quality-check
Skill2 starsChanged 35 days agoMITView on GitHub
Final gate before publishing. Checks the /voice-guardian and /web-content-optimizer grades and that the sensitivity scan ran on work content. Orchestrates, doesn't duplicate.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- emergent-wisdom/understanding-graphtheir own version, first seen Nov 1, 2026
- AlekseiUL/heisenberg-team-GPTtheir own version, first seen Nov 1, 2026
- AlekseiUL/heisenberg-teamtheir own version, first seen Nov 1, 2026
- neeldas1209/GTM-Strategy-Enginetheir own version, first seen Oct 20, 2026
- hsnice16/agent-friendly-codetheir own version, first seen Oct 11, 2026
- bloxy-studios/shorts-studiotheir own version, first seen Oct 1, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- dlupiak/claude-session-dashboard★ 66same name
- AlekseiUL/heisenberg-team★ 17same name
- AlekseiUL/heisenberg-team-GPT★ 9same name
- joris887/exosuit★ 9same name
- MainFrame100/quality-check-skill★ 7same name
- hsnice16/agent-friendly-code★ 2same name
- emergent-wisdom/understanding-graph★ 1same name
- Evan-Kim2028/agent-skills★ 1same name
- bloxy-studios/shorts-studio★ 0same name
- neeldas1209/GTM-Strategy-Engine★ 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 repository11 other files it gives its agents.
- anonymizerSkill
- content-strategistSkill
- find-my-voiceSkill
- portfolio-copywriterSkill
- refreshSkill
- setupSkill
- skill-improverSkill
- story-adapterSkill
- voice-guardianSkill
- web-content-optimizerSkill
- website-expertSkill
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 8 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
- Very specific: line 12
Run before publishing or committing significant changes, after /website-expert builds or changes the site, or whenever the user asks "ready …
- Distinctive: line 26
If a specialist makes changes, re-run that specialist to verify, then come back to QC.
- Distinctive: line 60
If the user wants a quick pass without the specialists:
“Common” is measured: kept by at least 6 in 10 of the 8 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
Quality Check
Final gate before publishing. You are the gate, not the inspector. QC trusts specialists, doesn't redo them.
Run before publishing or committing significant changes, after /website-expert builds or changes the site, or whenever the user asks "ready to publish?". QC is re-runnable, not a one-time gate.
Gate Logic
Gate on the grades from /voice-guardian (all content) and /web-content-optimizer (web pages; N/A for non-web content). Ask the user or check recent output.
| Grade | Decision |
| A / B | PASS |
| C / D | FAIL — fix, re-run that specialist, then come back |
| Not run (or scan not run) | INCOMPLETE — run it first. Takes precedence over FAIL. |
Work content also needs a yes/no: did the sensitivity scan run (/story-adapter's built-in scan or /anonymizer)? Not a grade.
If a specialist makes changes, re-run that specialist to verify, then come back to QC.
Output Format
## Quality Check — Gate Review
**Content:** [what's being checked]
| Check | Specialist | Result |
|-------|------------|--------|
| Voice | `/voice-guardian` | [A/B/C/D/Not run] |
| Web | `/web-content-optimizer` | [A/B/C/D/Not run/N/A] |
| Sensitivity scan (work content) | `/story-adapter` or `/anonymizer` | [Yes/No/N/A] |
**[PASS / FAIL / INCOMPLETE]**
[If PASS:] All checks passed. Content approved.
- "Build it" — `/website-expert` populates the site with approved content
- "Build + deploy" — `/website-expert` builds, then push to GitHub Pages
- "Export content" — get the approved content as files, build later
[If FAIL:] [Area]: Grade [X]. `/[specialist]` can address this.
- "Fix and re-check" — address issues, then re-run `/quality-check`
- "Ship anyway" — publish as-is; your call
- "Fix later" — note issues, move to build with known gaps
[If INCOMPLETE:] Run `/[specialist]` for [area] first.
- "Run them now" — then re-run `/quality-check`
- "Skip and build" — proceed to `/website-expert` with known gapsQuick Spot-Checks (Optional)
If the user wants a quick pass without the specialists:
- No placeholder text visible ("[Your Name]", "Lorem ipsum")
- No obvious broken links on main pages
- Content loads on mobile
Recommend full specialist reviews before a major publish.
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.

