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 Thesis And Argument

ASecurity

Use when building the central argument of a Mind article — stating a sharp thesis and constructing a valid, sound argument for it. This is the core of an analytic-philosophy paper: explicit premises, a valid inference to the conclusion, and defensible premises. Structures the argument; it does not generate the philosophical content for you.

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

Security Analysis

A100/100

Scanned 6/6/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Mind Thesis And Argument?

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

Security grade badge for Mind Thesis And Argument
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-mind-thesis-and-argument/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-mind-thesis-and-argument)

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

Download with Pro
Files
SKILL.md
---
name: mind-thesis-and-argument
description: Use when building the central argument of a Mind article — stating a sharp thesis and constructing a valid, sound argument for it. This is the core of an analytic-philosophy paper: explicit premises, a valid inference to the conclusion, and defensible premises. Structures the argument; it does not generate the philosophical content for you.
---

# Thesis & Argument (mind-thesis-and-argument)

At Mind the paper *is* the argument. A finding, an intuition, or a clever example is not yet a
contribution until it is the conclusion of an **argument the reader is rationally compelled to take
seriously**: a sharp thesis, explicit premises, a valid inference, and premises that survive scrutiny.
This skill turns an idea into that argument.

## When to trigger

- You have an intuition or insight but not yet a stated thesis
- A reader said the paper is "suggestive" but "doesn't actually argue for the claim"
- You need to lay out premises and check that the conclusion really follows
- The argument feels strong but you cannot say which premise does the work

## Build the argument

1. **State the thesis.** One sentence, in the strongest defensible form. It must be **deniable** — a
   competent peer could reject it. If no one could disagree, it is not a thesis.
2. **Make the argument explicit.** Write the premises and the conclusion as numbered steps. The
   reader should see exactly **which claims**, taken together, yield the thesis.
3. **Check validity.** Does the conclusion *follow* from the premises? If there is a gap, name the
   hidden premise and add it — then defend it (a suppressed premise is where papers die).
4. **Check soundness.** Are the premises **true / defensible**? For each premise, give the supporting
   reason, distinction, or example. The most contestable premise needs the most support.
5. **Identify the load-bearing premise.** Say which premise the whole argument turns on. That is where
   objections will land (hand to `mind-objections-and-replies`), so defend it hardest.
6. **Calibrate the conclusion.** Claim exactly what the argument earns — no more. State **scope and
   qualifications** explicitly; an overclaim invites a cheap refutation.

## Forms of argument Mind accepts

- **Deductive** — premises entail the conclusion; the work is defending the premises.
- **Counterexample** — a single clear case refutes a universal claim; make the case undeniable.
- **Inference to the best explanation** — your thesis explains the data of the debate better than rivals; show the comparison.
- **Reductio / dilemma** — derive an unacceptable consequence from the opposing view, or trap it between two bad options.
- **Transcendental / presupposition** — show the opponent's position presupposes your conclusion.

Where any of these uses formal apparatus, **accompany it with informal exposition** so a non-specialist
philosopher can follow the move (a Mind expectation).

## Anti-patterns

- A thesis no one could deny (a truism dressed as a discovery)
- Asserting the conclusion instead of arguing to it ("clearly, …")
- An invalid step papered over by rhetoric — find the missing premise
- The load-bearing premise stated but never defended
- Overclaiming scope, then being refuted by an easy counterexample

## Output format

```
【Thesis】one deniable sentence
【Argument】numbered premises → conclusion
【Form】deductive / counterexample / IBE / reductio / dilemma / transcendental
【Validity】does the conclusion follow? hidden premise named? [Y/N]
【Load-bearing premise】the one to defend hardest
【Scope】qualifications / where the claim stops
【Next】mind-objections-and-replies
```

## Supplementary resources

- [`../../resources/external_tools.md`](../../resources/external_tools.md) — argument-mapping and logic/proof tools
- [`../../resources/official-source-map.md`](../../resources/official-source-map.md) — Mind expectation of accessible argument with informal exposition

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 →