agentleFS
boyingliu01boyingliu01/xp-gate/skills/test-specification-alignment/AGENTS.md

xp-gate / test-specification-alignment

AGENTS.md4 starsChanged 6 months agoMITView on GitHub

Generated: 2026-11-04 Commit: eb2097b0 Branch: sprint/2026-11-03-02 Version: 0.37.0.0

The file

We split this AGENTS.md into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    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:

    Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.

    line 9
  2. Distinctive:

    Test annotations trace to REQ-XXX and AC-XXX

    line 31
  3. Distinctive:

    Do NOT modify tests during Phase 2 execution

    line 34
  4. Distinctive:

    Do NOT proceed with low alignment score (<80%)

    line 35
  5. Distinctive:

    Do NOT skip specification validation if specification exists

    line 36
  6. Distinctive:

    Do NOT delete test files in Phase 2 (freeze intercepts)

    line 37
  7. Distinctive:

    Do NOT modify assertions when tests fail (modify business code instead)

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md

SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE

Generated: 2026-11-04 Commit: eb2097b0 Branch: sprint/2026-11-03-02 Version: 0.37.0.0

OVERVIEW

Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.

STRUCTURE

skills/test-specification-alignment/
├── SKILL.md              # Core alignment workflow (2-phase)
├── AGENTS.md             # This file
├── evals/                # Evaluation test cases
└── references/           # Supporting documentation

WHERE TO LOOK

TaskLocationNotes
Core workflowSKILL.mdPhase 1 (align) + Phase 2 (execute)
Freeze mechanismSKILL.mdPrevents test modifications during Phase 2

CONVENTIONS

  • Phase 1 (Align): test modifications ALLOWED to align with specification
  • Phase 2 (Execute): test modifications FORBIDDEN (freeze enforced)
  • Minimum 80% alignment score required to pass
  • All @test, @intent, @covers JSDoc tags mandatory in test files
  • Test annotations trace to REQ-XXX and AC-XXX

ANTI-PATTERNS (THIS PROJECT)

  • Do NOT modify tests during Phase 2 execution
  • Do NOT proceed with low alignment score (<80%)
  • Do NOT skip specification validation if specification exists
  • Do NOT delete test files in Phase 2 (freeze intercepts)
  • Do NOT modify assertions when tests fail (modify business code instead)
  • Missing @test tags → test rejected

UNIQUE STYLES

  • Two-phase separation (modify vs. execute)
  • Freeze/unfreeze test protection mechanism
  • YAML specification-driven validation (specification.yaml)
  • Structured JSDoc tag requirements (@test, @intent, @covers)

COMMANDS

/test-specification-alignment   # Run alignment check

NOTES

  • Runs during BUILD (Phase 2) after TDD
  • Mandatory before gstack-ship release
  • Integrates with test-driven-development skill
  • Uses freeze skill to lock test directories during Phase 2

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.