Scan reports · trailofbits/skills
skill-improver: scan report
Runs an autonomous review-and-fix improvement loop over a Claude Code skill until a review comes back clean, with a cross-round findings ledger, escalation when fixes stop converging, and a mechanical scope guard.… An automated scan of this public skill from trailofbits/skills: security, token cost, spec and clarity, with every finding and its fix.
Result
Verdict
90/100 · grade A
trailofbits/skills/plugins/code-improver/skills/skill-improver at 5c99c03
Spec 21 · Efficiency 19 · Clarity 25 · Security 25 (each out of 25)
Always loaded 139 tokens · on trigger 1,888 · on demand 0
eff/description-triggerwarn · SKILL.mddescription doesn't say *when* to use the skill ("Use when …"). Agents decide from this line alone.spec/non-portable-keyswarn · SKILL.mdNon-spec frontmatter (argument-hint). claude.ai and the Skills API reject the upload; move them under `metadata` or drop them.
Where it comes from
Source
| Fact | Value |
|---|---|
| Repository | trailofbits/skills |
| Skill folder | plugins/code-improver/skills/skill-improver |
| Stars | 7,641 |
| License | CC-BY-SA-4.0 |
| Commit scanned | 5c99c03 |
| Scanned | 2026-10-19 |
| Files | 1 |
ProSkills doesn't host or redistribute this skill. Get it from its repository, and check the license before reusing it. Something wrong here? Open an issue for a rescan or removal.
For maintainers
Badge for the README
If you maintain this skill, this badge shows its score and links to this report. Fix findings and the score moves with the next scan.
[](https://proskills.dev/reports/trailofbits-skill-improver)
Alternatives
Scanned alternatives on ProSkills
Skills in the ProSkills catalog that cover similar ground. Every one passes the same scanner before it ships.
- TDD LoopOne red, the least green, a refactor, a commit. Repeat.Loads when the user wants a feature or fix driven by tests, one slice at a time.5 rules · Code ReviewScan 100$9
- Test WriterTests that fail before the fix and pass after.Loads when the user needs tests for new code or a bug fix.5 rules · Code ReviewScan 100$9
- Handoff MemoryResume any task in a minute, in any session.Loads when a task outlasts one session, context runs low or the user says resume.5 rules · Agent OpsScan 100$9
Same repository
More from trailofbits/skills
- agentic-actions-auditorGrade F50/100
- algorand-vulnerability-scannerGrade A100/100
- audit-context-buildingGrade F70/100
- audit-prep-assistantGrade A100/100
- burpsuite-project-parserGrade A90/100
- c-reviewGrade A93/100
- cairo-vulnerability-scannerGrade A100/100
- chrome-mcp-troubleshootingGrade A90/100
- code-improverGrade A92/100
- code-maturity-assessorGrade A100/100
- constant-time-analysisGrade C71/100
- cosmos-vulnerability-scannerGrade A92/100
FAQ
Questions
- Is skill-improver safe to install?
- No known risky patterns found. The scan covers prompt injection, hidden Unicode, remote code execution and credential access in every text file of the skill. It cannot judge intent, so read any flagged line in context before installing.
- How was this score calculated?
- Four checks of 25 points each: spec, efficiency, clarity and security. Findings take points off the check they belong to, and any critical finding caps the grade at F. The same scanner runs in your browser at proskills.dev/scan.
- Is this report current?
- It was made from commit 5c99c03 on 2026-10-19. If the skill has changed since, paste the new version into the scanner for a fresh score.
- I wrote this skill. Can I fix the score or have the page removed?
- Fix the findings and push. The reports are rebuilt from GitHub on a schedule, so the next run picks the change up. To have the page removed, open an issue on the ProSkills GitHub repo.
Related
Keep reading
Free tool
Scan your own skill
Paste a SKILL.md or drop a folder. It is scored in your browser and nothing is uploaded.
Want a skill that already passes? Start with a free one.