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
  • Authors
  • 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.

ProTermsPrivacyRefunds
Back to skills

Mind Structure And Exposition

ASecurity

Use when organizing a Mind article so the argument unfolds in the clearest possible order within the ~8,000-word limit. The job is architecture, not prose polish — a roadmap, the right order of premises, signposting, and a conclusion that claims exactly what was earned. Structures the paper; it does not write the sentences (see mind-writing-style).

1,052 stars
0 votes
0 copies
0 views
Added 6/6/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 6/6/2026

Install to Claude Code

$npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill mind-structure-and-exposition --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mind Structure And Exposition?

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

Security grade badge for Mind Structure And Exposition
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-mind-structure-and-exposition/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-mind-structure-and-exposition)

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

Download with Pro
Files
SKILL.md
---
name: mind-structure-and-exposition
description: Use when organizing a Mind article so the argument unfolds in the clearest possible order within the ~8,000-word limit. The job is architecture, not prose polish — a roadmap, the right order of premises, signposting, and a conclusion that claims exactly what was earned. Structures the paper; it does not write the sentences (see mind-writing-style).
---

# Structure & Exposition (mind-structure-and-exposition)

A Mind reader should never be lost about **what is being claimed, why, and where they are**. A strong
argument poorly arranged reads as confused; the same argument well arranged reads as inevitable. This
skill is about **architecture** — the order in which the thesis, premises, objections, and replies
appear — within the **~8,000-word** article limit. (Sentence-level polish is `mind-writing-style`.)

## When to trigger

- The argument is sound but the draft "wanders" or reviewers "can't find the thesis"
- Deciding the order of sections, and where objections should go
- Over the word limit and needing to cut structurally, not just trim words
- Writing the introduction's roadmap or the conclusion

## A reliable shape for a Mind article

1. **Introduction** — state the **thesis** and why it matters in the opening paragraphs; sketch the
   argument; give a short roadmap. A Mind reader should know your claim by the end of page one.
2. **Setup** — fix terminology and the target view (from `mind-literature-positioning` and
   `mind-conceptual-analysis-and-method`) only as far as the argument needs.
3. **The argument** — present the premises in the order that makes the inference feel forced; defend
   the load-bearing premise where the reader most needs it.
4. **Objections and replies** — place each objection where it naturally arises, or gather them in a
   dedicated section. Answer the strongest one visibly (see `mind-objections-and-replies`).
5. **Conclusion** — restate what was **established** (and only that), note scope, and gesture at the
   upshot. Do not introduce a new argument here.

## Exposition discipline

- **Front-load the thesis.** Do not make the reader excavate it. The contribution belongs in the intro.
- **One idea per section; signpost transitions.** Say what each section does before doing it.
- **Order premises for the reader, not the discovery.** The sequence in which you *found* the argument
  is rarely the clearest sequence to *present* it.
- **Put objections where they bite,** not all dumped at the end as an afterthought.
- **Move the inessential out.** Long ancillary proofs or tangents can go to a footnote or appendix —
  but the **core argument must stand in the main text**.

## Fit the ~8,000-word limit

- Cut throat-clearing, literature dumps, and re-explanation of well-known views.
- Each paragraph should advance the argument; delete any that only decorates it.
- Tighten or fold footnotes — digressive notes are where word budgets quietly bleed.
- If still over, the cut is usually a **second, weaker argument** for the same thesis: keep the best one.

## Anti-patterns

- A thesis that surfaces only on page 6
- Sections that summarize the literature without advancing the argument
- All objections quarantined in a final section, disconnected from where they arise
- A conclusion that introduces a brand-new claim or overstates what was shown
- Padding to look comprehensive while drifting over the word limit

## Output format

```
【Thesis located in intro?】[Y/N]
【Section map】intro → setup → argument → objections/replies → conclusion (adapted)
【Premise order】clearest for the reader? [Y/N]
【Objections placed where they bite?】[Y/N]
【Within ~8,000 words?】[Y/N] — what to cut
【Next】mind-writing-style
```

## Supplementary resources

- [`../../resources/official-source-map.md`](../../resources/official-source-map.md) — ~8,000-word article limit and accessibility expectation

Attribution

brycewang-stanfordbrycewang-stanford
View sourceMore from brycewang-stanford →
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 that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 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', ...

693161 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 the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 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 →