一键导入
automatic-documentation
Principles for writing READMEs, API docs, ADRs, code comments, and changelogs. Use when creating or improving any technical documentation.
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
Principles for writing READMEs, API docs, ADRs, code comments, and changelogs. Use when creating or improving any technical documentation.
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
How to conduct and receive effective code reviews. Use when reviewing a PR, requesting review, or improving review quality.
Systematic process for diagnosing and resolving defects. Use when debugging failures, investigating errors, or reproducing issues.
How to use Automatic's feature tracking system — creating, progressing, and updating per-project work items via the Automatic MCP service. Activate when working on a project managed by Automatic that has feature tracking enabled.
Data-driven approach to identifying and resolving performance bottlenecks. Use when investigating slow queries, high latency, or memory growth.
Techniques for improving code structure without changing behaviour. Use when cleaning up code, reducing complexity, or addressing technical debt.
Security review checklist and threat mindset for any codebase. Use when reviewing code for vulnerabilities, implementing auth, or handling user input.
| name | automatic-documentation |
| description | Principles for writing READMEs, API docs, ADRs, code comments, and changelogs. Use when creating or improving any technical documentation. |
| authors | ["Automatic"] |
Documentation is a product. It requires the same deliberateness as code. Outdated, incomplete, or misleading documentation is worse than none — it wastes time and creates false confidence.
Write for the reader, not the writer. The author already knows how the system works. Documentation exists to transfer that understanding to someone who does not. Every sentence should serve that goal.
Document decisions, not just descriptions. Code describes what the system does. Documentation should explain why it does it that way. The most valuable documentation captures constraints, trade-offs, and rejected alternatives.
Treat documentation as a deliverable. A feature is not complete until it is documented. Documentation that is written later rarely gets written.
The entry point for any project. Must answer:
Keep it short. Link to deeper documentation. It should take under 5 minutes to read.
Document every public interface: functions, REST endpoints, event schemas.
For each item, include:
Record significant technical decisions as short, dated documents:
# ADR-042: Use PostgreSQL for primary data store
**Status**: Accepted
**Date**: 2025-03-02
## Context
We needed a relational database that supports ...
## Decision
We will use PostgreSQL 16 because ...
## Consequences
- We gain: JSONB support, strong ACID guarantees, mature tooling
- We accept: operational complexity vs. a managed service
- We reject: MySQL (weaker JSON support), SQLite (no concurrent writes)
ADRs are permanent. Even superseded decisions should be marked "Superseded" and kept — the reasoning matters.
Comment why, not what. The code says what is happening; comments explain why it happens that way.
// Good: "Skip validation here — this path is only reachable from the
// internal job queue, which has already validated the payload."
// Bad: "Skip validation"
// Bad: "Call the validate function" (the next line says that)
Comment anything surprising, non-obvious, or that required a decision that is not evident from the code itself.
Record what changed for users, not for developers.
Use plain English. Avoid jargon where a simpler word exists. If jargon is necessary, define it on first use.
Short sentences. Break long sentences into two. If a sentence requires re-reading, rewrite it.
Active voice. "The server validates the token" not "The token is validated by the server."
Present tense. "Returns the user object" not "Will return the user object."
Examples are mandatory. Abstract descriptions without examples make readers do extra work. Show, then tell.