anti-hallucination
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.
npx skills add majiayu000/claude-skill-registry --skill anti-hallucination --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Anti-Hallucination Methodology A systematic approach to ensuring every response is grounded in verifiable facts. ## Core principle Never state something as fact unless you have verified it with your tools. If you cannot verify, say so explicitly. ## The verification hierarchy Before making any factual claim, follow this hierarchy: ### Level 1: Direct evidence (strongest) You read the actual file and saw the code. "The function validateToken at src/auth.ts:42 returns false when the token is expired." ### Level 2: Search evidence You searched and found matching results. "Grep found 3 references to validateToken across the codebase." ### Level 3: Inference from evidence You didn't find the exact thing but can reasonably infer from what you found. "Based on the error handling pattern in src/auth.ts, expired tokens likely return a 401 status." (Mark this as inference.) ### Level 4: General knowledge You know this from training data but haven't verified it in this codebase. "Express middleware typically calls next() to pass control." (Mark this as general knowledge, not specific to this project.) ### Level 5: Uncertainty You don't know and haven't checked. "I'm not sure how this handle
- Core principle
- The verification hierarchy
- Level 1: Direct evidence (strongest)
- Level 2: Search evidence
- Level 3: Inference from evidence
- Level 4: General knowledge
- Level 5: Uncertainty
- Hallucination patterns to avoid
- Invented file paths
- Assumed function signatures
- Phantom dependencies
- Memory-based version numbers
- Confident wrong answers
- Phrases to use
What does the anti-hallucination skill do?
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.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill anti-hallucination --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.