agentleFS
arjun988arjun988/blender-skills/.claude/skills/qa-review/SKILL.md

qa-review

Skill2.2k starsChanged 4 months agoMITView on GitHub

Production QA gate for Blender assets using viewport screenshots, validation checklists, naming audits, and ship/no-ship verdicts via MCP.

14 other projects use a version of this.

Adopted by

Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data

Week of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 0 new projectsWeek of Oct 25: 0 new projectsWeek of Nov 1: 0 new projectsWeek of Nov 8: 0 new projects
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 0 in all, so this is a hint, not a trend.

Most recently taken up by

Who's talking about arjun988/blender-skills

The biggest 5 of 12 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 12

Talked about on GitHub (12 times).

On GitHub · 12

7 more on GitHub

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before export or handoff

    line 20
  2. Distinctive:

    After major modeling/lookdev milestones

    line 21
  3. Very specific:

    Use get_viewport_screenshot via MCP when connected.

    line 40

“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

QA Review

Screenshot-backed review. Checklist gate. Explicit ship / no-ship.

When to Use

  • Before export or handoff
  • After major modeling/lookdev milestones
  • Reference-match final compare
  • Periodic scene health checks

Workflow

Gather brief budgets → Screenshot key angles → Run checklists
  → List defects (severity) → Fix or reject → Re-verify → Verdict

Required Screenshots

  1. 3/4 hero angle
  2. Ortho or profile if proportion-critical
  3. Wireframe or poly overview (optional but useful)
  4. Material/light beauty
  5. Vs reference (if reference task)

Use get_viewport_screenshot via MCP when connected.

Checklists (load as needed)

  • ../references/validation-checklist.md
  • ../references/visual-match-checklist.md (reference tasks)
  • ../references/naming-conventions.md
  • ../references/polycount-budgets.md

Defect Severity

LevelMeaning
BlockerWrong scale, broken normals, fails budget badly
MajorSilhouette/readability issues, bad pivots
MinorNaming, minor shading, small gaps
NoteOptional polish

Verdict Template

## QA Verdict: [Asset]

**Result:** SHIP / SHIP WITH NOTES / NO-SHIP
**Budgets:** [tris/textures] vs target
**Screenshots:** [listed]
**Blockers:** ...
**Majors:** ...
**Minors:** ...
**Next actions:** ...

Constraints

MUST DO

  • Give explicit verdict
  • Attach or capture screenshots for visual claims
  • Re-check after fixes before flipping to SHIP

MUST NOT DO

  • Rubber-stamp without screenshots on visual tasks
  • Ignore budget overruns without approval

Reference Guide

TopicReferenceLoad When
Qa Verdict Templatereferences/qa-verdict-template.mdWhen needed
Screenshot Anglesreferences/screenshot-angles.mdWhen needed

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.