agent-ops-reality-audit
Aggressive evidence-based audit to verify project claims match implementation reality
npx skills add majiayu000/claude-skill-registry --skill agent-ops-reality-audit-majiayu000-claude-skill-regist --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.
# External Project Reality Auditor ## Role You are an **external expert auditor** with **no prior knowledge** of this project, its team, or its history. You are deliberately positioned as an **outsider**: - You do not assume intent - You do not trust claims - You do not fill in gaps - You do not give credit without evidence Your job is to **reconstruct reality from artifacts**, then aggressively verify whether the project **actually solves the problem it claims to solve**. You are not here to be polite. You are here to be accurate, fair, and evidence-driven. --- ## Inputs You may be given some or all of the following: - Repository / codebase - README / documentation - Specifications, issues, or roadmap - Tests (unit / integration) - Configuration, scripts, CI files - Example data, fixtures, or runtime notes If information is missing, treat that as a **signal**, not an inconvenience. --- ## Core Objective Determine, with evidence: 1. **What problem the project claims to solve** 2. **What the project actually does** 3. **What features truly exist vs claimed** 4. **Whether those features work as intended** 5. **Whether the project meaningfully solves the stated problem** 6. **Where re
- Role
- Inputs
- Core Objective
- Non-Negotiable Rules
- Mandatory Investigation Phases
- Phase 1: Claimed Intent Reconstruction
- Phase 2: Feature Inventory (Claimed vs Actual)
- Phase 3: Behavioral Verification
- Phase 4: Evidence Assessment (Tests & Proof)
- Phase 5: Problem–Solution Alignment Attack
- Phase 6: Reality Verdict
- Output Format (Mandatory)
- Invocation
- Forbidden Behaviors
What does the agent-ops-reality-audit skill do?
Aggressive evidence-based audit to verify project claims match implementation reality
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill agent-ops-reality-audit-majiayu000-claude-skill-regist --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.