agentleFS
NVIDIAKnown publisherNVIDIA/simready-foundation/.agents/skills/simready-foundation-update-validator/SKILL.md

simready-foundation-update-validator

Skill156 starsChanged 52 days agoApache-2.0View on GitHub

Use for updating SimReady validators, failure messages, edge cases, and tests while preserving requirement semantics.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 12 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈12

    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:

    Use this skill when a validator exists but is stale, wrong, incomplete, too strict, too loose, or out of sync with requirement docs.

    line 17
  2. Distinctive:

    If changing validator behavior changes the contract, coordinate requirement and feature version updates instead of silently altering …

    line 19
  3. Distinctive:

    Use this checklist when changing the repository:

    line 44
  4. Distinctive:

    Keep failure messages stable unless they are unclear or wrong.

    line 53
  5. Distinctive:

    import/syntax checks where possible

    line 57
  6. Distinctive:

    Do not broaden a validator to cover undocumented requirements.

    line 78
  7. Distinctive:

    Do not remove a failure without explaining why the requirement allows the case.

    line 79
  8. Distinctive:

    Avoid changing registration IDs except to fix a clear mismatch with docs.

    line 80
  9. Distinctive:

    If tooling is unavailable, report the exact environment gap and the narrower checks performed.

    line 81
  10. Distinctive:

    Do not silently change published contracts.

    line 85
  11. Distinctive:

    Do not update docs without checking validator, manifest, profile, adapter, and runtime-test impact.

    line 86
  12. Distinctive:

    Do not broaden a change beyond the selected requirement, capability, feature, profile, validator, or adapter.

    line 87

≈ “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

SimReady Update Validator

Purpose

Use this skill when a validator exists but is stale, wrong, incomplete, too strict, too loose, or out of sync with requirement docs.

If changing validator behavior changes the contract, coordinate requirement and feature version updates instead of silently altering published validation semantics.

Prerequisites

Before editing, read:

  • AGENTS.md
  • target validation.py
  • requirement docs for every registered requirement in the checker
  • feature manifests and profiles that include those requirements
  • existing tests or sample assets for the capability

Inputs

Collect or infer:

InputRequirement
checkerExisting class/function to update.
requirement_codesRequirement IDs affected.
bug_or_gapFalse positive, false negative, crash, message issue, missing edge case, or docs drift.
contract_impactEditorial/bug fix or changed pass/fail semantics.
test_evidenceReport, asset, stack trace, or expected behavior.

Instructions

Use this checklist when changing the repository:

  1. Reproduce or inspect the reported validator behavior when possible.
  2. Compare validator logic to requirement docs and feature manifest usage.
  3. Classify the change:
    • Bug fix: implementation failed to match existing requirement.
    • Contract change: desired behavior differs from documented requirement.
  4. For bug fixes, patch the validator and tests/samples.
  5. For contract changes, update requirement docs and create new feature/profile versions before or alongside validator changes.
  6. Keep failure messages stable unless they are unclear or wrong.
  7. Preserve existing valid edge cases unless the requirement explicitly changes.
  8. Validate:
    • focused pass/fail assets or tests
    • import/syntax checks where possible
    • affected feature/profile validation when tooling is available

Examples

Example request:

Update an existing SimReady validator after a requirement behavior change.

Expected result summary:

changed_files: updated docs, manifests, indexes, validators, or adapters
validation: focused checks for the changed contract
remaining_gaps: downstream feature, profile, adapter, or runtime-test follow-up

Policies

  • Do not broaden a validator to cover undocumented requirements.
  • Do not remove a failure without explaining why the requirement allows the case.
  • Avoid changing registration IDs except to fix a clear mismatch with docs.
  • If tooling is unavailable, report the exact environment gap and the narrower checks performed.

Limitations

  • Do not silently change published contracts; add versions when behavior changes.
  • Do not update docs without checking validator, manifest, profile, adapter, and runtime-test impact.
  • Do not broaden a change beyond the selected requirement, capability, feature, profile, validator, or adapter.

Troubleshooting

  • Error: the requested change alters a published contract. Solution: create a new version and preserve the old artifact.
  • Error: docs and machine-readable manifests diverge. Solution: make the JSON/TOML and markdown agree, then rerun focused checks.
  • Error: downstream profile or adapter impact is unclear. Solution: list the affected artifacts before making broad edits.

Resources

  • assets/openai.yaml preserves optional UI metadata for clients that read skill display hints. It is not required for the workflow.

Summary Format

Report:

FieldMeaning
checkerValidator changed.
requirement_codesRequirements affected.
contract_impactBug fix or contract change.
docs_changedRequirement docs updated or not needed.
testsTests/assets run.
feature_profile_followupVersioning or profile updates needed.
validationRemaining gaps.

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.