agentleFS
rpraharajrpraharaj/ai-sdlc/skills/plan-uat/SKILL.md

plan-uat

Skill0 starsChanged 16 days agoMITView on GitHub

Plan user acceptance testing — scope, data, scripts, and exit criteria. Use when the user asks for a UAT plan, acceptance scripts, business test pack, or /plan-uat. Do not invent sign-off. Do not write product code.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not implement. Do not invent exit criteria or signers.

    line 18
  2. Very specific:

    If Must requirements do not exist, stop and name write-requirements.

    line 35
  3. Very specific:

    Read AGENTS.md if present.

    line 45
  4. Distinctive:

    Read requirements (Must) and the process map.

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Plan UAT

Give the business a pack they can run and sign. This is not a test strategy (write-test-strategy), not automated tests (write-tests), and not go-live (cut-release).

Do not implement. Do not invent exit criteria or signers.

Is this the right skill?

SignalDo this instead
Layers and what we will not automatewrite-test-strategy
Automated caseswrite-tests or write-test-plan
Process as-is / to-bemap-process first
Production releasecut-release after UAT exit is signed

Required inputs

  • Requirements path (Must items)
  • Process map if the change crosses teams (map-process)
  • context/decision-rights.md and context/environments.md if they exist

If Must requirements do not exist, stop and name write-requirements. Do not write UAT against a slide deck.

Human decisions (do not invent)

  • Who signs UAT (decision-rights or the user)
  • Exit criteria if not already on the PRD success checks
  • Whether production-like data may be used (default: no live personal data)

Procedure

  1. Read AGENTS.md if present. Read context/decision-rights.md and context/environments.md if present.
  2. Read requirements (Must) and the process map. Each UAT script traces to a Must id.
  3. Find the home: first existing docs/qa/, or offer to create it. Name: docs/qa/uat-<slug>.md.
  4. Open references/uat-template.md. Copy every heading. Write n/a when unused.
  5. Scripts: actor, steps, data (synthetic), expected. Happy, empty, and deny/error when the requirement has those journeys.
  6. Environment must be a name from environments.md or unknown.
  7. Data: synthetic only unless a human explicitly allows otherwise. Never put live personal data or secrets in the pack.
  8. Exit: reuse PRD success checks when they exist. Otherwise unknown — need human.

Output

  • Path: docs/qa/uat-<slug>.md
  • Template: references/uat-template.md

Quality bar

  • Every script traces to a Must requirement id
  • Signer is named from decision-rights or marked unassigned — need human
  • Exit criteria are PRD success checks or unknown — need human
  • Data is synthetic or an explicit human waiver
  • Unused headings are n/a

Done

  1. Path
  2. Script count
  3. Next skill: wait for human sign-off, then cut-release / ship-notes as the program uses them

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.