Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/ahr-argument-development
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.
Passed 20 of 22 test cases with the skill, and 13 of 22 without it.
and 9 more in the full report
7 fixed13 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
My manuscript analyzes 17th-century Venetian guild trial transcripts, but right now the opening just hedges with 'this paper explores apprentice disputes.' Can you help me rebuild this into a sharp argument framework? Please output a single-sentence disputable claim, explain why these findings matter to scholars outside Venetian history, construct a step-by-step chain linking claims to specific archival sources, identify the top rival explanation along with a counter-rebuttal, define the scope limits of the argument, and state what step to take next.
| Checked | Without skill | With skill |
|---|---|---|
| Includes the tag 【Stakes】 | Missed | Passed |
| Includes the tag 【Scope conditions】 | Missed | Passed |
| Lists ahr-sources-and-archives under the Next section | Missed | Passed |
The instructions your model reads when the skill loads.
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."
ahr-historiography-positioning).ahr-sources-and-archives). Show the reader the evidence, do not just assert.ahr-structure-and-exposition).test cases passed, vs 13 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.