qa-gate
Skill2 starsChanged 25 days agoMITView on GitHub
Use when a 3MF must be checked in code against the physical load record and the GUI-only slicer checks during a session (model-invocable variant of /preprint-check). Runs print-qa in a fresh context and returns the PASS/FAIL table; nothing prints on a FAIL.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- GeorgeAuth26/authentalink-playbooktheir own version, first seen Nov 8, 2026
- weedmo/skillstheir own version, first seen Nov 8, 2026
- ZachArticulateV/designer-pro-and-seotheir own version, first seen Oct 19, 2026
- manhds82/claude-code-anyllmtheir own version, first seen Oct 13, 2026
- victoraguilarsantamariadev/qa-exploretheir own version, first seen Sep 28, 2026
- Daniellaguips/ai-agent-ostheir own version, first seen Jun 10, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- manhds82/claude-code-anyllm★ 16same name
- ZachArticulateV/designer-pro-and-seo★ 10same name
- victoraguilarsantamariadev/qa-explore★ 2same name
- GeorgeAuth26/authentalink-playbook★ 1same name
- weedmo/skills★ 1same name
- Daniellaguips/ai-agent-os★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository30 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-reviewSkill
- ai-mesh-cleanSkill
- cad-buildSkill
- couponSkill
- curriculumSkill
- dfm-reviewSkill
- fileSkill
- gddSkill
- ip-checkSkill
- led-budgetSkill
- lesson-learnedSkill
- makerworld-publishSkill
- material-pickSkill
- mcp-new-toolSkill
- ortho-sheetSkill
- pi-power-budgetSkill
- preprint-checkSkill
- promo-planSkill
- render-criticSkill
- research-oneSkill
- research-topicSkill
- retopoSkill
- safety-sheetSkill
- sculptSkill
- slicer-questionSkill
- style-bibleSkill
- tech-packSkill
- unit-costSkill
- verifySkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Before any 3MF is considered for printing, and when the lead needs the gate's verdict inside a running session.
- Very specific: line 17
Read knowledge\00-gear-inventory\current-load.md.
- Very specific: line 18
Read templates\preprint-checklist.md and count its items (15 in the shipped template).
“Common” is measured: kept by at least 6 in 10 of the 4 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.
Files
Overview
Input: $ARGUMENTS, a 3MF path. Output: the PASS/FAIL table in the reply (print-qa has no Write tool); the lead saves it to work\reports\proofs\ or the project's _tests\ folder.
No AI ever starts, sends, uploads or queues a print. A PASS means the file may be shown to you; you press Print in Bambu Studio yourself.
When to use
Before any 3MF is considered for printing, and when the lead needs the gate's verdict inside a running session. When you trigger the gate yourself, use /preprint-check; the two run the same agent and the same steps.
Steps
- Read
knowledge\00-gear-inventory\current-load.md. If it is absent or has noVerified:date, the slots-recorded item FAILs and no filament item can PASS. - Read
templates\preprint-checklist.mdand count its items (15 in the shipped template). - Run, with
.venv\Scripts\python.exefrom the repo root:tools\audit_3mf.py,tools\slice_cli.py(or reuse a fresh slice inwork\slice\<stem>\whose sha256 matches), then per platetools\gcode_audit.py,tools\tower_bounds.py,tools\tower_clearance.py --min-gap 8; plustools\interface_coverage.pyon plates with support,tools\stability_check.pyfor display pieces andtools\visible_ratio.pyfor display or stream prints. Follow the full step list in.claude\skills\preprint-check\SKILL.md. - Fill the checklist item by item with the script line that proves each verdict and one fix per FAIL.
- Return the table, the sha256 lines and the verdict.
Common rationalizations
| Rationalization | Reality |
| "The GUI showed no warning." | The CLI does not surface every GUI warning (the prime-tower clearance warning never reaches result.json); only the scripts prove clearance. |
| "Nothing is loaded yet, skip the load item." | A plate sliced without a recorded load is sliced for a guessed material, and a guessed filament type gets the wrong temperatures. FAIL it. |
| "Another agent already checked this." | Independence is the point. Run the scripts yourself and quote them. |
Red flags
- A PASS without a script line as evidence.
- Any write to the 3MF or to
knowledge\. - Any call that would send, upload or queue a print.
Verification
- Every checklist item has PASS/FAIL plus evidence; row count equals the checklist's item count.
- Verdict stated; FAIL items each have one fix. Nothing prints on a FAIL.
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
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.

