# best-practices
An Agent Skill that holds an AI coding agent's output to the standard of **current best practice** — the recommended, idiomatic way *now*, not merely an answer that runs — by teaching it when to distrust its own (stale, version-fuzzy) memory and verify against authoritative sources.
中文说明请见：[README.zh-CN.md](README.zh-CN.md)
## Why
Training knowledge has a cutoff and is fuzzy about versions. In fast-moving areas — frameworks, SDKs, toolchains, "best practices" — an agent will be **confidently wrong** and usually won't notice. But "search every time" is an anti-pattern too: it pollutes context, slows everything down, and pulls in low-quality content.
This skill is pure **judgment**, with zero new infrastructure. It teaches two things models get wrong:
- **Predicting your own blind spots** — version/time-sensitive facts, "idiomatic way" questions, code against external APIs.
- **Recovering after being corrected** — the moment the user corrects you, doubts you, or repeats a request is *ground truth* that your memory was wrong. Stop re-guessing from the same memory. Verify first.
It deliberately does **not** build a knowledge base or cache results — cached version-sensitive facts go stale and then get re-trusted with false authority. Verify when it matters, then move on.
## Installation
Install as an **Agent Skill** — tell any AI coding tool that supports agent skills (Claude Code, Codex, OpenCode, Cursor, Antigravity, etc.):
```text
Install the skill from liustack/best-practices
```
Or use the `skills` CLI directly:
```bash
npx skills add liustack/best-practices --skill best-practices
```
Or install manually by copying the skill into your agent's skills directory:
```bash
# Claude Code (personal, global)
cp -r skills/best-practices ~/.claude/skills/best-practices
```
## What it covers
- **When to distrust yourself** — internal signals (version-sensitive facts, fast-moving domains, "best practice" questions, code against external APIs) and external signals (user corrects/doubts/repeats — highest weight).
- **The doubling-down rule** — once corrected, stop answering from memory. Verify, then speak.
- **Triage before reacting** — being corrected tells you *something* is wrong, not *what*. Re-read context (cheap) before reaching for the web.
- **Guardrails** — don't over-verify stable fundamentals, locally confirmable facts, or things the user already specified.
- **Source hierarchy** — installed source / lockfile > official docs (MCP / `llms.txt`) > web search, always version-aligned.
## The skill
- [skills/best-practices/SKILL.md](skills/best-practices/SKILL.md)
## License
MIT