Claude Tools / Plugins / skill-creator (example-skills)
Audited plugin listing
skill-creator (example-skills)
Builds, evaluates, and iteratively improves Claude Code skills using an eval-loop: write → test → grade → rewrite → repeat.
Listing signals
Install check
✓ Pass
Risk scan
⚠ Flagged
Implementation
Code-backed
Assessment
Verdict
Skill-creator closes the loop on skill development: write a draft, run eval queries through a fresh Claude subprocess, grade pass/fail with a separate grader agent, auto-improve the description, repeat. The eval infrastructure is the real value — most skill authors never build this, and the gap shows in skills that trigger randomly. The only flag is a Google Fonts load in locally-rendered eval-viewer HTML; it is cosmetic and easy to block at the network level. The SKILL.md's explicit prohibition on building exfiltration or access-bypass skills is a small but meaningful trust signal.
Installation
Add to Claude Code
Source: github.com/anthropics/skills
Evidence
Audit receipts
This listing is tied to a specific source commit and records both installation and risk checks.
Install check
✓ Pass
Ships as part of the example-skills bundle. run_eval.py and run_loop.py invoke `claude -p` via subprocess (list-form, no shell=True) to test skill triggering. eval-viewer spins a local HTTP server on 127.0.0.1 only.
Risk scan
⚠ Flagged
generate_report.py embeds Google Fonts via <link rel="preconnect" href="https://fonts.googleapis.com"> in locally-generated HTML reports — a cosmetic font load that pings Google each time a user opens the eval-viewer. Not a security threat but an undisclosed third-party network contact. The SKILL.md explicitly prohibits creating skills for "unauthorized access, data exfiltration" — a positive safety signal.
Composition
What was measured
Prose lines
1,815
Code lines
2,368
Prose / code
0.77
Related