跳到正文
cccskills
免费在 GitHub 公开

sdd-map

Produce a deterministic, read-only evidence map of the repository for SDD Composy (languages, manifests, commands, modules, boundaries, staleness) and publish the context bundle only on request. Use before a PRD or TechSpec, or when the map is stale — 'mapear o repositório', 'atualizar o contexto do código', 'what does this codebase look like for SDD'. Do NOT use for architecture decisions, code review, or repository exploration without an SDD workspace.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(2)

  • SKILL.md3.2 KB
  • agents/openai.yaml202 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

SDD Map

Create or inspect the SDD Composy codebase map. The bundled scripts/sdd_map.py helper owns traversal, secret exclusion, deterministic serialization, and atomic publication; this skill owns scope, approval, interpretation, and downstream routing.

Language: before writing human-facing prose, run scripts/sdd_language.py <repo-root> and use the persisted language; on not_initialized, return it with next_action: run_init. Localization rules: references/language.md.

Inputs

  • Repository root: the current repository unless the user supplies another real directory.
  • Optional output directory: inside the repository, default .planning/sdd-composy/context.
  • Optional request to publish. A scan is observation-only; publishing is the only permitted write and is limited to the context bundle.

Do not execute commands discovered in manifests, and do not modify source files, governance files, task artifacts, or architectural plans.

Procedure

  1. Resolve and validate the repository root and output directory without changing files.

  2. Run the read-only scan and present its JSON result, preserving source_commit, mapped_commit, observation_only, confidence, observed languages, manifests, commands, modules, boundaries, domain evidence, and staleness. Commands in the result are evidence only; never run them.

    python3 "<plugin-root>/scripts/sdd_map.py" --repo-root <repository-root> [--output-dir <context-dir>]
    
  3. Only when the user explicitly requests publication, repeat with --write (and the exact --output-dir when supplied). Publication writes only codebase.json, project.md, stack.md, domain.md, and pitfalls.md under the context directory. Report those paths and the recorded source commit.

  4. Check staleness.stale. A stale prior map is not valid downstream evidence: report the previous and current commit and refresh before routing. A missing or unknown commit is an uncertainty to report, not permission to invent one.

  5. Route a fresh map to the next approved lifecycle stage: PRD first, then STORIES, TECHSPEC, and TASKS as applicable. Those stages interpret the evidence under their own human gates; a map never turns file observations into unapproved architecture.

Read when

  • references/mapping.md — publishing the bundle, or interpreting the output schema and staleness record.

Output

Return the helper JSON or a faithful summary, publication status, output paths, source commit, the observation_only field, staleness status, and the next lifecycle stage.

Safety: Do not commit, push, or publish. Do not read or expose .env, credentials, tokens, private keys, certificates, or fleet environment files. Full contract: references/safety.md.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Accessibility auditing and remediation skill for Vue 3 + Reka UI. Use when reviewing components, verifying WCAG 2.1 AA, fixing ARIA issues, or validating keyboard navigation in Reka UI components.

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

ai-infra

免费

Infraestrutura para IA — GPU, servidores MCP, gateway de LLM, pipeline de inferência, custo de token, cache semântico e observabilidade de modelo. Use quando o usuário disser "GPU", "MCP server", "LLM", "inferência", "modelo", "gateway de IA", "custo de token", "rate limit da API de IA", "self-host de modelo".

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

alt-text

免费

Escreve texto alternativo e descrição de imagem para peças de rede social. Use quando o usuário disser "alt text", "texto alternativo", "descrição da imagem", "acessibilidade da peça", "descrever para leitor de tela", ou automaticamente antes de qualquer publicação. Obrigatório em todas as peças — em carrossel, um por slide.

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

Organiza, compara e seleciona entre as variações geradas, e publica a grade de comparação como Artifact para aprovação do time. Use quando o usuário disser "qual dessas", "comparar as variações", "escolher a melhor", "mostrar as opções", "montar grade de aprovação", ou após qualquer lote de geração. Selecionar é trabalho, não detalhe.

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

Aumenta resolução e qualidade de imagem via Freepik/Magnific, ou orienta o processo manual quando não há chave. Use quando o usuário disser "upscale", "melhorar a resolução", "a imagem está pixelada", "Magnific", "Freepik", "aumentar a imagem", "imagem pequena demais". Gasta crédito — exige confirmação.

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

CI/CD e automação — GitHub Actions, Terraform, OpenTofu, Ansible, n8n. Use quando o usuário disser "pipeline", "CI/CD", "GitHub Actions", "workflow", "terraform", "ansible", "n8n", "automatizar", "deploy automático", "IaC".

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

查看 pwdev-solucoes 的全部技能

报告此技能的问题