human-docs
Creates human-friendly documentation from AI context documentation. Transforms detailed AI documentation in ai/ folder into digestible summaries, quick starts, and visual diagrams in docs/ folder. Use when users need to quickly understand complex systems or when AI documentation is too detailed for human consumption. Specializes in Mermaid diagrams, executive summaries, and quick reference guides.
What this skill does
# Human Documentation Generator
## Purpose
This skill transforms detailed AI documentation stored in `ai/` folder into human-friendly documentation in `docs/` folder. It creates summaries, quick starts, and visual diagrams that enable humans to quickly understand and operate complex systems.
**Key principle:** `ai/` folder remains the source of truth (detailed, comprehensive, for AI context). `docs/` folder contains human-optimized extracts (summaries, diagrams, quick references).
## When to Use This Skill
Use this skill when:
- User needs human-readable documentation from AI context docs
- AI documentation is too detailed for quick human consumption
- System complexity requires visual diagrams for understanding
- Need quick start guides or executive summaries
- User specifically mentions difficulty following AI documentation
- Creating onboarding materials for new team members
- Extracting crucial information for operational quick reference
**Trigger phrases:**
- "Create human docs for..."
- "I can't follow the AI documentation"
- "Make this easier to understand"
- "Create a quick start guide"
- "Add diagrams to explain..."
- "Summarize the AI docs"
## Core Principles
### 1. Parallel Structure Maintained
```
ai/ docs/
├── architect/ ├── architect/
│ ├── app/ │ ├── app/
│ │ └── 01_DOC.md │ │ └── 01_DOC_SUMMARY.md
│ └── src/ │ └── src/
│ └── 01_DOC.md │ └── 01_DOC_QUICKSTART.md
├── backend/ ├── backend/
├── frontend/ ├── frontend/
└── testing/ └── testing/
```
**Key rule:** `docs/` mirrors `ai/` structure but contains human-optimized versions
### 2. Three Human-Friendly Formats
**For each AI doc, create ONE or MORE of:**
1. **SUMMARY** (`*_SUMMARY.md`)
- Executive summary (1-2 paragraphs)
- Key points (bullet list)
- Quick decision aids
- 20% of original length
2. **QUICKSTART** (`*_QUICKSTART.md`)
- Step-by-step getting started
- 5-minute read maximum
- Code examples
- Common pitfalls
- Success criteria
3. **DIAGRAMS** (`*_DIAGRAMS.md`)
- Visual representation with Mermaid.js
- Architecture diagrams
- Flow charts
- Sequence diagrams
- Entity relationships
### 3. Mermaid Diagram Guidelines
**Always use Mermaid.js** for diagrams (renders in GitHub, VS Code, most markdown viewers):
```mermaid
graph TD
A[Start] --> B{Decision}
B -->|Yes| C[Action 1]
B -->|No| D[Action 2]
```
**Diagram types to use:**
- `graph TD` - Top-down flowcharts
- `sequenceDiagram` - API/interaction flows
- `erDiagram` - Database schemas
- `journey` - User journeys
- `stateDiagram-v2` - State machines
- `gantt` - Timelines/roadmaps
See [references/mermaid_examples.md](references/mermaid_examples.md) for templates
## Workflows
### Workflow 1: Create Summary from AI Doc
**Input:** Path to AI documentation file (e.g., `ai/architect/app/02_BACKEND_REQUIREMENTS.md`)
**Process:**
1. Read AI documentation thoroughly
2. Identify the 20% most crucial information
3. Create executive summary (2-3 paragraphs)
4. Extract key points (5-10 bullets)
5. Add quick reference table
6. Save to parallel location in `docs/` with `_SUMMARY.md` suffix
**Output:** `docs/architect/app/02_BACKEND_REQUIREMENTS_SUMMARY.md`
**Template:** [assets/templates/summary_template.md](assets/templates/summary_template.md)
### Workflow 2: Create Quick Start Guide
**Input:** Path to AI documentation file
**Process:**
1. Read AI documentation
2. Identify "getting started" path
3. Create step-by-step instructions (numbered)
4. Add code snippets/commands
5. Include success criteria
6. Add "Next steps" section
7. Save to parallel location with `_QUICKSTART.md` suffix
**Output:** `docs/architect/app/02_BACKEND_REQUIREMENTS_QUICKSTART.md`
**Template:** [assets/templates/quickstart_template.md](assets/templates/quickstart_template.md)
### Workflow 3: Create Visual Diagrams
**Input:** Path to AI documentation file OR topic description
**Process:**
1. Read AI documentation
2. Identify visualizable concepts:
- System architecture
- Data flow
- User journeys
- Database schemas
- Decision trees
3. Create Mermaid diagrams (2-5 diagrams)
4. Add explanatory text for each diagram
5. Save to parallel location with `_DIAGRAMS.md` suffix
**Output:** `docs/architect/app/02_BACKEND_REQUIREMENTS_DIAGRAMS.md`
**Template:** [assets/templates/diagrams_template.md](assets/templates/diagrams_template.md)
### Workflow 4: Batch Process Entire Folder
**Input:** Path to AI documentation folder (e.g., `ai/architect/app/`)
**Process:**
1. List all markdown files in folder
2. For each file, determine best format(s):
- Architecture docs → SUMMARY + DIAGRAMS
- Implementation guides → QUICKSTART
- Specifications → SUMMARY + DIAGRAMS
3. Create human docs in parallel structure
4. Generate index README for `docs/` folder
5. Report completion summary
**Output:** Complete `docs/` folder structure
### Workflow 5: Update Existing Human Docs
**Input:** Path to updated AI documentation
**Process:**
1. Check if human doc already exists in `docs/`
2. If exists, compare modification dates
3. If AI doc is newer, regenerate human doc
4. Preserve any manual additions (check for "Manual:" markers)
5. Save updated human doc
**Output:** Updated human documentation
## Document Format Standards
### SUMMARY Format
```markdown
# [Original Title] - Summary
**Source:** Link to AI doc
**Last Updated:** Date
**Read Time:** X minutes
## Executive Summary
[2-3 paragraphs capturing essence]
## Key Points
- Point 1
- Point 2
- Point 3
## Quick Reference
| Aspect | Detail |
|--------|--------|
| Key 1 | Value |
## When to Read Full Doc
- Scenario 1
- Scenario 2
[Link to full documentation]
```
### QUICKSTART Format
```markdown
# [Topic] Quick Start
**Time to complete:** X minutes
**Prerequisites:** List
## Step 1: [Action]
[Instructions + code/commands]
## Step 2: [Action]
[Instructions + code/commands]
## Success Criteria
✅ Checklist item
✅ Checklist item
## Next Steps
- Link to detailed docs
- Related quick starts
## Troubleshooting
**Issue:** Description
**Fix:** Solution
```
### DIAGRAMS Format
```markdown
# [Topic] Visual Guide
**Source:** Link to AI doc
## Overview Diagram
```mermaid
[diagram code]
```
**Explanation:** What this diagram shows
## [Specific Aspect] Diagram
```mermaid
[diagram code]
```
**Explanation:** What this diagram shows
## Legend
- Symbol → Meaning
```
## Integration with Other Skills
**Use with architect skill:**
- Architect creates detailed specs in `ai/architect/`
- Human-docs creates summaries in `docs/architect/`
**Use with business skill:**
- Business creates use cases in `ai/business/`
- Human-docs creates executive summaries
**Use with executive skill:**
- Executive defines strategy
- Human-docs creates visual roadmaps
**Use with cleanup skill:**
- Cleanup organizes `ai/` folder
- Human-docs regenerates `docs/` structure
## Quality Standards
**Every human doc must have:**
✅ **Clarity** - Understandable without reading AI doc
✅ **Conciseness** - 20% or less of original length (summaries)
✅ **Actionable** - Clear next steps
✅ **Visual** - At least 1 diagram for complex topics
✅ **Navigable** - Links to source and related docs
✅ **Dated** - Last updated timestamp
**Minimum quality threshold: 8/10**
## File Naming Conventions
```
AI doc: ai/folder/FILE.md
Summary: docs/folder/FILE_SUMMARY.md
Quickstart: docs/folder/FILE_QUICKSTART.md
Diagrams: docs/folder/FILE_DIAGRAMS.md
```
**Never:**
- Create files in `ai/` (only read froRelated in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.