critique-argument

Solid

Reviews argumentative prose - essays, proposals, position papers, recommendation memos, strategy docs, and op-eds - against the Toulmin model of argument: whether the claim, grounds, warrant, backing, qualifier, and rebuttal are present, explicit, and actually hold together. Judges the argument's structure, not prose readability or sentence mechanics (critique-clarity covers that). Use when the user asks for a review, feedback, a second opinion, a red-line pass, a quality check, or a critique of whether an argument holds up before it goes out.

AI & Automation 1 stars 0 forks Updated 4 days ago Apache-2.0

Install

View on GitHub

Quality Score: 80/100

Stars 20%
10
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# critique-argument Reviews argumentative prose against the Toulmin model of argument, asking whether a reader can reconstruct why the conclusion follows: is there a single stated claim, is it attached to checkable grounds, is the principle licensing the move from grounds to claim explicit, is that principle itself supported, does the claim's asserted strength match its evidence, and does the argument name the conditions that would defeat it. The full criterion registry, with each criterion's operationalization, operational test, severity anchors, and lane, is `references/TOULMIN.md`. ## Artifact claim This skill critiques **argumentative prose**: essays, proposals, position papers, recommendation memos, strategy documents, op-eds, and any document whose purpose is to get a reader to accept a conclusion. Markdown or plain text. It evaluates the **structure of the argument**, not the truth of its content. Whether the grounds an artifact cites are factually correct, whether a cited study replicates, whether the numbers add up: none of that is a `TOULMIN-*` question, and a finding that turns on it is out of scope. The claim this skill makes is that a reader could or could not reconstruct the argument from what the artifact supplies, and that claim is answerable from the artifact alone. Three criteria (`TOULMIN-BACKING`, `TOULMIN-REBUTTAL`, `TOULMIN-WARRANT`) turn on what a reader would grant without being told, which is the one place this skill could smuggle in knowledge th...

Details

Author
product-on-purpose
Repository
product-on-purpose/critique-skills
Created
3 weeks ago
Last Updated
4 days ago
Language
Python
License
Apache-2.0

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

critique-clarity

Reviews markdown or plain-text prose for clarity against the Federal Plain Language Guidelines and Williams' Style: readability, passive voice, sentence length, and nominalization density. Judges sentence- and passage-level readability, not whether an argument's claim is supported or its structure holds together (critique-argument covers that). Use when the user asks for feedback, a second opinion, a red-line pass, or a quality check on a memo, PRD, proposal, or any prose document before it goes out.

1 Updated 4 days ago
product-on-purpose
Data & Documents Solid

critique-toy

Reviews short markdown field-operations notices, memos, and similar prose documents against the toy TOY-* grammar, covering a passive-voice recast that deletes the actor, a hedging phrase stacked ahead of an otherwise direct statement, and a subheading left with no body before the next heading of equal or higher level. Use when the user asks for a review, feedback, a second opinion, a red-line pass, or a quality check on one of this fixture's worked-example documents. This is the skill template's own committed fixture, not a shipped critique-family skill, and it is never registered in library.json.

1 Updated 4 days ago
product-on-purpose
AI & Automation Solid

critique-usability

Reviews HTML or markdown UI specs, wireframe write-ups, and page mockups against Nielsen's 10 usability heuristics: system status, user control and exits, consistency, error prevention and recovery, recognition over recall, and minimalist design. Judges the interface's flow, controls, and states, not the wording of error or empty-state message text (critique-microcopy covers that), and not conformance against accessibility standards such as contrast or screen-reader access (critique-accessibility covers that). Use when the user asks for a usability review, design feedback, a second opinion, a red-line pass, a heuristic evaluation, or a quality check on a screen, a flow, or an interface spec before it goes to build. Covers static specs and mockups, not live running applications.

1 Updated 4 days ago
product-on-purpose