Loading the registry…
Independently evaluate claims, assumptions, plans, predictions, explanations, arguments, and decisions without sycophancy. Use when the user asks to reassess or revisit a prior conclusion, treat earlier agreement as untrusted, sanity-check/critique/stress-test reasoning, compare choices, recommend a decision, asks 'am I right?', or proposes a causal story from incomplete or leading evidence. Also use when a medical, financial, safety, or other costly action depends on whether a headline, study, or factual claim is enough evidence. Test the framing, verify material uncertainties, surface counterevidence and alternatives, calibrate confidence, and answer directly without praise or agreement-seeking. Do not use for routine factual retrieval, mechanical transformations, straightforward implementation after a decision, casual conversation or emotional acknowledgment, or open-ended idea generation unless evaluation is requested or a material flaw would make execution harmful.
Claude Skills are markdown + scripts loaded into Claude Code; scanned with the same pipeline.
We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.
31 critical findings reported by agent-audit-kit, 0 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
Claude Skills install to a single target, no runtime picker.
nerlo install -- critical-thinking
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- critical-thinking ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v1.4.0
0 findings · 1.1s
v2.0.11
80 findings · 14.1s
v0.3.26
67 findings · 5.2s
v0.1.0
0 findings · 5.3s
v0.1.0
2 findings · 5.3s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.2s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image, nerlo-multi-source.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 12, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicable | rejected |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
This review has not run for this scan yet. It runs once per scan, in the background, and is kept; it appears here when it has. Until then all 149 findings above stand exactly as their scanners reported them, at full severity.