agentleFS
MicrosoftKnown publishermicrosoft/frontier-ghcp-ttt-rvas/.github/skills/session-format-validator/SKILL.md

session-format-validator

Skill3 starsChanged 54 days agoMITView on GitHub

Validate new or changed GitHub Copilot Train-the-Trainer session directories before they are added to the curriculum. Use this skill whenever a user creates, adds, updates, reviews, or asks whether a session under sessions/session-* follows the repository's repeatable format, including required materials, catalog metadata, navigation, and lab access or fallback guidance. Use it even when the user only asks to check a session README or lab.

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 7 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to verify that a training session is ready to join the curriculum.

    line 9
  2. Distinctive:

    Run the validator from the repository root:

    line 18
  3. Very specific:

    Add --json when the result must feed another tool or a CI job.

    line 25
  4. Distinctive:

    Read the session overview, lab, and trainer guide only for findings that need explanation.

    line 26
  5. Distinctive:

    If every check passes, omit Needs work.

    line 68
  6. Distinctive:

    Keep existing material intact during validation.

    line 74
  7. Distinctive:

    Do not accept a manual simulation as a replacement for required Copilot access.

    line 76
  8. Distinctive:

    Do not require a live vendor tool, customer access, or a finished application.

    line 79
  9. Very specific:

    Use scripts/validate-labs.sh separately when the user also asks to validate executable starter or solution files.

    line 80

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Session format validator

Use this skill to verify that a training session is ready to join the curriculum. It reports gaps. It does not create files, rewrite curriculum content, or repair metadata unless the user asks for a separate implementation task.

Validate a session

  1. Identify the session directory by its full module-local ID, such as m2-01. Find the matching sessions/session-m2-01-* directory. If the user provides only a local number, ask which module they mean.
  2. Run the validator from the repository root:

    python .github/skills/session-format-validator/scripts/validate_session.py \
      sessions/session-mN-NN-topic

    Add --json when the result must feed another tool or a CI job.

  3. Read the session overview, lab, and trainer guide only for findings that need explanation. Do not invent a requirement that the validator did not find.
  4. Report results under Passed checks and Needs work. Group failures by materials, metadata, navigation, or lab readiness. Include the exact file and a concrete correction for every failed check.

What the validator checks

  • Required materials: overview, trainer guide, lab guide, slides, starter assets, and solution assets.
  • Trainer slides: a trainer-facing deck that explains the core concepts before the lab, including an agenda, concrete examples or decision criteria, and a lab handoff. Treat a short agenda-only outline as incomplete teaching material.
  • Metadata: the directory name, overview heading, shared catalog entry, and valid module, difficulty, and duration values.
  • Navigation: entries in mkdocs.yml, README.md, curriculum-plan.md, and tracks/full-mastery.md.
  • Lab readiness: a setup or preflight section, a learner deliverable, and one clear access policy. The lab must require access to the named tools and tell learners to stop when access is missing.

The repository's established template is the reference: track-template/session-template/.

Result format

Use this structure:

## Session mN-NN — <title>

**Status:** Ready | Needs work

### Passed checks

- <short confirmation>

### Needs work

- `path:line or section` — <what is missing>. <specific correction>.

If every check passes, omit Needs work. If the directory is missing, state that first and stop. Do not claim that a session is ready when required files or curriculum navigation are missing.

Scope boundaries

  • Keep existing material intact during validation.
  • Require a firm access prerequisite with a stop-if-missing instruction.
  • Do not accept a manual simulation as a replacement for required Copilot access.
  • Accept another setup only when it uses the same required Copilot capability and preserves the same completion evidence.
  • Do not require a live vendor tool, customer access, or a finished application.
  • Use scripts/validate-labs.sh separately when the user also asks to validate executable starter or solution files.

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.