human-docs-generator
Generates role-based human documentation (<1000 words per doc). Use when epics complete, breaking changes occur, or architecture decisions are made. Creates guides for developers, QA, DevOps, and business stakeholders.
What this skill does
# Human Docs Generator Skill
## Role
Automatically generates and maintains role-specific documentation for humans when significant changes occur in the system.
## Purpose
Transform complex AI state and technical implementations into simple, role-specific guides that humans can actually understand and use.
## Trigger Conditions
### Automatic Triggers
- โ
Epic completed
- ๐ง Public API modified
- ๐ฏ New user feature deployed
- ๐ฅ Breaking change introduced
- ๐ Critical bug fixed
- ๐ 5+ related tasks completed
### Manual Trigger
```json
{
"event": "generate.human.docs",
"scope": "all|specific-role",
"reason": "manual request"
}
```
## Document Structure
### Files Maintained
```
ai-state/human-docs/
โโโ INDEX.md # Role directory & quick nav
โโโ frontend-developer.md # React, components, routes
โโโ backend-developer.md # APIs, models, database
โโโ architect.md # System design, patterns
โโโ devops.md # Deploy, monitor, debug
โโโ tester.md # Test suites, coverage
โโโ product-manager.md # Features, metrics, roadmap
โโโ end-user-guide.md # Screenshots, how-to-use
```
## Generation Process
### 1. Gather Context
```yaml
sources:
- ai-state/active/ # Current implementations
- ai-state/knowledge/ # Patterns and decisions
- operations.log # Recent changes
- test-results/ # What's working
```
### 2. Extract Role-Relevant Info
#### Frontend Developer Needs
- Component locations & hierarchy
- State management patterns
- Reusable components list
- Recent UI changes
#### Backend Developer Needs
- API endpoint documentation
- Database schema changes
- Authentication flow
- Service dependencies
#### End User Needs
- Screenshots with annotations
- Step-by-step guides
- Feature locations
- Common workflows
### 3. Transform to Human Format
#### Rules for Human Docs
1. **Max 1000 words** per document
2. **Diagrams over text** (Mermaid.js)
3. **Examples over explanations**
4. **Current state only** (no history)
5. **Quickstart focused**
### 4. Generate Diagrams
#### Component Tree (Frontend)
```mermaid
graph TD
App --> Header
App --> Routes
Routes --> Login
Routes --> Dashboard
Dashboard --> Charts
Dashboard --> Tables
```
#### API Flow (Backend)
```mermaid
sequenceDiagram
User->>Frontend: Click Login
Frontend->>API: POST /auth/login
API->>Database: Validate credentials
Database->>API: User data
API->>Frontend: JWT token
Frontend->>User: Dashboard
```
#### User Flow (End User)
```mermaid
graph LR
Start[Open App] --> Login[Enter Email/Pass]
Login --> Dash[View Dashboard]
Dash --> Upload[Upload Data]
Upload --> Process[Wait for Processing]
Process --> View[View Results]
View --> Export[Download Report]
```
## Document Templates
### Frontend Developer Template
```markdown
# Frontend Developer Guide
## Quick Start
[3-step setup process]
## Component Map
[Mermaid diagram of components]
## To Add a New Page
1. Create component in `/src/pages/`
2. Add route in `/src/routes.tsx`
3. Update navigation in `/src/components/Nav.tsx`
## Available Components
- `<Button>` - Primary actions
- `<Card>` - Content containers
- `<Table>` - Data display
[List reusable components]
## State Management
[Current state shape diagram]
## Recent Changes
- โ
Added password reset
- โ
Updated dashboard layout
```
### End User Template
```markdown
# How to Use [App Name]
## Getting Started
[Screenshot of login page with arrows]
## Main Features
### Upload Data
1. Click "Upload" button (top-right)
2. Select your CSV file
3. Click "Process"
[Screenshot with numbered steps]
### View Reports
[Screenshot of reports page]
- Yellow box = Warnings
- Green box = Success
- Red box = Errors
## Common Tasks
**Q: How do I reset my password?**
A: Click "Forgot Password" on login page
**Q: Where are my old reports?**
A: Click "History" in sidebar
```
## Quality Checks
### Before Publishing
- [ ] Under 1000 words?
- [ ] Has diagrams/screenshots?
- [ ] Includes quickstart?
- [ ] Examples provided?
- [ ] No technical jargon?
- [ ] Tested instructions work?
## Integration
### Input Events
```json
{
"event": "epic.completed",
"epic_id": "epic-oauth",
"tasks_completed": ["task-001", "task-002"],
"changes": ["Added Google login"]
}
```
### Output Events
```json
{
"event": "human.docs.updated",
"files": [
"frontend-developer.md",
"end-user-guide.md"
],
"sections_changed": [
"authentication",
"login-methods"
]
}
```
## Anti-Patterns to Avoid
โ Writing changelogs (just current state)
โ Technical deep-dives (keep it simple)
โ Walls of text (use bullets/diagrams)
โ Assuming knowledge (explain everything)
โ Version history (one living document)
## Success Metrics
- Reading time < 5 minutes
- Diagram-to-text ratio > 40%
- Quickstart success rate > 90%
- Human confusion tickets < 5%
- Doc update frequency = feature frequencyRelated 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 โ 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.