Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Outline

ASecurity

Generate document skeleton from audience-purpose statement using Diataxis type patterns — Phase 2 of the document writing workflow

8 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add tstapler/dotfiles --skill outline --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Outline?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Outline
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tstapler-outline-dotfiles/badge)](https://www.skillsdirectory.com/skills/tstapler-outline-dotfiles)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
description: Generate document skeleton from audience-purpose statement using Diataxis type patterns — Phase 2 of the document writing workflow
---

# Generate Document Outline

Phase 2 of the document writing workflow. Generate a document skeleton based on the audience-purpose statement produced by `/docs:define`.

**Input**: $ARGUMENTS (audience-purpose statement inline, or path to audience-purpose.md)

If no input provided, ask: "What is the document type and who is it for? (Run `/docs:define` first for a guided interview.)"

## Structural Patterns by Diataxis Type

Use the declared type to select the correct skeleton. Do not mix patterns.

### Tutorial
```
# [Title: "Build/Create/Learn X"]

> What you'll accomplish: [concrete, checkable outcome — not "you'll learn about X"]

## Prerequisites
- [Specific item the reader must have or know — checkable]
- [Another prerequisite]

## Step 1: [Imperative verb] [specific action]
[placeholder: what happens here]

## Step 2: [Imperative verb] [specific action]
[placeholder]

## (repeat steps — each step does exactly one thing)

## Verify it works
[placeholder: what success looks like — specific, testable]

## What's next
[placeholder: links to related how-tos or deeper explanation]
```

### How-to
```
# [Title: "[Verb phrase] — e.g. 'Configure X for Y'"]

## Prerequisites
- [Only what's actually required — nothing informational]

## Steps

1. [Imperative verb] [specific action]
2. [Imperative verb] [specific action]
3. (continue)

## Result
[placeholder: what the completed state looks like]
```
Note: No background sections. No explanation. Steps only.

### Reference
```
# [Entity name]

[One sentence: what this is.]

## [Property/Parameter/Field name]

**Type**: [type]
**Default**: [value or "none"]
**Description**: [one sentence]
**Example**: [minimal working example]
**Constraints**: [edge cases, if any]

## (repeat entry structure for each item)
```
Note: No narrative prose. Every entry uses the same structure.

### Explanation
```
# [Title: "How/Why/What [concept] works"]

## What this is
[placeholder: definition without jargon — one paragraph]

## The problem it solves
[placeholder: the context that makes this concept necessary]

## How it works
[placeholder: mechanism — not instructions, understanding]

## [Key concept] vs. [adjacent concept]
[placeholder: where the boundary is and why it exists]

## Tradeoffs and constraints
[placeholder: when this approach wins, when it loses]

## When to use this / when not to
[placeholder: decision criteria]

## Further reading
[placeholder: links to related tutorials, how-tos, or reference — not summaries]
```

## Output

1. Print the skeleton with section headers filled in (not placeholders — real section titles based on the content)
2. Annotate each section: one-line note on what goes there
3. Add at the top: `Type: [Diataxis type] | Estimated length: ~[N × 200] words`
4. Flag any section that risks type mixing (e.g., explanation creeping into a how-to)

Ask: "Should I save this to `doc_plans/<topic>/outline.md`?"

## Next Step

Run `/docs:draft` with this outline as input to write the document.

Attribution

tstaplertstapler
View sourceMore from tstapler →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →