agentleFS
Sign inStart free
extra-orgextra-org/extra/.claude/skills/yaml-schema/SKILL.md

yaml-schema

Skill119 starsChanged 5 months agoMITView on GitHub

Loading agent.yml, defining schema models, and validating the specification (definitions, hierarchy, security). Primary task is tasks/0002-yaml-schema-and-validation.md.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Very specific:

    Do not edit this file directly.

    line 10
  2. Very specific:

    Use this when working on loading YAML configs, defining schema models, or validating the Agent Engine specification.

    line 18
  3. Distinctive:

    Keep schema/validation separate from the compiler.

    line 47

≈ “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
<!-- This file is generated by tools/skills. Do not edit this file directly. Edit .ai/skills/yaml-schema.md and run `make generate-ai`. -->

Skill: YAML Schema & Validation

When to use this skill

Use this when working on loading YAML configs, defining schema models, or validating the Agent Engine specification. Primary task: tasks/0002-yaml-schema-and-validation.md.

Files to read first

  • AGENTS.md
  • docs/YAML_SPEC.md
  • examples/agents.yml
  • examples/config.schema.json
  • docs/adr/0002-yaml-is-compiled-not-executed-directly.md

Architecture rules

  • YAML is declarative data, never code.
  • The spec has two halves: flat declarations and graph topology.
  • Validation must happen before compilation.
  • Runtime layers consume only validated/compiled models, never raw YAML dicts.
  • Secrets are never values in YAML.

Implementation rules

  • Define typed schema models in src/agentplatform/spec.
  • Validation belongs in src/agentplatform/validation.
  • Report all validation errors with useful locations.
  • Enforce: required system and graph; one graph root; graph ids exist in orchestrators or agents; no cycles; referenced resolvers/tools/MCPs exist; orchestrators have prompts.orchestrator; model overrides are complete; protected nodes require the access plugin at startup.
  • Keep schema/validation separate from the compiler.

Validation checklist

  • Schema models cover docs/YAML_SPEC.md.
  • examples/agents.yml validates successfully.
  • Dangling references, missing/multiple roots, and cycles fail clearly.
  • Unknown keys and hardcoded secrets are rejected.
  • Tests cover valid and invalid specs.
  • make check passes.

Common mistakes to avoid

  • Mixing validation with compilation or runtime logic.
  • Failing fast on the first error instead of collecting all errors.
  • Reintroducing the old definitions / hierarchy shape.
  • Letting unknown/typo'd keys pass silently.

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