跳到正文
cccskills
免费在 GitHub 公开

citation-enforcer

Forces every code-related claim to include file:line citations. No citation means the claim must be verified or removed. Use when building documentation, writing code reviews, or any output that others will rely on.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md2.1 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Citation Enforcer

Every code claim needs a citation. file:line or it didn't happen.

The rule

When you mention any of these, include the file path and line number:

  • A function name -> "validateToken() at src/auth.ts:42"
  • A variable -> "the MAX_RETRIES constant at src/config.ts:15"
  • A class -> "the UserService class at src/services/user.ts:1"
  • An import -> "imported from @auth/core at src/auth.ts:3"
  • A config value -> "timeout set to 30000 at config/default.json:12"
  • An error message -> "the error 'Invalid token' thrown at src/auth.ts:67"

Citation format

Standard: file:line Example: src/auth.ts:42

With range: file:line-line Example: src/auth.ts:42-58

With context: description at file:line Example: "the validateToken function at src/auth.ts:42"

Self-check

Before sending a response, scan it for uncited claims:

  1. Find every mention of a function, file, class, or variable
  2. Does each one have a file:line citation?
  3. If not, either: a. Use Read/Grep to find the actual location and add it b. Remove the claim if you can't find it c. Clearly state "I haven't verified where this is located"

Examples

Bad: "The authentication middleware checks for valid tokens." Good: "The authentication middleware at src/middleware/auth.ts:15-30 checks for valid tokens by calling validateToken()."

Bad: "There's a bug in the error handling." Good: "The catch block at src/api/users.ts:87 swallows the error without logging it."

Bad: "The config file has the wrong timeout." Good: "The timeout at config/production.json:23 is set to 5000ms, which may be too low for this API call."

When citations aren't needed

  • General programming concepts ("REST APIs use HTTP methods")
  • Suggestions that aren't about existing code ("you could add a retry mechanism")
  • Questions to the user ("what error are you seeing?")
  • Tool output that already includes file references

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Complete methodology for preventing AI hallucinations. Use when accuracy is critical and you need Claude to verify before claiming, cite before asserting, and admit uncertainty instead of guessing.

中文简介正在准备中。当前显示原文说明。

a-ariff/ariff-claude-plugins142026年3月29日 更新

Transform rough ideas into solid designs through structured questioning

中文简介正在准备中。当前显示原文说明。

a-ariff/ariff-claude-plugins142026年3月29日 更新

Canvas API Connection Skill

中文简介正在准备中。当前显示原文说明。

a-ariff/ariff-claude-plugins142026年3月29日 更新

Assign confidence scores (0-100) to every claim in a response. Helps users understand which parts are verified facts and which are educated guesses. Use when the user needs to know how much to trust each part of the answer.

中文简介正在准备中。当前显示原文说明。

a-ariff/ariff-claude-plugins142026年3月29日 更新

Forces Claude to extract exact quotes from files before making claims about them. Prevents hallucinations by grounding every statement in actual text from the codebase. Use when working with large files or unfamiliar code.

中文简介正在准备中。当前显示原文说明。

a-ariff/ariff-claude-plugins142026年3月29日 更新

Verify every claim from multiple independent angles -- code, docs, tests, git history. Use when you need high confidence that something is correct before acting on it.

中文简介正在准备中。当前显示原文说明。

a-ariff/ariff-claude-plugins142026年3月29日 更新

查看 a-ariff 的全部技能

报告此技能的问题