Agent skill · AI & Agents

uncertainty-detector

Detects when Claude is uncertain but presenting answers confidently. Teaches Claude to recognize and communicate uncertainty clearly instead of masking it with confident language.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill uncertainty-detector --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 3 KB
Bundled scripts: none
Path: skills/ai-llm/uncertainty-detector/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Uncertainty Detector Catch yourself when you're guessing but sounding certain. ## The problem AI tends to present uncertain answers with confident language. "The function returns null" sounds certain even when you haven't checked. This is how hallucinations become accepted as fact. ## Uncertainty signals to watch for ### In your own thinking When you notice yourself: - Answering without having read the file -> STOP, read it first - Using training data instead of tool results -> STOP, search the codebase - Filling in gaps with "reasonable assumptions" -> STOP, verify or flag - Choosing between multiple possible answers -> STATE the options - Extrapolating from one file to another -> VERIFY the other file ### In your language Replace confident-uncertain phrases: | Don't say (hides uncertainty) | Say instead (honest) | |-------------------------------|---------------------| | "The function returns X" | "Let me check what the function returns" | | "This should work" | "Based on X, this should work. Let me verify" | | "The issue is probably X" | "One possible cause is X. Let me check" | | "You need to update X" | "Looking at the code, X might need updating. Let me confirm" | | "This i

What's inside
Steps it walks through
  1. The problem
  2. Uncertainty signals to watch for
  3. In your own thinking
  4. In your language
  5. In your process
  6. How to handle uncertainty
  7. Option 1: Verify first, then answer
  8. Option 2: Answer with caveats
  9. Option 3: State what you know and don't know
  10. Option 4: Admit you don't know
  11. The golden rule
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the uncertainty-detector skill do?

Detects when Claude is uncertain but presenting answers confidently. Teaches Claude to recognize and communicate uncertainty clearly instead of masking it with confident language.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill uncertainty-detector --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.

Keep going