| name | agent-skill-governance |
| description | Define and enforce project-wide quality standards for agent and skill documents. Use when creating, reviewing, or refactoring files under agents/ and skills/ to keep structure, terminology, and output contracts consistent. |
| disable-model-invocation | false |
Agent and Skill Governance
This skill defines mandatory authoring standards for files under agents/ and skills/.
Scope
- Agent definitions in
agents/*.md
- Skill definitions in
skills/**/SKILL.md
Language and Terminology
- Use English only.
- Keep terminology consistent across files:
decision: go|no_go
blocking_issues
next_actions
validator, generator, checker, interactor
limit_ratio, limit_semantics, wrong_solution_kill
Required Structure
Agent files
Must include:
- Role and responsibility statement.
- Workflow or audit scope.
- Mandatory output contract.
- Fail-fast behavior.
- Forbidden behavior.
Skill files
Must include:
- Purpose.
- Trigger conditions.
- Step-by-step execution guidance.
- Required output format.
- Decision rules (
go vs no_go).
- Forbidden behavior.
Workflow Consistency Rules
- Do not define contradictory workflow steps between agents and skills.
- Do not relax hard gates in documentation unless workflow guard and tool behavior are updated accordingly.
- Never infer completion from file presence when structured tool evidence is required.
Quality Bar
Before finalizing edits:
- Ensure no duplicated instruction blocks.
- Ensure no mixed-language fragments.
- Ensure contract fields are spelled identically across files.
- Ensure each file has explicit no-go criteria.
- Ensure examples do not conflict with enforced gates.
Review Checklist Template
Use this checklist when updating any agents/ or skills/ file:
Project-specific constraints such as maximum clarification count are allowed as long as they are explicit and non-contradictory.