Skip to content
Agentmart
Submit a tool

nongeneric-critique

Unanchored Dual-Persona Design & Motion Critique skill.

Skill by codewithasnari

IndexedMIT★ 9
Write a review

Chalk Labs

Need help deploying nongeneric-critique?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/codewithasnari-nongeneric-critique

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Unanchored Dual-Persona Design & Motion Critique skill. Evaluates any UI surface cold from both a Design Director perspective (5-pillar 0-100 scorecard) and a Skeptical Target Visitor perspective, followed by a prioritized P0-P3 remediation plan.

Use cases: design

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/nongeneric-critique

What's inside

Skill name
nongeneric-critique
Description
Unanchored Dual-Persona Design & Motion Critique skill. Evaluates any UI surface cold from both a Design Director perspective (5-pillar 0-100 scorecard) and a Skeptical Target Visitor perspective, followed by a prioritized P0-P3 remediation plan.
License
MIT
Instructions
20 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# NonGeneric Dual-Persona Critique

When asked to critique, review, or audit a UI:

1. **Inspect the Surface Cold**:
   Follow `../nongeneric/references/browser-verification.md` and inspect rendered evidence before reading the builder's rationale or static score. Mark unavailable evidence as not verified.
2. **Run the Deterministic Audit**:
   ```bash
   node scripts/nongeneric.js audit <target>
   ```
   This is a static-check score, not a visual or usability grade.
3. **Execute Unanchored Dual-Persona Evaluation**:
   - **Persona 1 (Design & Motion Director)**: Use `../nongeneric/references/restrained-design.md`; do not penalize intentional stillness or one-family typography. Grade Typography (20), OKLCH Color & Atmosphere (20), Spatial Rhythm & 320px Responsive (20), Motion Appropriateness & Interaction Feedback (20), and Copy Authenticity & Task Fit (20).
   - **Persona 2 (Skeptical Target Visitor)**: Evaluate according to Visitor Mode: offer and proof for persuade, task completion for operate, comprehension for read, participation and exit for experience. Execute the primary task and a relevant recovery path; report observed outcomes. This is expert review, not user research.
4. **Output Prioritized P0–P3 Remediation Plan**:
   - Follow the impact-based severity rules in `../nongeneric/references/critique-and-finish.md`. Task blockers, lost work, and false completion take priority over visual polish; keep these review priorities separate from CLI rule severities.
   - List exact file:line locations and concrete code replacements for every P0 and P1 issue.
   - Separate static findings from rendered observations. Include viewport/state coverage and unverified dimensions. Do not assign a visual score without rendered evidence.

From codewithasnari/nongeneric, MIT.

Signals

Stars
9
Forks
0
Open issues
0
Last commit (this folder)
Oct 21, 2026 (9 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from codewithasnari

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get nongeneric-critique running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying nongeneric-critique?

CallGet help
Cite this page

nongeneric-critique skill. Agent Mart. https://agentmart.dev/skills/codewithasnari-nongeneric-critique (last updated 2026-10-24)