Loading the registry…
Use this skill for anything to do with authoring, fixing, or measuring Claude skills. Reach for it whenever someone wants to turn a repeated workflow, house format, template, or set of team conventions into something Claude applies automatically every time, even when they never use the word 'skill' and only describe the outcome they want. Also use it when a SKILL.md already exists and misbehaves: it never fires, it fires on the wrong things, the frontmatter will not validate, it has grown too long to follow, or its outputs are inconsistent. Use it to word a description so triggering is reliable, to run evals comparing a skill against a no-skill baseline to find out whether it actually helps, to decide whether something should be a skill at all, and to package one so teammates can install it. Consult it even when the SKILL.md is sitting right there and the format looks simple enough to answer from memory.
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.
23 critical findings reported by cisco-skill-scanner, agent-audit-kit, 13 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 -- 'opencnid/dovetail (better-skill-creator)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'opencnid/dovetail (better-skill-creator)' ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
4 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.
v2.0.11
105 findings · 25.9s
v0.3.74
24 findings · 23.0s
v0.1.0
0 findings · 9.2s
v0.1.0
31 findings · 9.2s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.3s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.2s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.0s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 17, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·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 160 findings above stand exactly as their scanners reported them, at full severity.