agentleFS
Sign inStart free
adhyayanrathi01adhyayanrathi01/product-manager-os/skills/qa/test-product-flow/SKILL.md

test-product-flow

Skill2 starsChanged 2 months agoMITView on GitHub

Test a product flow against acceptance criteria across relevant personas, roles, environments, and states. Use for prototype validation, regression checks, exploratory testing, role-based access, instrumentation verification, or PM acceptance testing.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    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:

    Verify browser or test readiness and confirm that the flow cannot affect real users or production data beyond the approved scope.

    line 13
  2. Distinctive:

    If a persona or environment is unavailable, test only ready coverage and report it as partial.

    line 14
  3. Distinctive:

    Read the project goal, selected direction, acceptance criteria, and relevant user roles.

    line 20
  4. Distinctive:

    Read arbitrary QA persona definitions and credential environment-variable names from context.md.

    line 21
  5. Distinctive:

    Test the critical path, alternate states, permissions, errors, empty states, and recovery.

    line 23
  6. Distinctive:

    Verify important analytics behavior when observable.

    line 24
  7. Distinctive:

    Do not deploy fixes or change production without explicit approval.

    line 28
  8. Distinctive:

    Stop and report when a test could affect production data or real users.

    line 31
  9. Very specific:

    Every field above must appear as a labeled section in the produced output.

    line 40

≈ “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

Test Product Flow

<!-- CORE:BEGIN -->

Contract

  • Require the project acceptance criteria, environment, persona names, permitted actions, test scope, and evidence-retention boundary.
  • Resolve persona credentials through the environment-variable names configured in context.md; do not assume fixed roles.
  • Verify browser or test readiness and confirm that the flow cannot affect real users or production data beyond the approved scope.
  • If a persona or environment is unavailable, test only ready coverage and report it as partial. Block unsafe or unauthorized execution.
  • Output reproducible cases, evidence pointers, coverage, failures, and untested areas.
<!-- CORE:END -->

Process

  1. Read the project goal, selected direction, acceptance criteria, and relevant user roles.
  2. Read arbitrary QA persona definitions and credential environment-variable names from context.md; read secret values from the environment only.
  3. Discover the available browser or test capability. Prefer repeatable Playwright CLI flows when configured.
  4. Test the critical path, alternate states, permissions, errors, empty states, and recovery.
  5. Verify important analytics behavior when observable.
  6. Capture reproducible evidence without exposing credentials or personal data.
  7. Distinguish confirmed defects, usability concerns, instrumentation gaps, and untested areas. Mark each finding reproduced, not reproduced, or unknown. A skipped check is not a pass, and a route behind a login with no seeded session is unknown.
  8. Report severity, affected role, reproduction steps, expected behavior, and actual behavior.
  9. Do not deploy fixes or change production without explicit approval.
  10. Save reusable test cases or findings in the project.

Stop and report when a test could affect production data or real users.

<!-- CORE:BEGIN -->

Output

Provide tested environment and personas, coverage, reproducible cases, expected and actual behavior, severity, evidence pointers, instrumentation observations, untested areas, and blockers.

Required fields: Tested environment and personas|Coverage|Reproducible cases|Expected and actual behavior|Severity|Evidence pointers|Untested areas|Blockers

Every field above must appear as a labeled section in the produced output. Verify with evals/check-output.sh test-product-flow <artifact>.

<!-- CORE:END -->

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