ogt-docs-create

0
1
Source

Create new documentation entities in the docs-first system. Routes to specialized creation sub-skills for tasks, definitions, rules, features, and social content. Use when adding any new documentation.

Install

mkdir -p .claude/skills/ogt-docs-create && curl -L -o skill.zip "https://mcp.directory/api/skills/download/5580" && unzip -o skill.zip -d .claude/skills/ogt-docs-create && rm skill.zip

Installs to .claude/skills/ogt-docs-create

About this skill

OGT Docs - Create

Root skill for creating new documentation entities.

Overview

This skill routes to specialized creation workflows based on what type of document you're creating. Every entity becomes a folder with appropriate files and signals.

flowchart TB
    CREATE["ogt-docs-create"] --> TASK["ogt-docs-create-task"]
    CREATE --> DEF["ogt-docs-define"]
    CREATE --> RULE["ogt-docs-rules"]
    CREATE --> SOCIAL["ogt-docs-create-social"]
    CREATE --> CHANGE["ogt-docs-changelog"]

    TASK --> |folder| PENDING["docs/todo/pending/"]
    DEF --> |folder| DEFINE["docs/define/"]
    RULE --> |folder| RULES["docs/rules/"]
    SOCIAL --> |folder| CONTENT["docs/content/"]
    CHANGE --> |file| CHANGELOG["CHANGELOG.md"]

When to Use

  • Creating new tasks
  • Adding definitions (features, code, business, etc.)
  • Establishing new rules
  • Creating social/marketing content
  • Updating changelog

Quick Reference

CreatingSub-SkillTarget
Taskogt-docs-create-taskdocs/todo/pending/
Featureogt-docs-define-featuredocs/define/features/
Business defogt-docs-define-businessdocs/define/business/
Code defogt-docs-define-codedocs/define/code/
Marketing defogt-docs-define-marketingdocs/define/marketing/
Branding defogt-docs-define-brandingdocs/define/branding/
Tool docogt-docs-define-toolsdocs/define/tools/
Code ruleogt-docs-rules-codedocs/rules/code/
Git ruleogt-docs-rules-gitdocs/rules/git/
Social postogt-docs-create-socialdocs/content/social/
Changelogogt-docs-changelogCHANGELOG.md

Creation Workflow

All creation follows the same pattern:

flowchart LR
    A[Identify Type] --> B[Create Folder]
    B --> C[Copy Template]
    C --> D[Fill Content]
    D --> E[Add Signals]
    E --> F[Verify Structure]

Step 1: Identify Type

Determine what you're creating:

If you need to...Create a...Location
Track work to doTaskdocs/todo/pending/
Document a product featureFeaturedocs/define/features/
Document code architectureCode definitiondocs/define/code/
Establish coding standardCode ruledocs/rules/code/
Record what changedChangelog entryCHANGELOG.md

Step 2: Create Folder

# Use slug format: lowercase, hyphens, no spaces
mkdir -p docs/{section}/{category}/{slug}

# Examples
mkdir -p docs/todo/pending/user-auth-flow
mkdir -p docs/define/features/dark-mode
mkdir -p docs/rules/code/error-handling

Step 3: Copy Template

# Copy appropriate template
cp docs/_templates/{type}.md docs/{path}/{slug}/{type}.md

# Examples
cp docs/_templates/task.md docs/todo/pending/user-auth-flow/task.md
cp docs/_templates/feature.md docs/define/features/dark-mode/feature.md
cp docs/_templates/rule.md docs/rules/code/error-handling/rule.md

Step 4: Fill Content

Edit the template with actual content. See sub-skill documentation for required sections.

Step 5: Add Signals

# Common signals
echo '{"schema": "1.0", "created": "'$(date -Iseconds)'"}' > {folder}/.version

# Type-specific signals
echo "high" > docs/todo/pending/{task}/.priority
touch docs/rules/code/{rule}/.enforced_by

Step 6: Verify Structure

# Verify folder has required files
ls -la docs/{path}/{slug}/

# Expected output example for task:
# task.md
# .version
# .priority

Templates Overview

Task Template

# Task: {Title}

## Summary

{What and why}

## Objectives

- Objective 1
- Objective 2

## Acceptance Criteria

- [ ] Criterion 1
- [ ] Criterion 2

## Dependencies

{None or list}

## Estimated Effort

{Size} ({time})

Feature Template

# Feature: {Name}

## Summary

{What the feature does}

## User Stories

As a {user}, I want to {action}, so that {benefit}.

## Scope

### In Scope

- Item 1

### Out of Scope

- Item 1

## Success Metrics

- Metric 1

Definition Template

# {Name}

## Summary

{One paragraph}

## Details

{Full explanation}

## Examples

{Examples}

## Related

- {Links}

Rule Template

# Rule: {Name}

## Summary

{One sentence}

## Rationale

{Why}

## The Rule

{MUST/SHOULD/MAY statements}

## Examples

### Correct

{example}

### Incorrect

{example}

## Enforcement

{How enforced}

Batch Creation

Create multiple related items at once:

#!/bin/bash
# create-feature-with-tasks.sh

FEATURE=$1

# Create feature definition
mkdir -p docs/define/features/$FEATURE
cat > docs/define/features/$FEATURE/feature.md << EOF
# Feature: $(echo $FEATURE | tr '-' ' ' | sed 's/\b\(.\)/\u\1/g')

## Summary

TODO: Add summary

## User Stories

As a user, I want to TODO, so that TODO.
EOF

# Create initial tasks
for task in "design" "implement" "test" "document"; do
  mkdir -p docs/todo/pending/${FEATURE}-${task}
  cat > docs/todo/pending/${FEATURE}-${task}/task.md << EOF
# Task: $(echo $FEATURE | tr '-' ' ' | sed 's/\b\(.\)/\u\1/g') - $(echo $task | sed 's/\b\(.\)/\u\1/g')

## Summary

${task^} the $FEATURE feature.

## Objectives

- TODO

## Acceptance Criteria

- [ ] TODO
EOF
  echo "medium" > docs/todo/pending/${FEATURE}-${task}/.priority
done

echo "Created feature: $FEATURE"
echo "Created tasks: ${FEATURE}-design, ${FEATURE}-implement, ${FEATURE}-test, ${FEATURE}-document"

Usage:

./create-feature-with-tasks.sh dark-mode

Naming Conventions

Slug Format

All folder names use slug format:

RuleExample
Lowercaseuser-auth not User-Auth
Hyphens for spacesdark-mode not dark_mode
No special charsoauth2 not oauth2.0
Descriptivesteam-oauth-provider not sop
Under 30 charsKeep it readable

Good Names

docs/todo/pending/add-steam-oauth
docs/define/features/dark-mode-toggle
docs/rules/code/no-implicit-any

Bad Names

docs/todo/pending/Add Steam OAuth          # Spaces, caps
docs/define/features/dark_mode_toggle      # Underscores
docs/rules/code/rule1                      # Not descriptive

Validation

After creating any document:

Check Required Files

# Task
test -f docs/todo/pending/{slug}/task.md || echo "MISSING: task.md"
test -f docs/todo/pending/{slug}/.priority || echo "MISSING: .priority"

# Feature
test -f docs/define/features/{slug}/feature.md || echo "MISSING: feature.md"
test -f docs/define/features/{slug}/mvp.md || echo "MISSING: mvp.md"

# Rule
test -f docs/rules/{category}/{slug}/rule.md || echo "MISSING: rule.md"
test -f docs/rules/{category}/{slug}/.enforced_by || echo "MISSING: .enforced_by"

Check Required Sections

# For any markdown file, check for required headings
file=$1
required=("## Summary" "## Objectives" "## Acceptance Criteria")

for section in "${required[@]}"; do
  grep -q "$section" "$file" || echo "MISSING: $section in $file"
done

Common Creation Patterns

New Feature Flow

  1. Create feature definition
  2. Create mvp.md defining scope
  3. Create phase_0.md for initial work
  4. Create tasks for phase_0
# 1. Feature folder
mkdir -p docs/define/features/search

# 2. Feature definition
cat > docs/define/features/search/feature.md << 'EOF'
# Feature: Global Search

## Summary
Fuzzy search across all content types.
EOF

# 3. MVP scope
cat > docs/define/features/search/mvp.md << 'EOF'
# MVP: Global Search

## In MVP
- Phase 0 only

## Definition of Done
- Search returns results in <100ms
- Fuzzy matching works
EOF

# 4. Phase 0
cat > docs/define/features/search/phase_0.md << 'EOF'
# Phase 0: Basic Search

## Deliverables
- MiniSearch integration
- Global search component
EOF

# 5. Tasks
mkdir -p docs/todo/pending/search-minisearch-setup
# ... create task

New Rule Flow

  1. Identify pattern to standardize
  2. Create rule folder
  3. Write rule with examples
  4. Configure enforcement
  5. Announce to team
# 1. Rule folder
mkdir -p docs/rules/code/async-await

# 2. Rule definition
cat > docs/rules/code/async-await/rule.md << 'EOF'
# Rule: Prefer async/await

## Summary
SHOULD use async/await over .then() chains.

## Rationale
Improved readability and error handling.

## The Rule
...
EOF

# 3. Examples
cat > docs/rules/code/async-await/examples.md << 'EOF'
# Examples
...
EOF

# 4. Enforcement
echo "eslint prefer-async-await" > docs/rules/code/async-await/.enforced_by

# 5. Configure ESLint
# Edit .eslintrc.js

Signal Files Quick Reference

SignalUsed ForContent
.versionAllJSON schema version
.priorityTaskscritical/high/medium/low
.enforced_byRulesList of tools
.statusDefinitionsdraft/review/approved
.created_atAllISO timestamp
.created_byAllAuthor name

Creation Checklist

Before finalizing any created document:

  • Folder uses slug format
  • Primary file exists (task.md, feature.md, etc.)
  • .version signal added
  • Required sections present
  • No TODO placeholders remain
  • Links are valid
  • Spelling/grammar checked
  • Related documents cross-referenced

You might also like

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

1,6851,430

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

1,2711,335

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

1,5441,153

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

1,359809

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

1,265728

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

1,495685