- name
SKILL.md
El archivo de la skill permanece en el repositorio del publicador.
Pega el comando copiado en una terminal. Instala este SKILL.md en ese agente.
npx skills add shinpr/ai-coding-project-boilerplate --skill documentation-criteria -a cursor -yPega el comando copiado en una terminal. Instala este SKILL.md en ese agente.
npx skills add shinpr/ai-coding-project-boilerplate --skill documentation-criteria -a claude-code -yPega el comando copiado en una terminal. Instala este SKILL.md en ese agente.
npx skills add shinpr/ai-coding-project-boilerplate --skill documentation-criteria -a codex -yPega el comando copiado en una terminal. Instala este SKILL.md en ese agente.
npx skills add shinpr/ai-coding-project-boilerplate --skill documentation-criteria -a grok -yEnvía el mensaje copiado en un chat de Grok Bot. El Bot obtiene este SKILL.md de GitHub y lo añade a las skills que comparten todos tus Bots.
Install this skill: https://github.com/shinpr/ai-coding-project-boilerplate/tree/HEAD/.claude/skills-en/documentation-criteriaDel publicador
This skill owns document routing: which durable decisions the change needs to record and where each document lives. Each template linked from Storage Locations owns the document's content and structural requirements.
Accepted records the currently selected means, not an obligation to retain it: when later evidence supports a smaller sufficient choice, update or supersede the ADR while the outcome, desired-future requirements, and non-goals remain true. Complete implementation design belongs in the Design DocAdd a UI Spec before the Design Doc for frontend/fullstack work when its decisions remain open. Complete any qualifying ADR batch before the Design Doc. A qualifying ADR raises the scale to Medium at minimum.
For a Large change, satisfy the PRD requirement by creating a new PRD, updating the relevant PRD, or creating a reverse PRD when no current product document exists. At any scale, update an existing PRD when the product scope changes.
Classify decision burden rather than repository layout. File count is supporting evidence only.
A cross-layer implementation can remain Medium when it serves one coherent outcome.
Apply the Choice filter, then the Durability filter, to each technical topic inside the implementation scope. Check accepted ADRs before creating another record.
Create one ADR for each topic that passes both filters and review the complete batch together. Group choices that must be selected or reconsidered together; separate independently revisitable decisions. Local implementation details and other cheaply reversible choices belong in the Design Doc.
Every placeholder substituted into a generated directory or file name must be a lowercase ASCII kebab-case slug. Convert non-ASCII source text to that form before constructing the path.
Work Plans are excluded by .gitignore.
Each template defines its document's content, status rules, required evidence, optional diagrams, and completion checks. Load only the template for the document being created or reviewed.
Determines which PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires and where each is stored. Use when deciding documentation scope or creating or reviewing a technical document.
---name: documentation-criteriadescription: Determines which PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires and where each is stored. Use…---# .claude/skills-en/documentation-criteria/SKILL.mdPreguntas frecuentes
Descarga .claude/skills-en/documentation-criteria/SKILL.md desde el publicador, o copia la ruta y abre el repositorio. PlugMCP lista la skill y no aloja el archivo.
El publicador lo mantiene en https://github.com/shinpr/ai-coding-project-boilerplate.
Claude, Cursor, Codex y Grok Build pueden leer un SKILL.md que añadas desde el repositorio del publicador. Grok Bot lo instala cuando envías en un chat el enlace a la carpeta de la skill en GitHub.