generate-output
Create the deliverable (code, documentation, tests, content) following the user's standards and best practices. Use after validation passes to actually build the work product.
What this skill does
# Generate Output Skill
## Purpose
Transforms validated requirements into actual deliverables (code, documentation, tests, content). This skill follows the user's principles and common patterns defined in their standards.
## What to Do
1. **Read the validated requirements** from the previous step
2. **Load the project type's standards** (from standards.json) to understand their principles and patterns
3. **Generate the deliverable** based on:
- User's specific requirements
- Their saved principles for this project type
- Their common patterns (what they always do)
- Best practices for this type of work
4. **Follow their patterns** - If they defined common patterns, include them:
- Example: "Always include error handling" → include it
- Example: "Always write JSDoc comments" → include it
5. **Create complete, ready-to-use output**
## Project Type Specific Guidance
### Code Features
- Write complete, production-ready code
- Include prop types, type annotations, or schema validation
- Include error handling
- Add comments for complex logic
- Include example usage or test case
- Follow their coding standards (naming, structure, patterns)
### Documentation
- Clear structure with headers
- Include purpose/overview at top
- Add examples and use cases
- Include troubleshooting if applicable
- Link related documentation
- Use their documentation template if defined
### Refactoring
- Show the "before" code
- Show the "after" refactored code
- Explain the improvements
- Highlight what changed and why
- Include the refactored code ready to copy
- Note any behavioral changes
### Test Suite
- Write comprehensive tests
- Test happy path and edge cases
- Use descriptive test names
- Include setup/teardown as needed
- Follow their testing conventions
- Ensure tests are maintainable
### Content Creation
- Compelling introduction
- Clear structure with sections
- Use headers, lists, and examples
- Include practical examples
- Conclusion with key takeaways
- Appropriate tone for audience
## Process
1. Review requirements
2. Load their standards using StandardsRepository
3. Identify their common patterns for this type
4. Generate the output
5. Do a self-check against their principles
6. Present the output with brief summary
## Loading Standards
Use StandardsRepository to access standards:
```javascript
const standards = standardsRepository.getStandards(context.projectType)
if (standards) {
// Use their principles and patterns
const principles = standards.principles
const patterns = standards.commonPatterns
// Generate output following their standards
} else {
// Generate following best practices
}
```
See `.claude/lib/standards-repository.md` for interface details.
## Output Format
Deliver the work with:
```
# [Title of Deliverable]
## Summary
[Brief description of what was created]
## Principles Applied
- [First principle from their standards]
- [Second principle]
- [Third principle]
## Common Patterns Included
- [Pattern 1: brief explanation]
- [Pattern 2: brief explanation]
## The Deliverable
[Complete code, documentation, tests, or content]
## Next Steps
[What they should do next - formatting, testing, review]
```
## Success Criteria
✓ Deliverable is complete and ready to use
✓ Follows user's principles and patterns
✓ Appropriate to project type
✓ Professional quality
✓ Includes necessary supporting elements (comments, examples, structure)
## Example Generation
**Project Type**: React Component
**User Requirements**: "Searchable dropdown component with keyboard nav"
**Their Standards Include**:
- Principles: "Reusable, testable, well-documented"
- Patterns: "Use TypeScript, include PropTypes, export story"
**Generated Output Includes**:
- Complete React component in TypeScript
- PropTypes validation
- Error boundary
- Keyboard event handlers
- Storybook story file
- Usage example
- Comments on complex logic
## Notes
- If user's standards define specific patterns, ALWAYS include them
- Go above minimum - create something they're proud to use
- If unsure about a detail, follow their anti-patterns guidance (do opposite of what they said to avoid)
- Quality over quantity - one well-crafted deliverable beats multiple mediocre ones
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.