Agent skill
directory-generate
Generate NGM Commons directory listings with iterative research and quality review. Uses Perplexity for deep research and Claude Opus for content generation with embedded SVG diagrams.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/directory-generate
SKILL.md
NGM Commons Directory Generator
Generate comprehensive, clinically useful directory listings for the NGM Commons platform.
Invocation
/directory-generate <category_name> --entities "Entity1,Entity2,..." [options]
Arguments:
<category_name>- Category to generate (e.g., "Microbiome Testing")--entities "E1,E2,..."- Required: Comma-separated list of entities--resume- Resume from last checkpoint if interrupted--dry-run- Show execution plan without running--output-dir PATH- Custom output directory (default: content/commons/)
Execution Flow
Phase 1: Research (Perplexity Sonar)
For each entity:
- First Principles (Sonar Reasoning Pro) - HOW it works mechanistically
- Evidence Audit (Sonar Deep Research) - Studies, pricing, regulatory status
Then: 3. Market Context - Category trends and landscape
Phase 2: Content Generation (Claude Opus)
Generate with quality gates (auto-revise up to 3x if score < 0.8):
- Section A: Overview + methodology explanations
- Section B: Per-entity profiles
- Section C: Comparison tables + practice fit
- Section D: NGM Perspective + FAQ
- SVG Diagram: Methodology comparison
Phase 3: Assembly
Combine into directory_content.json + directory_page.html
Quality Criteria
| Criterion | Threshold |
|---|---|
| Clinical Utility | >= 0.8 |
| Educational Rigor | >= 0.8 |
| Vendor Neutrality | >= 0.8 |
| Factual Precision | >= 1.0 |
| Information Density | >= 0.8 |
Key Principles
- EDUCATING not RANKING - No declaring winners
- First Principles - Explain HOW, not just WHAT
- Factual Precision - Never guess pricing
- AEO Optimization - Structured for AI search
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?