insightflo/claude-impl-tools

Última actividad de origen registrada: 6 de abril de 2026 a las 03:40

Catálogo de SkillsMP actualizado: 12 de noviembre de 2026 a las 12:52

skills recopiladas: 28

Estrellas en GitHub: 17
Forks en GitHub: 3

Instalar con un asistente de IA

Copia este prompt en el asistente de IA que estés usando.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/insightflo/claude-impl-tools.

README del repositorio

Archivo de origen del README: README.md

Leer el README original

Mostrar README completo

# claude-impl-tools > **Implementation skill pack for Claude Code** — Build software with AI agent teams [**English**](./README.md) | [**한국어**](./README_ko.md) A plugin of **28 skills** for Claude Code. Covers the full dev lifecycle: planning, orchestration, quality, security, maintenance, and skill ecosystem intelligence. Skills auto-install project-level hooks and agents on demand. --- ## Quick Start ### Option 1: Plugin Install (Recommended) Launch Claude Code, then run: ``` /plugin marketplace add insightflo/claude-impl-tools /plugin install claude-impl-tools@insightflo ``` ### Option 2: Quick Install (No plugin) ```bash curl -fsSL https://raw.githubusercontent.com/insightflo/claude-impl-tools/main/scripts/quick-install.sh | bash ``` This clones the repo and symlinks skills. No hooks or agents installed — skills handle that on demand. --- ## What You Get | Component | Count | Installed when | |-----------|-------|----------------| | **Skills** | 28 | Plugin install | | **Hooks** | up to 17 | On demand (skill runs `install.sh --local`) | | **Worker Agents** | 4 | On demand (project-level) | | **Templates** | 11 | On demand (project-level) | --- ## Skills (28) ### Core Workflow | Skill | What it does | |-------|--------------| | `/workflow` | **Meta hub** — analyzes project state, recommends the next skill (rules + experience hybrid) | | `/agile` | Layered sprints (Skeleton → Muscles → Skin) for 1-30 tasks | | `/recover` | Resume work after CLI crashes, network drops, or agent errors | | `/checkpoint` | Two-stage code review at task/PR completion | ### Project Initialization | Skill | What it does | |-------|--------------| | `/si-planning` | SI requirements engineering — Socratic elicitation, domain checklist, auto-generated deliverables (requirements analysis / functional spec / screen spec / traceability matrix), change impact analysis, customer dashboard | | `/governance-setup` | Set up Agent Teams governance or Mini-PRD | | `/tasks-init` | Generate TASKS.md from scratch | | `/tasks-migrate` | Consolidate legacy task files into TASKS.md | ### Quality & Security | Skill | What it does | |-------|--------------| | `/quality-auditor` | Comprehensive audit + verification discipline + quantitative metrics (v3.0) | | `/security-review` | OWASP Top 10, CVE, secrets detection | | `/multi-ai-review` | Claude + Gemini + Codex 3-AI consensus engine with domain presets | ### Orchestration | Skill | What it does | |-------|--------------| | `/team-orchestrate` | **Unified engine** — 3 modes: `auto` (Task dispatch), `team` (Agent Teams API), `thin` (ultra-minimal for 50-200 tasks) | | `/cmux-orchestrate` | cmux-based multi-AI team — Claude/Gemini/Codex in physical parallel | | `/cmux-ai-run` | cmux pane-split parallel task execution | | `/cmux-ai-review` | cmux pane-split parallel 3-stage review | | `/multi-ai-run` | Role-based AI model routing (Codex=code, Gemini=design, Claude=plan) | | `/whitebox` | Execution control plane — state, health, approvals | | `/cmux` | cmux terminal multiplexer control | ### Maintenance & Analysis | Skill | What it does | |-------|--------------| | `/maintenance` | ITIL 5-stage production maintenance orchestrator | | `/impact` | Blast radius and risk analysis before file modification | | `/deps` | Dependency graph + circular dependency detection | | `/changelog` | Change history query by domain/date/author | | `/coverage` | Test coverage analysis and gap identification | | `/architecture` | Project structure and tech stack visualization | | `/compress` | Context optimization with self-editing `/prune` (H2O + Context-1 pattern, v2.0) | | `/statusline` | TASKS.md progress in Claude Code status bar | ### Skill Intelligence | Skill | What it does | |-------|--------------| | `/memento` | **Skill ecosystem engine** — experience logging, smart routing, failure reflection, harness generation, cross-project knowledge via DuckDB | --- ## Memento: Skill Ecosystem Intelligence `/memento` learns which skills work best for which tasks and improves the ecosystem over time. | Mode | Purpose | |------|---------| | `log` | Record skill execution outcomes (auto via PostToolUse hook) | | `route <task>` | Experience-weighted skill recommendation | | `health` | Unified skill dashboard across all projects | | `reflect <skill>` | Analyze failure patterns, suggest SKILL.md fixes | | `harness <skill>` | Generate validation scripts from failure patterns (AutoHarness-inspired) | | `global search` | Cross-project knowledge search via DuckDB | | `global recall` | Topic-specific cross-project learning retrieval | ### Prerequisites for Memento Memento's SKILL.md is included in the plugin. The execution infrastructure requires one-time global setup: ```bash # 1. Install DuckDB pip install duckdb # 2. Initialize the global experience store python3 -c " import duckdb db = duckdb.connect('$HOME/.claude/memento/experience.duckdb') # Tables are auto-created on first use db.close() " # 3. Add experience logging hook to ~/.claude/settings.json # (See Harness Infrastructure below) ``` --- ## Orchestration Modes `/team-orchestrate` auto-selects the right mode based on task count: | Task count | Mode | How it works | |-----------|------|--------------| | 1-50 | `--mode=auto` | Direct Task dispatch, worktree-based phases | | 10-80 | `--mode=team` | Agent Teams API, 3-level hierarchy | | 50-200 | `--mode=thin` | Ultra-minimal context (76% token reduction) | ```bash # Examples /team-orchestrate # auto-selects mode /team-orchestrate --mode=thin # force thin mode /auto-orchestrate # alias for --mode=auto ``` --- ## Agent Teams Uses Claude Code native **Agent Teams** with `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`. ``` Your Claude session (= team lead) ├── architecture-lead │ ├── backend-builder │ └── reviewer ├── design-lead │ ├── frontend-builder │ └── designer └── qa-lead ``` ### Enabling Agent Teams ```bash bash plugin/project-team/install.sh --local --mode=team ``` Or let `/team-orchestrate` auto-install when needed. ### Project-level hooks (installed on demand) | Category | Hooks | |----------|-------| | **Permission** | `permission-checker`, `domain-boundary-enforcer` | | **Safety** | `pre-edit-impact-check`, `risk-area-warning`, `security-scan` | | **Quality** | `standards-validator`, `design-validator`, `interface-validator`, `quality-gate` | | **Gates** | `policy-gate`, `contract-gate`, `risk-gate`, `docs-gate` | | **Sync** | `architecture-updater`, `changelog-recorder`, `cross-domain-notifier`, `task-sync` | ### Hook modes | Mode | Hooks | Use case | |------|-------|----------| | **lite** | 4 | MVP, startups | | **standard** | 7 | Most projects | | **full** | 17 | Regulated industries | | **team** | 8 + Agent Teams hooks | Team orchestration | --- ## Harness Infrastructure (Global) The plugin works out of the box, but full harness engineering features require global setup in `~/.claude/`: ### Invariant Hooks (PreToolUse) Enforce rules with code, not just instructions. Add to `~/.claude/settings.json`: ```json { "hooks": { "PreToolUse": [ { "matcher": "Write|Edit", "hooks": [ { "type": "command", "command": "bash ~/.claude/memento/invariants/cross-domain-guard.sh", "timeout": 3 }, { "type": "command", "command": "bash ~/.claude/memento/invariants/sensitive-file-guard.sh", "timeout": 2 } ] }, { "matcher": "Bash", "hooks": [ { "type": "command", "command": "bash ~/.claude/memento/invariants/test-before-commit.sh", "timeout": 3 } ] } ], "PostToolUse": [ { "matcher": "Skill", "hooks": [ { "type": "command", "command": "bash ~/.claude/memento/log_skill.sh", "timeout": 5 } ] } ] } } ``` ### Global files | File | Purpose | |------|---------| | `~/.claude/memento/experience.duckdb` | Unified experience store (DuckDB) | | `~/.claude/memento/query.py` | CLI: `search`, `health`, `recall`, `sync`, `sql` | | `~/.claude/memento/log_skill.sh` | PostToolUse hook — auto-log skill executions | | `~/.claude/memento/update_outcome.py` | Update experience outcome with failure taxonomy | | `~/.claude/memento/invariants/*.sh` | PreToolUse invariant enforcement scripts | --- ## Recommended Workflow ``` Start │ ├─ "What should I do?" ────────────── /workflow │ ├─ Plan your project │ ├─ Large project? ──────── /governance-setup │ └─ Generate tasks ───────── /tasks-init │ ├─ Implement (choose by scale) │ ├─ Small (≤30 tasks) ───── /agile auto │ ├─ Medium (30-50) ──────── /team-orchestrate --mode=auto │ ├─ Large (50-200) ──────── /team-orchestrate --mode=thin │ └─ With cmux ────────────── /cmux-orchestrate │ ├─ Maintain │ ├─ Before editing ──────── /impact │ ├─ Bug fix ──────────────── /maintenance │ ├─ Check dependencies ──── /deps │ └─ Review changes ──────── /changelog │ ├─ Quality │ ├─ Test coverage ───────── /coverage │ ├─ Security scan ───────── /security-review │ ├─ Pre-deploy audit ────── /quality-auditor │ └─ Context cleanup ─────── /compress (or /prune) │ ├─ Skill ecosystem │ ├─ Skill performance ──── /memento health │ ├─ Cross-project recall ── /memento global recall │ └─ Improve a skill ─────── /memento reflect <skill> │ └─ If interrupted ───────────── /recover ``` --- ## Repository Structure ``` claude-impl-tools/ ├── .claude-plugin/ │ └── marketplace.json # Marketplace manifest ├── plugin/ │ ├── .claude-plugin/ │ │ └── plugin.json # Plugin manifest (version, metadata) │ ├── skills/ # 26 skills (auto-discovered) │ │ ├── memento/ # Skill ecosystem intelligence │ │ ├── team-orchestrate/ # Unified orchestration (3 modes) │ │ ├── quality-auditor/ # Comprehensive audit (v3.0) │ │ ├── context-optimize/ # H2O + self-editing (v2.0) │ │ └── ... │ └── project-team/ # On-demand project setup │ ├── install.sh # Local installer │ ├── agents/ # Worker agents │ ├── hooks/ # Validation & governance hooks │ └── templates/ # Protocols, ADR, contracts └── scripts/ └── quick-install.sh # Alternative install (clone + symlink) ``` --- ## Requirements | Component | Requirement | |-----------|-------------| | All skills | Claude Code CLI | | `/memento` global features | Python 3.10+, `pip install duckdb` | | `/multi-ai-review`, `/cmux-ai-*` | `gemini` CLI, `codex` CLI (optional) | | `/cmux-*` skills | [cmux](https://github.com/nicholasgasior/cmux) terminal multiplexer | | Project Team hooks | Node.js 18+ | | Agent Teams | `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` | | Invariant hooks | Global `~/.claude/memento/invariants/*.sh` setup | --- ## Version History | Version | Changes | |---------|---------| | **4.7.0** | /si-planning skill (SI requirements engineering, domain profiles, customer dashboard), GSD benchmark integration | | **4.6.0** | GSD patterns: context monitoring hooks, /discuss skill, goal-backward verification, deviation rules, autonomous mode | | **4.5.0** | context-optimize v2.0 (self-editing /prune), hybrid recall | | **4.4.0** | Unified DuckDB experience store, memento global mode | | **4.3.1** | memento harness mode (AutoHarness-inspired validation) | | **4.3.0** | memento skill, team-orchestrate 3-mode unification, quality-auditor v3.0 | | **4.2.0** | cmux live-mode: paste-buffer + callback scripts | | **3.5.x** | cmux skills, auto-revision quality improvements | | **3.4.0** | Agent Teams API migration | --- ## License MIT License - Copyright (c) 2026 Insightflo Team --- **[English](./README.md) | [한국어](./README_ko.md)**

Cargando el README del repositorio…

Skills en este repositorio

Desarrolladores de software Analistas de sistemas informáticos Analistas de garantía de calidad de software y probadores Otras ocupaciones informáticas

10 categorías ocupacionales · 100% clasificado

skill

ocupación

descripción

actualizado

memento

Desarrolladores de software

Cross-project experience memory — your persistent knowledge base across sessions. Remembers what worked, what failed, and why, so every new session starts smarter. Log outcomes → recall lessons → apply patterns. Use when starting work that other projects have…

Idioma del texto original: inglés

2026-04-06

cmux-ai-review

Desarrolladores de software

cmux 창 분할 기반 멀티-AI 합의 리뷰 엔진. 동일 워크스페이스에서 Gemini/Codex 패널을 나란히 분할해 3-Stage 파이프라인(의견 → 반론 → 합성)을 진짜 병렬로 실행합니다. multi-ai-review의 순차 실행 대신 두 AI가 동시에 리뷰하는 것을 실시간으로 볼 수 있음. "/cmux-ai-review", "cmux 코드 리뷰", "AI 패널 리뷰", "병렬 리뷰" 등 cmux 환경에서 여러 AI의 동시 리뷰가 필요한 요청이라면 반드시…

Idioma del texto original: coreano

2026-04-01

multi-ai-review

Analistas de sistemas informáticos

Claude + Gemini CLI + Codex CLI multi-AI consensus engine. 3-Stage Pipeline (opinions → rebuttal → synthesis) drives consensus across domains: code review, market analysis, investment diligence, risk assessment, and more. Automatically detects domain from…

Idioma del texto original: inglés

2026-04-01

multi-ai-run

Otras ocupaciones informáticas

Routes each agent role to the optimal AI model (Claude/Gemini/Codex) and executes it. Automatically assigns Codex for code writing, Gemini for design, and Claude for planning and orchestration. Use this skill whenever you see "use Codex for code", "use Gemini…

Idioma del texto original: inglés

2026-04-01

quality-auditor

Analistas de garantía de calidad de software y probadores

Comprehensive quality audit before phase completion or deployment. Performs planning conformance, DDD validation, security checks, tests, browser verification, and quantitative metrics. Also enforces verification-before-completion discipline — no claims…

Idioma del texto original: inglés

2026-04-01

cmux-ai-run

Otras ocupaciones informáticas

cmux 창 분할 기반 멀티-AI 병렬 태스크 실행. 동일 워크스페이스에서 Codex(코드)/Gemini(디자인)/Claude(계획)를 패널로 분할해 동시에 실행합니다. multi-ai-run의 순차 실행과 달리 진짜 병렬. "/cmux-ai-run", "cmux로 AI 분업", "창 분할 병렬 실행", "codex gemini 동시 실행" 등 cmux 환경에서 여러 AI를 동시에 돌리고 싶은 요청이라면 반드시 이 스킬을 사용하세요.

Idioma del texto original: coreano

2026-03-29

si-planning

Especialistas en gestión de proyectos

SI 프로젝트 요구사항 공학 스킬. 소크라테스식 요구사항 수집 → 도메인별 체크리스트 검증 → 산출물 자동 생성(요구사항분석서/기능정의서/화면정의서/추적표) → 변경 영향 분석. 대시보드 연동으로 고객 공유 지원.

Idioma del texto original: coreano

2026-03-29

workflow-guide

Desarrolladores de software

Routes you to the right skill for any situation by auto-analyzing project state. Use this whenever you are unsure what to do next — it diagnoses the project and recommends the optimal skill. Invoke immediately on "what should I do?", "which skill?",…

Idioma del texto original: inglés

2026-03-29

agile

Gerentes generales y de operaciones

Agile Sprint Master for regular user check-ins and sprint management. Use this for /agile, /sprint, starting a sprint, checkpoint requests, or any time you are running structured iterative development. Triggers on "start sprint", "checkpoint", "sprint…

Idioma del texto original: inglés

2026-03-29

discuss

Especialistas en gestión de proyectos

Gray area 식별 및 사용자 결정 수집. CONTEXT.md를 생성하여 downstream 에이전트가 재질문 없이 작업 가능. GSD discuss-phase 패턴 기반.

Idioma del texto original: coreano

2026-03-29

team-orchestrate

Gerentes de sistemas informáticos y de información

Unified orchestration engine with 3 modes: team (Agent Teams API, 3-level hierarchy), auto (direct Task dispatch, worktree-based phases), and thin (ultra-minimal context for 50-200 tasks). Use this skill for any multi-task project execution — it auto-selects…

Idioma del texto original: coreano

2026-03-29

context-optimize

Desarrolladores de software

Long context optimization with self-editing — extract key information, compress, summarize, and auto-prune stale context using the H2O + Context-1 patterns. Use this whenever documents are too long, the context window is running low, you need to synthesize…

Idioma del texto original: inglés

2026-03-27

cmux-orchestrate

Desarrolladores de software

cmux 기반 멀티-AI 팀 오케스트레이션. cmux 워크스페이스에 Claude/Gemini/Codex를 독립 프로세스로 배치해 물리적 다중 레벨 팀을 구성합니다. Agent Teams API 없이 진짜 병렬 실행. 이기종 AI 팀 구성, 사이드바 실시간 모니터링, 동적 팀 확장/축소 지원. "/cmux-orchestrate", "cmux로 팀 실행", "멀티 AI 팀", "gemini codex claude 병렬 실행" 등 cmux 환경에서 여러 AI를…

Idioma del texto original: coreano

2026-03-18

cmux

Administradores de redes y sistemas informáticos

cmux 터미널 멀티플렉서 제어 스킬. 워크스페이스/패널/서피스 관리, 명령 전송, 브라우저 자동화, 알림, 사이드바 메타데이터 제어. '/cmux', 'cmux', '워크스페이스 만들어', '패널 분할', '브라우저 열어', '알림 보내' 등 cmux 터미널 제어 요청이라면 반드시 이 스킬을 사용하세요.

Idioma del texto original: coreano

2026-03-18

architecture

Analistas de sistemas informáticos

Query and visualize the full project architecture. Use this during project onboarding, before code reviews, before adding new domains, or whenever you need to understand the tech stack. Responds to questions like "show me the overall structure", "list all…

Idioma del texto original: inglés

2026-03-17

changelog

Desarrolladores de softwareOtras ocupaciones informáticas

Query and analyze project change history and statistics. Use this before code reviews, when preparing for a deployment, when tracing change history for a specific file, or when analyzing activity by domain. Responds to questions like "recent changes", "change…

Idioma del texto original: inglés

2026-03-17

checkpoint

Analistas de garantía de calidad de software y probadores

Immediate code review at task/PR completion. Auto-detects Git Diff, extracts TASKS.md context, runs Hook gates, and optionally invokes AI multi-review. Use this after completing a task, before committing, or whenever someone says "checkpoint", "review my…

Idioma del texto original: inglés

2026-03-17

coverage

Analistas de garantía de calidad de software y probadores

Query and analyze test coverage. Use this to check coverage before modifying code, identify uncovered files before a PR, or track coverage trends over time. Triggers immediately on keywords like "coverage", "test pass", "uncovered areas", or "add tests".

Idioma del texto original: inglés

2026-03-17

deps

Analistas de sistemas informáticos

Visualize the project dependency graph and detect circular dependencies. Use this before refactoring, during architecture reviews, before adding new domains, or when evaluating module separation. Trigger immediately when cross-domain coupling seems high or…

Idioma del texto original: inglés

2026-03-17

governance-setup

Gerentes generales y de operaciones

Sets up Agent Teams governance (team-lead + architecture/qa/design leads) for large projects, or a Mini-PRD for small ones. Use this skill at project kickoff, whenever a team structure is needed, or on requests like "set up governance", "configure project…

Idioma del texto original: inglés

2026-03-17

impact

Analistas de sistemas informáticos

Analyzes the blast radius and risk level before modifying any file. Run this skill before touching production code, before refactoring, and before changing core logic. It is mandatory for files under payment, auth, billing, and security paths. Triggers on…

Idioma del texto original: inglés

2026-03-17

maintenance

Analistas de sistemas informáticos

Production system maintenance orchestrator. Automates change acceptance → impact analysis → safe modification → test reinforcement → change record in 5 ITIL-based stages. Use this skill for bug fixes, feature changes, config updates, incident response, and…

Idioma del texto original: inglés

2026-03-17

recover

Desarrolladores de software

Automatically detects and resumes incomplete work after CLI crashes, network drops, or agent errors. Use this skill whenever a session is interrupted, or on requests like "recover work", "interrupted task", "continue where you left off", or "what were you…

Idioma del texto original: inglés

2026-03-17

security-review

Analistas de seguridad de la información

OWASP Top 10 security vulnerability scanner. Detects secret exposure, injection flaws, auth/authz gaps, supply-chain risks, security misconfigurations, and logging failures via static analysis. Use this before every deployment, before every PR merge, and…

Idioma del texto original: inglés

2026-03-17

statusline

Desarrolladores de software

Displays TASKS.md progress in real time on Line 3 of the Claude Code status bar. Use this whenever you want a live view of project progress or need task tracking at a glance. Guides "show progress", "set up statusline", or "task status" requests. Triggered by…

Idioma del texto original: inglés

2026-03-17

tasks-init

Desarrolladores de software

Interactively scaffolds a TASKS.md file from scratch. Use this at project start, whenever TASKS.md is missing, or whenever task structure is needed. Invoke immediately on "create tasks", "generate TASKS.md", "start project", or "organize to-dos" requests.…

Idioma del texto original: inglés

2026-03-17

tasks-migrate

Secretarios y asistentes administrativos (excepto legal, médico y ejecutivo)

Consolidates legacy task files (docs/planning/06-tasks.md, etc.) into the root TASKS.md. Use this whenever task files are scattered across multiple locations. Invoke immediately on "migrate tasks", "move 06-tasks to TASKS", or "consolidate tasks" requests.

Idioma del texto original: inglés

2026-03-17

whitebox

Analistas de sistemas informáticos

File-based control plane that observes, explains, and controls the AI coding process. /whitebox is the sole product boundary — launch|status|explain|health|approvals expose run start, current state, intervention triggers, linked DEC evidence, approval…

Idioma del texto original: inglés

2026-03-17

Mostrando 28 de 28 skills recopiladas.