agentleFS
Sign inStart free
teemutuoteemutuo/super-intelligent-AI-setup/skills/05-quality-gate/SKILL.md

quality-gate

Skill0 starsChanged 6 months agoMITView on GitHub

Auto-activating verification policy that runs after any significant output (document, analysis, report, presentation). Verifies factual accuracy, brand compliance, regulatory alignment, completeness, and reasoning quality. Triggers after creating: report, document, analysis, deck, presentation, board pack, memo, deliverable.

42 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use deploy.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • VercelSkill

    deploy

    Deploy applications to Vercel. Use when the user says "deploy", "deploy to Vercel", "push to production", "deploy my app", or "go live".

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 34 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After producing any non-trivial output, run this gate before declaring done.

    line 12
  2. Distinctive:

    Every named person, number, date, and quote: traceable to a source

    line 17
  3. Distinctive:

    No em dashes, no marketing superlatives, no AI-tells like "delve" or "in today's fast-paced world"

    line 29
  4. Distinctive:

    No circular references between sources

    line 44
  5. Distinctive:

    If all eight pass:

    line 58

“Common” is measured: kept by at least 6 in 10 of the 34 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

Quality Gate · Universal QA

After producing any non-trivial output, run this gate before declaring done. If any check fails, fix and re-run.

The Eight Checks

1. Factual accuracy

  • Every named person, number, date, and quote: traceable to a source
  • Any number not in the source data: explicitly marked as estimate
  • Any acronym: spelled out on first use

2. Source citation

  • Sources listed at the end of any data-bearing output
  • Distinguish primary (the actual document) from secondary (commentary on the document)
  • Distinguish company numbers (named) from market numbers (cited)

3. Brand and voice compliance

  • Voice attributes followed (refer to your brand-voice skill)
  • Colors and typography from the design system
  • No em dashes, no marketing superlatives, no AI-tells like "delve" or "in today's fast-paced world"

4. Regulatory alignment

  • For EU operations: GDPR (personal data), EU AI Act (any AI use case classified by risk), CSRD (sustainability claims), MAR (anything market-sensitive)
  • For US operations: SOX, SEC disclosure, state privacy laws
  • For finance specifically: applicable accounting standard cited (IFRS or GAAP)

5. Completeness

  • The user's question answered, not adjacent question
  • Counter-arguments acknowledged
  • Caveats and assumptions surfaced

6. Reasoning quality

  • Logic chain visible, not just conclusions
  • Numbers add up (literally check the arithmetic)
  • No circular references between sources

7. Audience fit

  • Plain language for non-experts; technical depth where audience expects it
  • Length matches the request (15-minute talk does not need 40 slides)
  • Format matches the context (memo, deck, table, conversation)

8. Tactical sanity

  • Does the user know what to do after reading this?
  • Are owners and dates assigned where relevant?
  • Is anything missing that the user will get asked about in the next meeting?

Output

If all eight pass:

QUALITY GATE: PASS
Confidence: [HIGH | MEDIUM | LOW]
Notes: [any caveats]

If any fail:

QUALITY GATE: FAIL on [check number and name]
Issue: [one line]
Fix: [what I'm doing about it]

Re-run until pass. Never declare done with an open fail.

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.

Check your setup, free