Agent SkillsPaca-AI/paca › paca-doc

paca-doc

GitHub

用于在Paca Docs中撰写或更新技术文档(如指南、参考手册、架构设计、BDD场景等)。支持从任务上下文加载信息,自动识别文档类型并生成Markdown内容,最终保存至Paca平台。

skills/paca-doc/SKILL.md Paca-AI/paca

Trigger Scenarios

用户要求为已完成的功能编写文档 创建指南、运行手册或架构规范 更新现有文档或创建BDD场景

Install

npx skills add Paca-AI/paca --skill paca-doc -g -y
More Options

Use without installing

npx skills use Paca-AI/paca@paca-doc

指定 Agent (Claude Code)

npx skills add Paca-AI/paca --skill paca-doc -a claude-code -g -y

安装 repo 全部 skill

npx skills add Paca-AI/paca --all -g -y

预览 repo 内 skill

npx skills add Paca-AI/paca --list

SKILL.md

Frontmatter
{
    "name": "paca-doc",
    "description": "Write or update documentation for a feature, task, or topic in Paca Docs. Use when asked to document a completed feature, write a guide or runbook, update existing docs, create a spec or architecture document, or produce BDD scenarios. Documentation is saved in Paca — never created as local files.",
    "compatibility": "Requires Paca MCP server. Run \/paca-setup if Paca tools are not available."
}

You are writing or updating documentation in Paca Docs. Documentation lives in Paca — never create local files for docs.

If no task or topic is specified, call list_tasks for recently completed tasks that have no linked document, and ask the user which feature to document.


Step 1 — Load project context

  1. Resolve any reference from the user's message:
    • #42, ABC-42get_task_by_number to read the feature being documented
    • Doc title or path → list_docsread_doc to load the existing doc
    • Free-text topic → list_docs first to verify no duplicate already exists; if a similar doc is found, offer to update it instead of creating a new one
  2. Call list_docs and read related docs — architecture, existing guides, BDD scenarios, API references. Matching the existing tone, structure, and terminology matters more than any individual stylistic choice.
  3. If documenting a task, call get_task + list_task_activities to read the implementation details and any design decisions recorded in comments — these are often the most valuable content to capture.

Step 2 — Identify doc type and draft outline

Based on context, identify the type:

  • Guide / tutorial — step-by-step, outcome-oriented, written for someone doing it for the first time
  • Reference — exhaustive API, config, or CLI reference
  • Architecture / design doc — decisions, tradeoffs, diagrams (as Markdown)
  • BDD / acceptance spec — Gherkin-style scenarios
  • Runbook — operational steps for a known procedure

If the type is obvious from the task or request, proceed directly. Only ask the user to confirm the outline when the type is genuinely unclear or the scope is large.

Step 3 — Write the documentation

Write complete, clear Markdown:

  • Active voice and present tense
  • Code examples and command snippets where they aid understanding
  • Link to related Paca docs by title or task number
  • No "last updated" timestamps, no "Created by Claude" lines — Paca tracks history
  • No placeholder sections ("TBD", "coming soon") — write real content or omit the section

Step 4 — Save to Paca

  • New document: call write_doc with a full path (e.g. 'Architecture/API Design' — the last segment is the title, preceding segments are folders) and the Markdown content. Missing folders are created automatically.
  • Existing document: call write_doc with the same path. Integrate new content with the existing structure rather than appending everything at the end.
  • If the doc is tied to a task, call add_task_comment on that task linking to the doc (e.g. "Documentation written: [link]").

Report back: the document's title and the path it was saved at.


If Paca MCP is not connected

Paca MCP tools are not available. Run /paca-setup to configure the connection.


Tool reference

Documents: write_doc · read_doc · list_docs · move_doc
Tasks: get_task · get_task_by_number · list_task_activities
Comments: add_task_comment · add_doc_comment · list_doc_activities
Projects: list_projects

Version History

  • acf4909 Current 2026-07-19 18:24

    重构了Agent处理逻辑,将文档相关工具调用从list_documents/get_document统一更新为list_docs/read_doc,以适配新的MCP接口标准。

  • 1a37f10 2026-07-05 14:57

Same Skill Collection

services/ai-agent/src/skills/paca-breakdown/SKILL.md
services/ai-agent/src/skills/paca-clarify/SKILL.md
services/ai-agent/src/skills/paca-do/SKILL.md
services/ai-agent/src/skills/paca-doc/SKILL.md
services/ai-agent/src/skills/paca-epic/SKILL.md
services/ai-agent/src/skills/paca-estimate/SKILL.md
services/ai-agent/src/skills/paca-prioritize/SKILL.md
services/ai-agent/src/skills/paca-sprint/SKILL.md
services/ai-agent/src/skills/paca-test/SKILL.md
services/ai-agent/src/skills/paca-workflow/SKILL.md
skills/paca-breakdown/SKILL.md
skills/paca-clarify/SKILL.md
skills/paca-do/SKILL.md
skills/paca-epic/SKILL.md
skills/paca-estimate/SKILL.md
skills/paca-prioritize/SKILL.md
skills/paca-setup/SKILL.md
skills/paca-sprint/SKILL.md
skills/paca-test/SKILL.md
skills/paca-workflow/SKILL.md
skills/paca/SKILL.md

Metadata

Files
0
Version
acf4909
Hash
ea70cbab
Indexed
2026-07-05 14:57

ホーム - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-22 02:31
浙ICP备14020137号-1 $お客様$