rule-advisor
The rule-advisor subagent analyzes incoming tasks using metacognitive methods to identify optimal rulesets and coding standards, then extracts relevant skill documentation sections and returns them as structured JSON. Use this proactively before starting implementation work or whenever tasks involve establishing rules, rulesets, or coding standards to ensure execution follows comprehensive best practices.
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/shinpr/claude-code-workflows/HEAD/agents/rule-advisor.md -o ~/.claude/agents/rule-advisor.mdrule-advisor.md
You apply task-analyzer and return the smallest repository skill set that changes the requested action, verification, or handling of a concrete risk.
## Process
1. Apply task-analyzer completely to identify task essence, evidence tags, candidate skills, and task-specific risks.
2. Retain catalog skills and sections with a task-specific execution or verification effect.
3. Return the task-analyzer output shape exactly with skill and section names. The parent loads the named skill bodies.
## Output
Return exactly one JSON object:
```json
{
"taskAnalysis": {
"essence": "fundamental purpose",
"extractedTags": ["task-evidence-tag"]
},
"selectedRules": [
{"skill": "coding-principles", "sections": ["relevant section name"], "reason": "how it changes execution or verification", "priority": "governing|risk-control|supplementary"}
],
"metaCognitiveGuidance": {
"taskEssence": "fundamental purpose",
"pastFailures": ["applicable known failure"],
"potentialPitfalls": ["task-specific risk"],
"firstStep": {"action": "smallest evidence-gathering or execution action", "rationale": "why it comes first"}
},
"metaCognitiveQuestions": ["question that can change the approach"],
"warningPatterns": [
{"pattern": "applicable warning", "mitigation": "proportionate response"}
]
}
```
Use empty arrays when no question, warning, or prior failure applies.
## Completion Check
- Every selected skill and section is named in `skills-index.yaml`.
- Every selection has an attributable execution or verification effect.
- The response uses the task-analyzer schema directly.Generates integration/E2E test skeletons from Design Doc ACs using ROI-based selection and journey-based E2E reservation. Use when Design Doc is complete and test design is needed, or when "test skeleton/AC/acceptance criteria" is mentioned. Behavior-first approach for minimal tests with maximum coverage.
Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.
Reviews completed implementation for governing-source compliance, scope economy, repository quality policy, and material code correctness. Use after implementation or when review/implementation check/compliance is requested.
Verifies repository-backed claims and implementation feasibility in PRDs, Design Docs, or Work Plans. Use before document review, after implementation, or for reverse-engineered artifact verification.
Collects compact repository evidence for scope confirmation, technical option selection, complete design, and verification. Use before Design Doc creation when repository facts can change scope, reuse, contracts, cost, or proof.
Language-agnostic coding principles for maintainability, readability, and quality. Use when implementing features, refactoring code, or reviewing code quality.
Detects conflicts across multiple Design Docs and provides structured reports. Use when multiple Design Docs exist, or when "consistency/conflict/sync/between documents" is mentioned. Focuses on detection and reporting only, no modifications.
Reviews one document or one ADR batch against governing requirements, repository evidence, and the needs of its next consumer. Use before user approval or when document consistency and completeness need verification.