Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cnfeat/top-pm-skills --skill figma-design-reviewgit clone --depth 1 https://github.com/cnfeat/top-pm-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cnfeat/top-pm-skills/figma-design-review)<a href="https://agentmods.dev/skills/cnfeat/top-pm-skills/figma-design-review"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/figma-design-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cnfeat/top-pm-skills/figma-design-review"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/figma-design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.00696 |
| Opus 5 | $0.00035 | $0.00348 |
| Sonnet 5 | $0.00014 | $0.00139 |
| Haiku 4.5 | $0.00007 | $0.00070 |
Grade A, and why
figma-design-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma Design Review Skill
Runs a structured PM design review — checking that a design meets product requirements, covers all user flows, and is ready for engineering. This is a requirements-and-outcomes review, not an aesthetic critique.
Required Inputs
- Design description or screen summary
- Original requirements (PRD snippet, ticket, or acceptance criteria)
- User flow being designed
- Review stage (concept / mid-fidelity / pre-handoff final)
Output Structure
1. Review Header
Feature, review stage, reviewed by, date. Overall status: Approved / Approved with changes / Needs revision
2. Requirements Coverage Check
| Requirement | Covered? | Notes |
|---|---|---|
| [Requirement from PRD] | Yes/No/Partial | [Specific observation] |
Missing coverage summary: [Requirements not addressed — must resolve before approval]
3. User Flow Completeness
| Flow step | Designed? | Issues |
|---|---|---|
| [Step] | Yes/No/Partial | [Issue] |
| Error state | Yes/No | |
| Empty state | Yes/No | |
| Loading state | Yes/No |
4. PM Concerns
[Concern] — Blocking / Should fix / Nice to fix
- What: [Specific observation]
- Why it matters: [Business or user impact — not aesthetic preference]
- Suggested resolution: [What PM wants to see]
5. Open Questions
| Question | Owner | Needed by |
|---|---|---|
| [Question] | Designer/Eng/PM | [Date] |
6. Approval Decision
Approved / Approved with changes (list) / Needs revision (focus area + next review date)
Quality Checks
- Every requirement assessed
- All flow states checked (error, empty, loading)
- Concerns are outcome-focused not aesthetic
- Open questions have owners
- Approval status is explicit
Anti-Patterns
- Do not review a design without a list of requirements to check against — always ask for the PRD, design brief, or acceptance criteria first
- Do not give a vague approval status — the decision must be explicitly "approved", "approved with conditions", or "not approved"
- Do not conflate requirements gaps with UX concerns — track them separately so engineers and designers can act independently
- Do not raise concerns without suggesting what information is needed to resolve them
- Do not skip open questions — unresolved assumptions at review time become bugs after engineering handoff
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 76 lines · 70 tokens per session scan A 8e6504604714
figma-design-review is a skill published in the GitHub repository cnfeat/top-pm-skills (48 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 696 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.