Agent skill
rules-normalize
Convert implicit or scattered project conventions into governed GAAI rule files, and create or modify rule files with integrity. Activate during Bootstrap, when creating a new rule, or when modifying an existing rule.
Install this agent skill to your Project
npx add-skill https://github.com/Fr-e-d/GAAI-framework/tree/main/.gaai/core/skills/cross/rules-normalize
Metadata
Additional technical details for this skill
- id
- SKILL-RULES-NORMALIZE-001
- track
- cross-cutting
- author
- gaai-framework
- status
- stable
- version
- 1.0
- category
- cross
- updated at
- 1772064000
SKILL.md
Rules Normalize
Purpose / When to Activate
Activate when:
- Bootstrap — project has existing conventions (linters, security policies, style guides, architecture docs, CI constraints) that need to become explicit governance
- Creating a new rule — any agent or human intends to add a new
.rules.mdfile - Modifying an existing rule — any agent or human intends to change the content or structure of an existing rule file
Converts all implicit conventions into explicit GAAI governance rules. Ensures rule integrity on creation and modification.
Process
When normalizing existing conventions (Bootstrap)
- Locate all rule-like files and convention sources
- Classify by domain: architecture / code quality / security / testing / performance
- Translate each convention into standard GAAI rule format:
- Explicit condition
- Scope of application
- Enforcement level
- Store normalized rules under
contexts/rules/ - Remove ambiguity and duplication
When creating or modifying a rule file
- Read
contexts/rules/README.rules.md— verify no existing rule already covers the intent - If creating: assign the correct
categoryand nextidin sequence; add entry to index - If modifying: confirm the change is a constraint refinement, not a workflow or agent behavior addition
- Apply the standard rule file format (YAML frontmatter + markdown body)
- Verify no overlap or contradiction with other rule files
Quality Checks
- All critical project constraints are explicit
- Rules are machine-checkable
- No important convention remains implicit
- Governance coverage is clear
- No duplication across rule files
Non-Goals
This skill must NOT:
- Create new architectural decisions
- Modify business logic
- Enforce rules during delivery (enforcement is handled by workflows and validation stages)
No silent assumptions. Every constraint becomes explicit and governed.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
ci-watch-and-fix
Watch GitHub Actions CI after PR creation, detect failures, extract logs, apply minimal fixes, and re-push — keeping the delivery session alive until CI resolves or escalating after 3 cycles. Activate immediately after gh pr create and before marking the story done.
qa-review
Validate that implemented code fully satisfies Story acceptance criteria, respects rules, and introduces no regressions. This is the hard quality gate — no pass means no delivery. Activate after implementation is complete.
compose-team
Assemble the context bundles for each sub-agent based on evaluate-story output. Produces spawn-ready packages for Planning, Implementation, QA, or MicroDelivery sub-agents. Activate after evaluate-story, before spawning any sub-agent.
coordinate-handoffs
Validate sub-agent handoff artefacts, sequence phase transitions, and manage retry and escalation logic. Activate after each sub-agent terminates to determine next action.
implement
Generate correct, minimal, maintainable code that satisfies a validated Story's acceptance criteria against an execution plan. Activate when a Story is validated, a plan exists, and all prerequisites are unambiguous.
delivery-high-level-plan
Transform validated Stories into a clear, minimal, governed execution plan. Used by the Planning Sub-Agent as the first planning pass before prepare-execution-plan for Tier 2/3, or as the sole planning output for simple Stories.
Didn't find tool you were looking for?