Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Spec Kit

ASecurity

Use when doing spec-driven development with Spec Kit (Astral/GitHub) — CLI workflow: `constitution` → `specify` → `plan` → `tasks` → `implement` with automatic git branching per spec, project constitution memory, and UV package manager. Triggers on "spec kit", "spec-driven", "specify plan tasks implement", "constitution spec", "branch por spec", "UV astral". Não use para planejamento genérico (isso é `blueprint`/`plan`/`orch-*`); Spec Kit é tool concreta com CLI própria e fluxo opinionado.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentspythongogit

Works with

claude codecursorcli

Security Analysis

A92/100
mediumInstalls packages at runtime which could introduce malicious dependencies

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill spec-kit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Spec Kit?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Spec Kit
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-spec-kit/badge)](https://www.skillsdirectory.com/skills/majinmagros-spec-kit)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: spec-kit
description: Use when doing spec-driven development with Spec Kit (Astral/GitHub) — CLI workflow: `constitution` → `specify` → `plan` → `tasks` → `implement` with automatic git branching per spec, project constitution memory, and UV package manager. Triggers on "spec kit", "spec-driven", "specify plan tasks implement", "constitution spec", "branch por spec", "UV astral". Não use para planejamento genérico (isso é `blueprint`/`plan`/`orch-*`); Spec Kit é tool concreta com CLI própria e fluxo opinionado.
metadata:
  origin: ecc
  module: agentic-patterns
  cost: medium
  stability: stable
  defaultInstall: false
---

# Skill: spec-kit — Spec-Driven Development com Spec Kit (Astral/GitHub)

**Spec Kit** é uma tool CLI open-source (Astral/GitHub) que implementa *Spec-Driven Development* (SDD): você escreve a especificação primeiro, a tool gera plano, tasks e implementação, com isolamento por branch git e constituição global do projeto.

## Quando usar

- Você quer seguir **spec-driven development** rigoroso: spec → plan → tasks → implement.
- Precisa de **isolamento automático por feature** (git branch criada automaticamente por spec).
- Quer uma **constituição global** do projeto (`.specify/memory/constitution.md`) que guia todas as specs.
- Usa **UV** (Astral) como gerenciador de pacotes Python (padrão do Spec Kit).
- Integra com **Claude Code, Copilot, Gemini, Cursor** via `--integration`.

Não use para:
- Planejamento genérico ECC → `blueprint`, `plan`, `orch-add-feature`, `orch-build-mvp`.
- Graph engineering paralelo → `engenharia-de-grafos`, `graph-engineering`.
- Apenas criar tasks → `orch-pipeline`/`orch-*`.

## Pipeline oficial (comandos CLI)

| Etapa | Comando | O que faz | Artefatos gerados |
|---|---|---|---|
| **0. Init** | `specify init <projeto> --integration <copilot\|claude\|gemini>` | Cria estrutura `.specify/`, templates, integração com agente | `.specify/`, `scripts/`, configs |
| **1. Constitution** | `/speckit.constitution "princípios do projeto"` | Define/atualiza constituição global em `.specify/memory/constitution.md` | `constitution.md` (memória base) |
| **2. Specify** | `/speckit.specify "descrição da feature"` | Cria branch `NNN-nome-feature`, gera `specs/NNN-nome/spec.md` com requisitos estruturados | `spec.md`, branch git |
| **3. Plan** | `/speckit.plan "detalhes técnicos: stack, arquitetura"` | Gera plano de implementação a partir da spec | `plan.md`, `data-model.md`, `contracts/`, `research.md`, `quickstart.md` |
| **4. Tasks** | `/speckit.tasks` | Deriva tasks executáveis do plano, marca paralelas | `tasks.md` |
| **5. Implement** | `/speckit.implement` ou `/speckit.implement "fase 1 apenas"` | Executa tasks em ordem de dependência, suporta execução por fases | Código implementado |

## Conceitos-chave

### Constitution (`.specify/memory/constitution.md`)
Arquivo **global** do projeto que define princípios, padrões de arquitetura, convenções de código, stack preferida. Toda spec herda essa constituição. Exemplo:
```
This project follows a "Library-First" approach. All features must be implemented as standalone libraries first. We use TDD strictly. We prefer functional programming patterns.
```

### Branch automática por spec
Cada `/speckit.specify` cria uma branch `NNN-nome-feature` (ex.: `003-chat-system`). Você **não trabalha na main** — isola a feature, implementa, abre PR, faz merge. Se der errado, deleta a branch.

### Memory/Constitution como contexto base
O agente lê a constituição + spec + plan + tasks como contexto. Isso evita "contexto vazio" no início de cada task.

### UV (Astral) — gerenciador padrão
`uv` substitui pip/poetry/pipx: `uv add`, `uv run`, `uv sync`, `uv pip install`. 10-100x mais rápido, lockfile universal (`uv.lock`). Spec Kit assume UV no ambiente.

## Integração com agentes

| Agente | Flag `--integration` | Como invoca comandos |
|---|---|---|
| **Claude Code** | `claude` | Slash commands `/speckit.*` no chat |
| **GitHub Copilot** | `copilot` | Slash commands no Copilot Chat |
| **Gemini CLI** | `gemini` | Via `@speckit` ou CLI direta |
| **Cursor** | `cursor` | Slash commands no Cursor Agent |

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →