human-review
victorrentea/human-reviewSkill
Assemble .human-review/review.html — a tabbed reviewer's guide for a change set — from the review-points.md the coding agent committed with its fixes (what it fixed, declined and assumed), plus diagram deltas, a Code City shot, a feature video, the endpoint-complexity increment, the REST contract diff and deep-linked snippets. Explicit invocation only — user types /human-review.
Why this score
This repo hosts 4 skills, so its 29 stars are split between them (about 7 each) for scoring.
Popularity score: 59/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 20, 2026 at commit 7bf88c9055a9, first 300 source files (it's a large repo), with Cisco's open-source skill-scanner.
What its code does:
- Reads environment variables and sends network requests with them API clients do this to send your key to the service. Check which service it talks to.
- Runs shell commands Common for dev tools. Read the commands it runs.scripts/drawio-diff.py:1146, scripts/endpoint-complexity.py:171, scripts/hrbuild/shared/c4.py:160 and 26 more
- Runs code it builds while running (eval or exec) Harder to read ahead of time, since the code is assembled while it runs.scripts/review-cost.py
- Makes network requestsSKILL.md, scripts/ds-audit.py:2415, scripts/endpoint-complexity.py:599 and 28 more
- Reads environment variables, where API keys usually livescripts/build-review-html.py:365, scripts/hrbuild/tabs/cost.py:43, scripts/refresh-report.py:421
Web addresses in its code:
- cdn.jsdelivr.netscripts/openapi-visual-diff.py:679
- code.claude.comscripts/hrbuild/tabs/review.py:450
- platform.claude.comscripts/tools/tooling-cost.py:17
- repo1.maven.orgscripts/endpoint-complexity.py:561
- unpkg.comscripts/openapi-visual-diff.py:2346
- victorrentea.github.ioscripts/hrbuild/shared/footer.py:19
- api.fish.audioscripts/narrate-cue.py:103
- app.diagrams.netscripts/drawio-diff.py:746
- apple.comscripts/install-serve-launcher.sh:54
- archunit.orgscripts/hrbuild/shared/adopt.py:249
- c4model.comscripts/c2-from-sequence.py:91
- claude.aiscripts/publish-demo-shots.sh:220
- claude.comscripts/hrbuild/tabs/cost.py:571
- opentelemetry.ioscripts/hrbuild/tabs/sequence.py:970
- sonarcloud.ioscripts/preflight.py:241
And 1 more.
These are the sites named in the code, so it's where your data could go. It isn't a complete list: code can build addresses while it runs, and a few of these may be links rather than calls. Whatever you send also goes to the AI model you use.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This onehuman-review victorrentea/human-review · Skill | 59 | ★ 29 | ≈99 always | 16d ago |
| human-writing KKKKhazix/human-writing · Skill Both about human | 81 | ★ 4.1k | ≈85 always | 3mo ago |
| human-management agentscope-ai/AgentTeams · Skill Both about human | 77 | ★ 5.8k | ≈39 always | 19d ago |
| human-ai fabricioctelles/skills · Skill Both about human | 59 | ★ 114 | ≈21 always | 16d ago |
| messaging-the-human mvschwarz/openrig · Skill Both about human | 78 | ★ 7.9k | ≈40 always | 16d ago |
| Human Risk Scoring WYRE-AI/msp-claude-plugins · Skill Both about human | 53 | ★ 49 | ≈24 always | 21d ago |