菜单
Use when about to modify code in a file or function you haven't actually read yet — making a change in an unfamiliar or existing part of the codebase. Makes the agent read the surrounding code first so the edit matches existing patterns and doesn't break nearby logic.
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
Use when a request is ambiguous, underspecified, or could be read more than one way — before writing code based on a guess. Makes the agent surface the ambiguity and either ask or state the assumption it's making, instead of silently picking one interpretation and building the wrong thing.
Use when the user is learning and wants to understand the code, not just receive it — they're new to the language, framework, or to coding agents in general. Makes the agent briefly explain what each change does and why, in plain language, so the user learns from every edit instead of blindly accepting it.
Use at the start of any non-trivial coding task — before writing code for a new feature, a fix, or a change that spans more than a couple of lines or files. Makes the agent state a short plan and confirm direction before implementing, so you catch a wrong approach in 3 sentences instead of 300 lines.
Use when editing existing code — making a fix, adding a feature, or changing behavior in a file that already has working code. Enforces minimal, scoped diffs so the agent changes only what the task requires and never refactors, reformats, or "improves" untouched code.
Use after making a code change and before telling the user it is finished or working. Forces the agent to actually check the change — run the test, build, or a concrete trace of the logic — and report real results, instead of optimistically claiming success it hasn't confirmed.
Use when restructuring existing code without intending to change its behavior — extracting functions, renaming across files, splitting modules, or swapping an implementation. Makes the agent pin current behavior with tests first, change in small verified steps, and prove behavior is unchanged, so a "cleanup" never silently breaks something.
| name | read-before-edit |
| description | Use when about to modify code in a file or function you haven't actually read yet — making a change in an unfamiliar or existing part of the codebase. Makes the agent read the surrounding code first so the edit matches existing patterns and doesn't break nearby logic. |
Before changing existing code, read enough of it to understand what you're touching. Editing blind is how agents break working software.
Read the function/section you're changing — and the code immediately around it. Understand what it does and what depends on it before you touch a line.
Find the existing patterns. How does this file name things, handle errors, structure logic? Match that, don't impose your own style.
Check who calls it. A quick look at where a function is used tells you what you might break. Changing a signature or return value without checking callers is a classic self-inflicted bug.
Reuse what's there. If the codebase already has a helper, a utility, or a pattern for what you need, use it instead of writing a parallel one. New code should look like it belongs.
Don't pattern-match on the name of a function and assume it does what you'd expect. Open it and confirm. The function called validateUser might also mutate state, log, or throw — assumptions about unread code are where bugs hide.
Most agent-introduced bugs aren't bad logic — they're good logic that didn't fit the existing code, broke an unseen caller, or duplicated something already there. Two minutes of reading prevents the kind of bug that takes an hour to trace.
