documentation-style-docs
Use when creating or updating project documentation in the same architecture and writing style as FogStages.md: title + visual block, index, introduction, implementation plan, code locations table, TODO, and limitations/bugs. Trigger on requests like create docs, write documentation, add design document, feature spec, system write-up, or architecture note.
- License 许可
- CC0-1.0
- 最近更新
- 2026-09-07
- Stars
- ★ 4
- Forks
- 0
01 前言 Front Matter
- name
- documentation-style-docs
- description
- Use when creating or updating project documentation in the same architecture and writing style as FogStages.md: title + visual block, index, introduction, implementation plan, code locations table, TODO, and limitations/bugs. Trigger on requests like create docs, write documentation, add design document, feature spec, system write-up, or architecture note.
03 SKILL.md 正文
Documentation Style Docs
Create markdown documentation that mirrors the structure, tone, and readability patterns used in docs/Features/FogStages.md.
Use This Skill When
- The user asks to create new documentation.
- The user asks to rewrite or expand a feature/design doc.
- The user requests a technical write-up intended for contributors.
Output Contract
Produce a markdown file with the following sections and order unless the user asks for a different structure.
- H1 title with a concise, memorable phrase.
- Optional centered visual block (gif/image) using HTML if an asset exists.
- Horizontal rule.
- Index section with anchor links to major sections.
- Introduction section.
- Plan section describing behavior and design intent.
- Code Locations section as a table.
- TODO section.
- Limitations & Bugs section.
Style Rules
- Keep language practical and contributor-focused.
- Explain player-facing impact first, then implementation details.
- Prefer short paragraphs and compact bullet lists.
- Use tables for behavior matrices and file responsibilities.
- Use clear section headings and predictable ordering.
- Keep claims concrete and verifiable in code.
Architecture Pattern
Follow this architecture pattern by default.
- Introduction: problem statement, why current behavior is weak, and design goal.
- Plan: staged model or system model with an explicit legend/table.
- Code Locations: map each feature slice to concrete function names and file paths.
- TODO: leave explicit placeholders for future follow-up.
- Limitations & Bugs: document known constraints and invite issue reports.
Code Locations Table Format
Use this 3-column format when possible.
| Feature | Location | Description |
|---|---|---|
| Feature slice | FunctionName in path/to/file.c |
What this code is responsible for |
Authoring Workflow
- Identify the target mechanic/system and its player-facing goals.
- Locate the relevant implementation files and core entry-point functions.
- Build a behavior table for visibility states, stages, or modes.
- Draft sections in the standard order.
- Verify links and symbols match repository names exactly.
Quality Checklist
- Headings and index anchors are valid.
- File/function references exist in the repository.
- Behavior table has no ambiguous state transitions.
- TODO and limitations are present even if brief.
- Tone matches contributor documentation, not marketing copy.
Default Template
If the user does not provide a custom structure, start from:
.github/skills/documentation-style-docs/templates/DocumentationStyleTemplate.md
04 同仓库更多 Skills
implement-skill
Resolves a named FE7 skill to its file pack and edits only those paths. Use when the user wants to implement, enable, port, wire, fix, add, install, or debug a skill (Nullify, Provoke, Adept, etc.).
caveman
Ultra-compressed communication AND thinking. Always use extreme (ultra) caveman to minimize tokens in both reasoning and replies. Cuts output ~65% and thinking tokens by skipping recap, option-lists, and filler thought. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", "extreme caveman", or invokes /caveman. Also auto-triggers when token efficiency is requested.
stay-within-limits
Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.
quick-recap
Use when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.
implement-skill
Resolves a named FE7 skill to its file pack and edits only those paths. Use when the user wants to implement, enable, port, wire, fix, add, install, or debug a skill (Nullify, Provoke, Adept, etc.).
efficient-frontier
Apply the same orchestration as `/efficient-fable` to any high-cost frontier model: delegate research, coding, and testing to cheaper subagents while keeping planning, synthesis, and final review with the expensive model.