一键导入
documentation
Activate when generating in-code comments or system documentation using the Diátaxis framework.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Activate when generating in-code comments or system documentation using the Diátaxis framework.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | documentation |
| version | 1.0.0 |
| description | Activate when generating in-code comments or system documentation using the Diátaxis framework. |
| triggers | ["docs","documentation","comments","tsdoc","phpdoc","diataxis","readme"] |
A protocol for generating in-code comments and system documentation. Uses the Diátaxis framework for external docs and enforces "explain why, not what" for inline comments.
/docs/ folderFollow the recursive principle: documentation must explain why, not what.
@throws for all identified exceptions in the call chain./docs/ Folder)When generating files for the project's /docs/ directory, strictly apply the Diátaxis Framework:
Before writing any documentation:
./docs/ folder for existing guides to avoid duplication and maintain a consistent voice../docs/ and source code are valid.Good inline comment (why):
// Retry up to 3 times because the payment gateway occasionally returns
// transient 503 errors during high-traffic windows.
const result = await retry(3, () => gateway.charge(amount));
Bad inline comment (what):
// Charge the amount using the gateway
const result = await gateway.charge(amount);
@throws for all exceptions in the call chain (PHP)typescript-standard (TSDoc conventions), php-standard (PHPDoc conventions), recursive-exploration (source tracing)Activate when an Engineering Manager needs to shape a rough initiative into a clear, scoped, outcome-oriented brief before execution.
Activate when reviewing branches, commits, or pull requests using the emoji-driven review protocol.
Activate when managing conversation history in long sessions, choosing compression strategies, or preserving critical information during context truncation.
Activate when designing agent systems, debugging unexpected agent behavior, or optimizing context usage and attention budgets.
Activate when hitting context limits, experiencing quality degradation in long sessions, or needing to extend effective context capacity.
Activate when testing agent systems, measuring output quality, or designing evaluation frameworks for AI-assisted workflows.