Scan reports · code-yeongyu/oh-my-openagent
work-with-pr: scan report
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only… An automated scan of this public skill from code-yeongyu/oh-my-openagent: security, token cost, spec and clarity, with every finding and its fix.
Verdict
code-yeongyu/oh-my-openagent/.agents/skills/work-with-pr at eb3d072
Spec 21 · Efficiency 22 · Clarity 25 · Security 25 (each out of 25)
Always loaded 229 tokens · on trigger 4,400 · on demand 0
spec/broken-refwarn · SKILL.md:141References docs/reference/github-attachment-upload.md, which isn't in the skill folder.eff/no-disclosureinfo · SKILL.md~4400 tokens in one file. Long tables, examples or catalogues belong in reference files.
Source
| Fact | Value |
|---|---|
| Repository | code-yeongyu/oh-my-openagent |
| Skill folder | .agents/skills/work-with-pr |
| Stars | 70,112 |
| License | None stated |
| Commit scanned | eb3d072 |
| 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.
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/code-yeongyu-work-with-pr)
Scanned alternatives on ProSkills
Skills in the ProSkills catalog that cover similar ground. Every one passes the same scanner before it ships.
- Subagent Designer$9Scan 100/1005 rules · Agent OpsSplit work into agents that earn their keep.Loads when the user designs subagents or specialist roles.
- Taste CoreFreeScan 100/1004 rules · Frontend TasteSpacing, type scale, one accent.Loads when the user builds or restyles any UI.
- PR Reviewer$12Scan 100/1005 rules · Code ReviewStaff-level review. Every finding labelled, with a line.Loads when the user asks for a code review or whether a change is safe to merge.
More from code-yeongyu/oh-my-openagent
| Skill | Scan | Grade |
|---|---|---|
| ast-grep | 69/100 | D |
| browser | 73/100 | C |
| codex-qa | 81/100 | B |
| comment-checker | 85/100 | B |
| dag-library | 96/100 | A |
| get-unpublished-changes | 94/100 | A |
| github-triage | 86/100 | B |
| give-me-tips | 84/100 | B |
| hyperplan | 89/100 | B |
| hyperplan | 89/100 | B |
| hyperplan | 85/100 | B |
| init-deep | 89/100 | B |
Questions
- Is work-with-pr 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 eb3d072 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.
Keep reading
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.