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

Define

ASecurity

Interview to define document audience, purpose, and Diataxis type — Phase 1 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 define --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Define?

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

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

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

Download Zip
Files
SKILL.md
---
description: Interview to define document audience, purpose, and Diataxis type — Phase 1 of the document writing workflow
---

# Define Document Audience & Purpose

Phase 1 of the document writing workflow. Conduct a focused interview to produce the audience-purpose statement that governs all downstream writing decisions.

**Document topic**: $ARGUMENTS

## Interview Protocol

Ask these questions in sequence. Wait for answers after each. Do not ask multiple questions at once.

### Question 1 — Reader Role
"Who is the primary reader? What is their role (developer, manager, end user, teammate, etc.) and their knowledge level relative to *this specific topic* — not their general expertise?"

### Question 2 — Reader Goal
"What does the reader need to accomplish after reading this? Pick the specific outcome:
- Complete a task they couldn't do before
- Learn a skill by doing it
- Look up a specific fact or value
- Understand *why* something works the way it does"

### Question 3 — Reader Gap
"What does the reader NOT know that you do? What's the curse-of-knowledge risk — what assumptions are you tempted to make that the reader can't share?"

### Question 4 — Scope Boundary
"What is explicitly out of scope? What will this document *not* cover, even if it's related?"

### Question 5 — Type Confirmation (Diataxis)
Based on answers 1–4, propose the best Diataxis type and confirm:

| Type | Reader state | Writer's job | Wrong when... |
|---|---|---|---|
| **Tutorial** | Doesn't know what they don't know | Guide by doing | Explaining instead of showing |
| **How-to** | Knows goal, needs path | Steps only, no context | Including background the reader didn't ask for |
| **Reference** | Needs exact answer | Complete, accurate, scannable | Writing prose instead of entries |
| **Explanation** | Wants to understand why | Context, tradeoffs, mental models | Embedding instructions |

Say: "Based on what you've described, this sounds like a [type] because [one reason]. Does that match what you're trying to write?"

## Output: Audience-Purpose Statement

After all answers, produce this artifact:

```
Document: [title or working title]
Type: [Diataxis type]

Audience: A [reader role] with [knowledge level relative to this topic]
Goal: reads this to [specific, concrete outcome]
Assumed knowledge: [2–4 things the reader already knows]
Not covered: [explicit scope boundary]

Test question: "A [reader role] with [knowledge level] reads this to [outcome] — can they do that after reading it?"
```

Print the completed statement. Ask: "Should I save this to `doc_plans/<topic>/audience-purpose.md`?"

If yes, save it there.

## Next Step

Run `/docs:outline` with this statement as input to generate the document skeleton.

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.

3351 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 →