담 AI 직원 — 데이터 프로파일링·시각화, 공공데이터 조회(부동산·경매·주식·KOSIS·건축물대장·DART 전자공시) 스킬 11종. KOSIS 통계·건축HUB·DART MCP 연동. 자연어 요청 시 매칭 스킬이 자동 호출됩니다. 이런 분께 추천: 데이터 애널리스트·사무직·기획자·자영업 운영자.

구직자 편 커리어 코칭 전담 AI 직원 — 이력서·포트폴리오 첨삭, 면접 준비, 이직 전략까지 커리어 전환 실무 스킬. 인사채용(고용주 편)과 구분되는 구직자 관점입니다. 이런 분께 추천: 이직 준비자·취업 준비생·주니어 직장인.

경영·창업 컨설팅 전담 AI 직원 — 사업계획서·비즈니스 모델·시장 분석(TAM/SAM/SOM)·경영 진단 브리프·정부 지원사업 매칭·상권분석 보고서까지 전략 실무 스킬 6종. 이런 분께 추천: 예비 창업자·소상공인·스타트업 운영자.