Scan reports · sickn33/agentic-awesome-skills
agent-evals: scan report
Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Use when shipping agent features, validating prompt changes, or gating deployments on quality. An automated scan of this public skill from sickn33/agentic-awesome-skills: security, token cost, spec and clarity, with every finding and its fix.
Result
Verdict
81/100 · grade B
sickn33/agentic-awesome-skills/plugins/agentic-awesome-skills-claude/skills/agent-evals at c564f9f
Spec 21 · Efficiency 22 · Clarity 25 · Security 13 (each out of 25)
Always loaded 52 tokens · on trigger 3,143 · on demand 0
sec/prompt-injectionwarn · SKILL.md:163Tries to override the agent's instructions. Reads as an example or a warning here; check it in context.sec/prompt-injectionwarn · SKILL.md:164Role-hijack phrasing. Reads as an example or a warning here; check it in context.spec/non-portable-keyswarn · SKILL.mdNon-spec frontmatter (category, risk, source, source_repo, source_type, date_added, license_source). claude.ai and the Skills API reject the upload; move them under `metadata` or drop them.eff/no-disclosureinfo · SKILL.md~3143 tokens in one file. Long tables, examples or catalogues belong in reference files.
Where it comes from
Source
| Fact | Value |
|---|---|
| Repository | sickn33/agentic-awesome-skills |
| Skill folder | plugins/agentic-awesome-skills-claude/skills/agent-evals |
| Stars | 47,723 |
| License | MIT |
| Commit scanned | c564f9f |
| Scanned | 2026-10-16 |
| 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/sickn33-agent-evals)
Same repository
More from sickn33/agentic-awesome-skills
- 00-andruia-consultantGrade A90/100
- 007Grade F50/100
- 10-andruia-skill-smithGrade B86/100
- 20-andruia-niche-intelligenceGrade B86/100
- 2slides-ppt-generatorGrade B80/100
- 360-feedback-systemGrade A91/100
- 3d-web-experienceGrade A96/100
- aas-compose-stackGrade A90/100
- aas-discoverGrade B84/100
- aas-review-stackGrade A90/100
- ab-test-setupGrade A96/100
- ab-testingGrade B84/100
FAQ
Questions
- Is agent-evals safe to install?
- No critical findings, some security notes. 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 c564f9f on 2026-10-16. 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.