Administer the Acceptance Gate — the leg-checklist that decides a build is DONE: the one command green on a clean checkout, every failure path triggered and clean, the documented path producing the artifacts, the owner's evidence-read of the suite, and the human legs (owner spot-trace + real-user read on main-lane builds). This skill runs the checklist and records the verdict; it never fixes code (red findings route to /finish-build), never weakens a test, and never passes a human leg on the human's behalf — it presents those as blocking stops and records the owner's ruling. The criterion to /finish-build's driver: finish-build drives parked xfail legs to green; this skill proves the whole gate and advances the build to /own-your-code or names exactly what blocks. Triggers on "run the acceptance gate", "gate this build", "is this build done", "verify the build end to end", "final check before ownership", or reaching the gate stage after /finish-build completes. Done when every leg is passed or explicitly deferred to a named discharger, the gate record is written to docs/build_status.md, and the verdict (ADVANCE / BLOCKED) is stated with evidence.
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.
2 critical findings reported by cisco-skill-scanner. 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 -- 'chzylee/ship-pipeline (acceptance-gate)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'chzylee/ship-pipeline (acceptance-gate)' ~/.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
3 findings · 0.7s
v2.0.11
40 findings · 7.9s
v0.3.74
2 findings · 1.3s
v0.1.0
0 findings · 3.3s
v0.1.0
0 findings · 3.3s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
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 16, 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 45 findings above stand exactly as their scanners reported them, at full severity.