agentleFS
veep2012veep2012/doc_mcp/.agents/skills/test-scenario-guardian/SKILL.md

test-scenario-guardian

Skill0 starsChanged 3 months agoMITView on GitHub

Enforce scenario-first verification development with strict bidirectional traceability between documentation/test_scenarios/*.md and automated verification artifacts in tests/ or scripts/. Use for test creation, updates, and reviews.

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 11 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    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:

    Use this skill to keep test scenarios and automated verification tightly synchronized.

    line 10
  2. Distinctive:

    Ensure bidirectional links so changing one requires updating the other.

    line 15
  3. Distinctive:

    Treat scenario documentation as the single source of truth for expected behavior.

    line 16
  4. Distinctive:

    Use for new or updated tests, smoke checks, scenario documents, and reviews where behavior or coverage changes.

    line 20
  5. Very specific:

    Ensure a scenario file exists in documentation/test_scenarios/.

    line 26
  6. Very specific:

    Add or update the executable verification artifact in tests/ or scripts/.

    line 34
  7. Distinctive:

    Keep assertions aligned to scenario acceptance criteria.

    line 36
  8. Distinctive:

    When behavior differs between docs and verification artifacts, update verification to match docs unless the user explicitly asks to revise …

    line 37
  9. Distinctive:

    Add or maintain a lightweight traceability check when feasible so missing scenario IDs or mapping entries fail validation.

    line 43
  10. Distinctive:

    If automated verification changed, update scenario docs in the same change.

    line 47
  11. Distinctive:

    If scenario docs changed, update automated verification in the same change.

    line 48
  12. Distinctive:

    Verify documentation markdown filenames contain no uppercase letters:

    line 51
  13. Distinctive:

    Always report scenario files updated, verification artifacts updated, traceability checks added or updated, and any intentional gaps such …

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 Scenario Guardian

Overview

Use this skill to keep test scenarios and automated verification tightly synchronized.

Core rule:

  1. Define or update scenarios first in documentation/test_scenarios/.
  2. Implement or update automated verification in the appropriate executable artifact.
  3. Ensure bidirectional links so changing one requires updating the other.
  4. Treat scenario documentation as the single source of truth for expected behavior.

When To Use

Use for new or updated tests, smoke checks, scenario documents, and reviews where behavior or coverage changes.

Workflow (Required)

Step 1: Create or update the scenario document first

  • Ensure a scenario file exists in documentation/test_scenarios/.
  • Scenario filenames must be lowercase only.
  • Update Document Control metadata.
  • Define stable scenario IDs, for example TS-DL-001.
  • For each scenario include intent, setup/preconditions, request or action, expected response/assertions, and cleanup when required.

Step 2: Implement automated verification from scenario IDs

  • Add or update the executable verification artifact in tests/ or scripts/.
  • Each artifact must reference scenario IDs in code, comments, docstrings, or adjacent metadata.
  • Keep assertions aligned to scenario acceptance criteria.
  • When behavior differs between docs and verification artifacts, update verification to match docs unless the user explicitly asks to revise docs first.

Step 3: Enforce bidirectional traceability

  • In scenario docs, add an Automated Test Mapping section with concrete artifact names and entrypoints.
  • In automated verification artifacts, map back to scenario IDs and the scenario document path where practical.
  • Add or maintain a lightweight traceability check when feasible so missing scenario IDs or mapping entries fail validation.

Step 4: Validate and tighten

  • If automated verification changed, update scenario docs in the same change.
  • If scenario docs changed, update automated verification in the same change.
  • Reject partial updates that only modify one side when linkage is affected.
  • Resolve ambiguity by tightening the scenario doc first, then update tests in the same change.
  • Verify documentation markdown filenames contain no uppercase letters:
    • find documentation -type f -name '*.md' | rg '[A-Z]'

Output Requirements

Always report scenario files updated, verification artifacts updated, traceability checks added or updated, and any intentional gaps such as manual-only scenarios.

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.