aif-grounded
Reliability gate for answers. Forces evidence-based reasoning, explicit uncertainty, and “insufficient information” instead of guesses. Use when user says “be 100% sure”, “no hallucinations”, “only if verified”, “grounded answer”, or when stakes are high.
npx skills add majiayu000/claude-skill-registry --skill aif-grounded-batformat-sancrm-docs --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.
# Grounded - Reliability Gate (No Guessing) This skill minimizes random / fabricated answers by enforcing a strict rule: **Only provide the final answer if confidence is 100/100 based on evidence available.** If confidence is not 100, **do not guess** and **do not implement**. Output a short “what’s missing” checklist that explains what would be required to reach 100. ## When to use Use when: - The user requests maximum reliability (“only if you’re sure”, “no assumptions”). - The request includes changeable facts (versions, “latest”, policies, prices, schedules). - The request is security/finance/legal/medical adjacent (high stakes). - You’re resuming after context loss and need to avoid accidental assumptions. ## Workflow ### Step 1: Classify the request Classify into one of: 1. **Repo-grounded** — can be answered purely from the local codebase and command outputs. 2. **Doc-grounded** — requires authoritative docs/specs/logs provided by the user or accessible tooling. 3. **External-facts** — depends on changeable facts outside the repo (must be verified, otherwise refuse). ### Step 2: Define evidence and unknowns Before answering, list: - **Evidence sources** you will use (files,
- When to use
- Workflow
- Step 1: Classify the request
- Step 2: Define evidence and unknowns
- Step 3: Mandatory verification for changeable facts
- Step 4: Confidence gate
- Step 5: Output format (strict)
- Implementation guardrail
What does the aif-grounded skill do?
Reliability gate for answers. Forces evidence-based reasoning, explicit uncertainty, and “insufficient information” instead of guesses. Use when user says “be 100% sure”, “no hallucinations”, “only if verified”, “grounded answer”, or when stakes are high.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill aif-grounded-batformat-sancrm-docs --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.