Skip to content
cccskills
FreePublished on GitHub

cross-checker

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.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md2.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Cross-Checker: Multi-Angle Verification

Never trust a single source. Verify from at least two independent angles before accepting a claim as fact.

The cross-checking method

For any claim, check it against multiple sources:

Source 1: The code itself

Read the actual file. What does the code do? This is the strongest evidence.

Source 2: Tests

What do the tests expect? Tests reveal intended behavior. If a test expects validateToken to return false for expired tokens, that's the designed behavior.

Source 3: Git history

What was the original intent? Git blame and commit messages reveal why code was written. "commit abc123: fix token expiration check to reject tokens older than 24h"

Source 4: Documentation

README, comments, JSDoc, API docs. Do they match the code? If docs say one thing and code does another, the code is truth but the discrepancy matters.

Source 5: Configuration

Config files, environment variables, feature flags. Runtime behavior may differ from what the code looks like.

Source 6: Dependencies

Package versions, API compatibility, deprecated features. A function might exist in the code but be broken due to a dependency update.

Minimum verification standard

SituationMinimum angles needed
Stating a fact to the user1 (read the code)
Recommending a code change2 (code + tests or git history)
Security-related claims3 (code + tests + docs/config)
Production deployment advice3 (code + config + git history)
"This is safe to delete"3 (code + grep for references + tests)

Cross-check workflow

  1. Make the initial claim based on what you know
  2. Identify which type of claim it is (fact, recommendation, security)
  3. Check the required number of angles
  4. If sources agree: proceed with confidence
  5. If sources disagree: flag the discrepancy, investigate further
  6. If sources are insufficient: say so, suggest how to get more evidence

Red flags that demand cross-checking

  • "This function is never called" (grep the entire codebase first)
  • "This file isn't used anymore" (check imports, configs, build scripts)
  • "This dependency can be removed" (check all import statements)
  • "This environment variable isn't needed" (check all config files and deploy scripts)
  • "This test is redundant" (check what specific edge case it covers)

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

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.

The English summary is being prepared. Showing the original description.

a-ariff/ariff-claude-plugins14Updated Mar 29, 2026

Transform rough ideas into solid designs through structured questioning

The English summary is being prepared. Showing the original description.

a-ariff/ariff-claude-plugins14Updated Mar 29, 2026

Canvas API Connection Skill

The English summary is being prepared. Showing the original description.

a-ariff/ariff-claude-plugins14Updated Mar 29, 2026

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.

The English summary is being prepared. Showing the original description.

a-ariff/ariff-claude-plugins14Updated Mar 29, 2026

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.

The English summary is being prepared. Showing the original description.

a-ariff/ariff-claude-plugins14Updated Mar 29, 2026

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.

The English summary is being prepared. Showing the original description.

a-ariff/ariff-claude-plugins14Updated Mar 29, 2026

See all skills by a-ariff

Report a problem with this skill