メニュー
Validates code, specifications, and tasks against project rules using Straion's semantic matching. Use when checking compliance, validating PRs, reviewing specs against rules, or when user asks "does this meet rules", "check compliance", "validate this".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Guides users through rules-first feature implementation from idea to production code. Validates specs, tasks, and implementation against project rules at every step. Use when building features, implementing specs, creating implementation plans, breaking down specs into tasks, or when user says "help me build", "implement this", "add feature", "plan this", "break down this spec", "create tasks", or wants rules compliance.
Extract development rules from a repository's agent-instruction files (CLAUDE.md, AGENTS.md, AGENT.md), the markdown they reference, and known rule locations like .cursor/rules and CONTRIBUTING.md, then upload them via `straion import-rules`. Use when the user asks to "import rules", "analyze this repo", "extract coding standards", "scan for conventions", when starting on an unfamiliar repository, or when the `straion` CLI hands off to the agent as part of its import flow.
| name | validating-rules |
| description | Validates code, specifications, and tasks against project rules using Straion's semantic matching. Use when checking compliance, validating PRs, reviewing specs against rules, or when user asks "does this meet rules", "check compliance", "validate this". |
straion find-rules:
--files with the key files supporting the change that should be validated--tags with applicable scope tags (e.g. api,domain,testing,security)--keywords with relevant technical keywords (e.g. auth,caching,logging)straion find-rules --help for the full flag list and scope-tag whitelist| Level | What | Check Against |
|---|---|---|
| Spec | PRDs, ADRs, RFCs | Architecture, security, design principles |
| Task | Implementation tasks | Technical rules, API contracts, testing |
| Code | Actual changes | Coding standards, security, performance |
For each rule returned by the CLI:
## Rules Validation Report
### Summary
[X rules checked, Y compliant, Z issues]
### Compliant ✅
- **RULE-123**: [Rule summary] — ✅ [What was done correctly]
### Partial Compliance ⚠️
- **RULE-456**: [Rule summary] — ⚠️ [What's missing]
- **Recommendation**: [Specific fix]
### Violations ❌
- **RULE-789**: [Rule summary] — ❌ [The violation]
- **Risk**: [Impact]
- **Fix**: [Concrete solution]
When violations are found: