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

Ahr Argument Development

ASecurity

Use when turning archival findings into a sustained historical argument for The American Historical Review (AHR). The AHR rewards a clear thesis that earns its claims from evidence while remaining alert to contingency and complexity. Builds the argument and its stakes; it does not gather new sources or fabricate evidence.

1,052 stars
0 votes
0 copies
1 views
Added 6/4/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 6/4/2026

Install to Claude Code

$npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill ahr-argument-development --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ahr Argument Development?

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

Security grade badge for Ahr Argument Development
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-ahr-argument-development/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-ahr-argument-development)

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

Download with Pro
Files
SKILL.md
---
name: ahr-argument-development
description: Use when turning archival findings into a sustained historical argument for The American Historical Review (AHR). The AHR rewards a clear thesis that earns its claims from evidence while remaining alert to contingency and complexity. Builds the argument and its stakes; it does not gather new sources or fabricate evidence.
---

# Argument Development (ahr-argument-development)

The AHR publishes **arguments**, not chronicles. A pile of well-researched facts is not yet an article;
an article advances a **thesis** — a contestable claim about the past — and earns it from primary
evidence while honoring historical contingency. This skill turns "here is what happened" into "here is
what it means and why it matters."

## When to trigger

- You have rich material but cannot state your thesis in a sentence
- The draft narrates events without making a claim
- A reader said the piece is "descriptive," "all background," or "doesn't add up to anything"
- The argument over-claims (too clean) or under-claims (buried, hedged into nothing)

## Building the argument

1. **State the thesis as a contestable claim.** A sentence a competent historian could disagree with.
   If no one could disagree, it is description, not argument.
2. **Make the stakes explicit.** Why does this claim matter for how we understand the period, place,
   or process? Tie back to the historiographical intervention (`ahr-historiography-positioning`).
3. **Build the chain of evidence.** Each major claim is supported by specific primary sources, read
   critically (`ahr-sources-and-archives`). Show the reader the evidence, do not just assert.
4. **Argue against the strongest alternative.** Name the rival explanation a skeptical reader would
   raise and show why your reading is better — not by ignoring counter-evidence but by accounting for it.
5. **Respect contingency and scale.** Resist determinism and anachronism; mark what is contingent,
   what is structural, and the limits of what your sources can bear.
6. **Hold narrative and analysis together.** The AHR prizes work that *tells a story and argues a
   point at once* — chronology in service of a claim (hand off to `ahr-structure-and-exposition`).

## Calibrating claims

- **Over-claiming:** universalizing from a single case, ignoring counter-evidence, smoothing away
  complexity. Fix by stating scope conditions.
- **Under-claiming:** hedging until the thesis disappears; "this paper explores…". Fix by committing
  to a claim and defending it.

## Anti-patterns

- A thesis no one could dispute (description in argument's clothing)
- Letting the chronology substitute for an argument
- Evidence that illustrates rather than tests the claim
- Ignoring the obvious counter-reading a reviewer will raise
- Anachronistic categories imposed on actors who did not share them

## Output format

```
【Thesis】one contestable sentence
【Stakes】why it matters beyond the case
【Evidence chain】claim → primary sources that earn it (per major move)
【Strongest counter-reading】and your answer
【Scope conditions】what the argument does and does not cover
【Next】ahr-sources-and-archives
```

## Supplementary resources

- [`../../resources/external_tools.md`](../../resources/external_tools.md) — note-taking and source-organization tools
- [`../../resources/official-source-map.md`](../../resources/official-source-map.md) — AHR article scope and significance bar

Attribution

brycewang-stanfordbrycewang-stanford
View sourceMore from brycewang-stanford →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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".

1074701 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.

691 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 →