Skip to content

Latest commit

 

History

History
32 lines (21 loc) · 1.93 KB

File metadata and controls

32 lines (21 loc) · 1.93 KB

Contributing

Prime directive

A new rule needs a failing test first. If you want to add or change a rule in any SKILL.md or domain adapter, bring the trap scenario where the current version fails and your version passes. A rule that sounds wise but does not move a measured number does not ship.

Nulls get reported. If your experiment shows no effect, that is welcome in the results log too. A log that only contains wins is not worth trusting.

Adding a trap scenario

  1. Create eval/scenarios/<name>/ with fixture files. A good trap makes the plausible action the wrong one, and its ground truth is deterministic (checkable by diff, execution, or a source file).
  2. Write GROUND-TRUTH.md: the task prompt, the trap, scoring caps, ideal behavior.
  3. Do not name the evidence in the task prompt (that pre-solves the scenario).
  4. Run it A/B (with and without the skill) using eval/workflow.py, 2+ seeds per cell.
  5. PR the fixture, sanitized judge outputs, and a RESULTS.md entry.

Adding a domain adapter

An adapter earns a file only if its four nouns genuinely differ from existing adapters: what counts as evidence, who the authority is, what verification means, and what the frauds are. Follow TEMPLATE.md. Bring the discriminating scenario. Sectors that fold into existing adapters get a routing line, not a file. Medical/clinical stays excluded.

Style

  • No em dashes or en dashes. Use commas, colons, parentheses, or two sentences. CI enforces this.
  • Skills stay lean. Depth goes in references/, loaded on demand.
  • Run python .github/checks.py before pushing.

Hermes skill standards

  • Frontmatter: name, description (trigger-focused, under 1024 chars), version, author, license, metadata.hermes.tags, metadata.hermes.related_skills
  • Directory: skills/<category>/<skill-name>/SKILL.md
  • Supporting files: references/, templates/, scripts/ subdirectories
  • Total file under 100,000 chars (aim for 8-15k)