convez.ai
MCP ServerAutomaçãoIntermediário
softspark

AI Toolkit – Ambiente Multi-plataforma de IA para Codificação

softspark/ai-toolkit

107 skills, 44 agents, multi-IDE, segurança embarcada, setup em 60s

Ver no GitHub
Muito bomPluginScore · de 0 a 100

MCP server profissional com 107 skills e 44 agents pré-configurados para Claude, Cursor, Windsurf, Copilot e outras IDEs de IA. Oferece hooks de segurança, integração automática em 60 segundos e suporte multi-plataforma (Windows via WSL, macOS, Linux). Acelera desenvolvimento com commands prontos, automação de hooks e gerenciamento de plugins.

Instalação

$npx convez-ai softspark/ai-toolkit

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
180
Forks
21
Acompanhando
4
Saúde
100%
Último commit
há 1 dia
Versão
v6.2.0
Issues abertas
0
Contribuidores
3

Casos de uso

  • Acelerar desenvolvimento de código com skills e agents pré-treinados
  • Integrar IA em workflow de múltiplos editores (Claude Code, Cursor, Windsurf, Copilot)
  • Automatizar processos de build e deployment com hooks machine-enforced
  • Gerenciar personas e presets para diferentes contextos de desenvolvimento

Veredito

Toolkit robusto e bem-mantido para times que usam múltiplas IDEs de IA. Instalação trivial, ampla cobertura de plataformas e rigor em segurança (safety constitution). Recomendado para quem quer padronizar comportamento de agentes across tools.

README

A tradução para o português deste README ainda está na fila.

ai-toolkit

Professional-grade AI coding toolkit with multi-platform support. Machine-enforced safety, 107 skills, 44 agents, expanded lifecycle hooks, persona presets, experimental opt-in plugin packs, and benchmark tooling — works with Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Google Antigravity, Codex CLI, and opencode, ready in 60 seconds.

CI License: MIT Skills Agents Tests

What's New in v4.8.0

v4.8.0 migrates the deprecated Windsurf Cascade hooks onto the Devin CLI surface before Cascade sunsets on 2026-07-01.

  • Devin CLI hooks: new generate_devin_hooks.py emits .devin/hooks.v1.json in the Claude-compatible format Devin CLI uses — Claude-style events (PreToolUse/PostToolUse/UserPromptSubmit/Stop/SessionStart) with matchers on Devin tool names (read/edit/exec/mcp__*), reusing the existing toolkit hook scripts.
  • Cascade deprecation: .windsurf/hooks.json is Cascade-scoped and dies 2026-07-01 with no Devin fallback; both generators run during the transition, the Cascade one drops in the first release after the sunset.
  • Global hooks reach Devin for free: Devin CLI reads ~/.claude/settings.json hooks directly, so a global ai-toolkit install already covers Devin even without the project-local file.
  • No normalizer change needed: _hook-io.sh already parses Devin's flat hook_event_name/tool_name/tool_input payload.

See CHANGELOG.md for full history.


Table of Contents


Install

# Option A: install globally (once per machine)
npm install -g @softspark/ai-toolkit
ai-toolkit install

# Option B: try without installing (npx)
npx @softspark/ai-toolkit install

That's it. Claude Code picks up 107 skills, 44 agents, quality hooks, and the safety constitution automatically.

Windows: WSL is the recommended runtime. Native Windows works when Git Bash is available for hook scripts; dependency hints cover winget, Chocolatey, and Scoop. See Windows Support.

Update

npm install -g @softspark/ai-toolkit@latest && ai-toolkit update

Per-Project Setup

cd your-project/
ai-toolkit install --local                        # Claude Code only
ai-toolkit install --local --editors all          # + all editors
ai-toolkit install --local --editors cursor,aider # + specific editors
ai-toolkit update --local                         # auto-detects editors

Plugin Management

ai-toolkit plugin list                            # show available packs
ai-toolkit plugin install --editor all --all      # install all for Claude + Codex
ai-toolkit plugin status --editor all             # show what's installed

Install Profiles

ai-toolkit install --profile minimal    # agents + skills only
ai-toolkit install --profile standard   # full install (default)
ai-toolkit install --profile strict     # full + git hooks

Verify & Repair

ai-toolkit validate          # check integrity
ai-toolkit doctor --fix      # auto-repair

See CLI Reference for all commands and options.


Platform Support

PlatformConfig FilesHooksScope
Claude Code~/.claude/✅global
Cursor.cursor/rules/*.mdc + .cursor/mcp.json + .cursor/skills/*✅project (~/.cursor/mcp.json for MCP only)
Windsurf (Devin Desktop)~/.codeium/.../global_rules.md + ~/.codeium/windsurf/skills/* + .devin/rules/*.md + .windsurf/rules/*.md (legacy)✅global + project
Gemini CLI~/.gemini/GEMINI.md✅global
GitHub Copilot.github/copilot-instructions.md—project
Cline~/Documents/Cline/Rules/*.md + ~/.cline/skills/* + .clinerules/*.md—global + project
Roo Code~/.roo/rules/*.md + .roomodes + .roo/rules/*.md—global rules + project
Aider~/.aider.conf.yml + .aider.conf.yml + CONVENTIONS.md—global + project
Augment~/.augment/rules/*.md + .augment/rules/ai-toolkit-*.md✅global + project
Google Antigravity.agents/rules/*.md + .agents/workflows/*.md + skill pointer in .agent/skills/* (IDE) and .agents/skills/* (CLI)—project
Codex CLIAGENTS.md (coding rules inlined) + .agents/skills/* + .codex/hooks.json✅project + global plugin
opencodeAGENTS.md + .opencode/{agents,commands,plugins}/* + opencode.json✅project + global (~/.config/opencode/)

Claude Code is always installed (primary platform). Other editors on demand with --editors. Every platform receives the agent/skill catalog, guidelines, and registered custom rules as text. The Hooks column marks platforms that also get lifecycle hook enforcement — the machine-enforced constitution (guard-destructive, quality gates, search-first discipline). Platforms marked — receive those rules as guidance only, without blocking hooks.


What You Get

ComponentCountDescription
skills/ (task)32Slash commands: /commit, /build, /deploy, /test, /mcp-builder, ...
skills/ (hybrid)30Slash commands with agent knowledge base
skills/ (knowledge)45Domain knowledge auto-loaded by agents (includes 13 <lang>-rules skills)
agents/44Specialized agents across 10 categories
hooks/29 entries / 14 eventsQuality gates, path safety, prompt governance, loop guard, session lifecycle
plugins/11 packsOpt-in domain bundles (security, research, frontend, enterprise, 6 language packs)
constitution.md6 articlesMachine-enforced safety rules
rules/auto-injectedLanguage-specific and custom rules injected into your configs
kb/reference docsArchitecture, procedures, and best practices

Architecture

ai-toolkit/
├── app/
│   ├── agents/          # 44 agent definitions
│   ├── skills/          # 107 skills (task / hybrid / knowledge)
│   ├── rules/           # Auto-injected into your CLAUDE.md
│   ├── hooks/           # Hook scripts (29 entries, 14 lifecycle events)
│   ├── plugins/         # 11 experimental plugin packs (opt-in)
│   ├── output-styles/   # System prompt output style overrides
│   ├── constitution.md  # 6 immutable safety articles
│   └── ARCHITECTURE.md  # Full system design
├── kb/                  # Reference docs, procedures, plans
├── scripts/             # Validation, install, evaluation scripts
├── tests/               # Bats test suite (1196 tests)
└── CHANGELOG.md

Distribution: Symlink-based for agents/skills, copy-based for hooks. Run ai-toolkit update after npm install — all projects pick up changes instantly. See Distribution Model.


Key Features

Machine-enforced constitution — 6-article safety constitution enforced via PreToolUse hooks that actually block rm -rf, DROP TABLE, and irreversible operations. Not just documentation.

29 lifecycle hooks — Executable scripts across 14 events (SessionStart → SessionEnd, plus InstructionsLoaded + ConfigChange). Guards, governance, quality gates, session persistence, MCP health checks, revert protection, test-cohesion enforcement, loop guard, search-first discipline. See Hooks Catalog.

Security scanning — /skill-audit for code-level risks, /cve-scan for dependency CVEs. Both CI-ready with exit codes.

Iron Law enforcement — /tdd, debugging-tactics, and verification-before-completion enforce non-negotiable gates with anti-rationalization tables. 15 skills total include rationalization resistance.

Multi-language quality gates — Stop hook runs lint + type checks across Python, TypeScript, PHP, Dart, Go after every response.

Agent verification checklists — 10 agents include exit criteria that must be met before presenting results.

Two-stage review — /subagent-development runs Implementer → Spec Review → Quality Review per task.

Persistent memory — memory-pack plugin: SQLite + FTS5 search across past sessions.

Local product telemetry — ai-toolkit stats --summary reports total invocations, skill coverage, unused catalog skills, recent activity, and top skills from local usage data.

Persona presets — 4 roles (backend-lead, frontend-lead, devops-eng, junior-dev) adjust style and priorities.

Config inheritance — Enterprise extends system with constitution immutability and enforcement constraints. See Enterprise Config Guide.

70 language rules — 13 languages + common, 5 categories each. Auto-detected or explicit --lang. See Language Rules.

26 MCP templates — Ready-to-use configs for GitHub, PostgreSQL, Slack, Jira, Sentry, and more. See MCP Templates.

See Unique Features for detailed descriptions of all differentiators.


Key Slash Commands

CommandPurposeEffort
/workflow <type>Pre-defined multi-agent workflow (15 types)max
/orchestrateCustom multi-agent coordination (3–6 agents)max
/swarmParallel Agent Teams: map-reduce, consensus, relaymax
/planImplementation plan with task breakdownhigh
/reviewCode review: quality, security, performancehigh
/debugSystematic debugging with diagnosticsmedium
/refactorSafe refactoring with pattern analysishigh
/tddTest-driven development with red-green-refactorhigh
/commitStructured commit with lintingmedium
/prPull request with generated checklistmedium
/docsGenerate README, API docs, architecture noteshigh
/exploreInteractive codebase visualizationmedium
/write-a-prdCreate PRD through interactive interviewhigh
/prd-to-planConvert PRD into vertical-slice implementation planhigh
/design-an-interfaceGenerate 3+ radically different interface designshigh
/grill-meStress-test a plan through Socratic questioningmedium
/triage-issueTriage bug with deep investigation and TDD fix planhigh
/architecture-auditDiscover shallow modules, propose refactorshigh
/council4-perspective decision evaluationhigh
/cve-scanScan dependencies for known CVEsmedium
/skill-auditScan skills/agents for security risksmedium
/repeatAutonomous loop with safety controlsmedium
/personaSwitch engineering persona at runtimelow

/workflow Types

feature-development    backend-feature       frontend-feature
api-design             database-evolution    test-coverage
security-audit         codebase-onboarding   spike
debugging              incident-response     performance-optimization
infrastructure-change  application-deploy    proactive-troubleshooting

Multi-Agent Skill Selection

Need multi-agent coordination?
├── Know your domains? → /orchestrate (ad-hoc, 3-6 agents)
├── Have a known pattern? → /workflow <type> (15 templates)
├── Need consensus/map-reduce? → /swarm <mode>
├── Want Agent Teams API? → /teams (experimental)
└── Executing a plan? → /subagent-development

Getting Started

  1. Customize CLAUDE.md — add your project's tech stack, commands, and conventions at the top (above toolkit markers).

  2. Start using skills:

    /onboard     # guided setup interview
    /explore     # understand your codebase
    /plan        # plan a feature
    
  3. Verify your install:

    ai-toolkit validate
    

Documentation

TopicLink
CLI Referencekb/reference/cli-reference.md
Unique Featureskb/reference/unique-features.md
Architecture Overviewkb/reference/architecture-overview.md
Hooks Catalogkb/reference/hooks-catalog.md
Language Ruleskb/reference/language-rules.md
MCP Templateskb/reference/mcp-templates.md
Extension APIkb/reference/extension-api.md
Manifest Installkb/reference/manifest-install.md
Plugin Packskb/reference/plugin-pack-conventions.md
Enterprise Configkb/reference/enterprise-config-guide.md
Distribution Modelkb/reference/distribution-model.md
Ecosystem Comparisonkb/reference/comparison.md
Codex CLI Compatibilitykb/reference/codex-cli-compatibility.md
opencode Compatibilitykb/reference/opencode-compatibility.md
Maintenance SOPkb/procedures/maintenance-sop.md

Contributing

See CONTRIBUTING.md.

Security

See SECURITY.md for responsible disclosure policy.

License

MIT — see LICENSE.

Changelog

See CHANGELOG.md.


Extracted from production use at SoftSpark. Built to be the toolkit we wished existed.

Ver o original no GitHub

Bom para

Relacionados