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-annotation-guidegit 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-annotation-guide)<a href="https://agentmods.dev/skills/cnfeat/top-pm-skills/figma-annotation-guide"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/figma-annotation-guide/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-annotation-guide"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/figma-annotation-guide.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 | $0.00069 | $0.00654 |
| Opus 5 | $0.00034 | $0.00327 |
| Sonnet 5 | $0.00014 | $0.00131 |
| Haiku 4.5 | $0.00007 | $0.00065 |
Grade A, and why
figma-annotation-guide 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 7d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma Annotation Guide Skill
Produces a complete set of developer handoff annotations for a Figma screen or component — the notes that turn a visual design into a buildable spec.
Required Inputs
- Screen or component description (describe or summarise what was designed)
- Platform (iOS / Android / Web / React Native)
- Interaction type (static / interactive / animated / form)
- Developer audience (mobile / frontend / full-stack)
Output Structure
1. Screen/Component Overview
Name, purpose, entry points, exit points.
2. Interaction Annotations
[Element name]
- Default state: [Visual description]
- On tap/click: [Exact action — API call, state change, navigation]
- Loading state: [Description]
- Success state: [What happens after]
- Error state: [What error looks like and user options]
- Disabled condition: [When and why]
3. State Inventory
| Element | States Required |
|---|---|
| [Element] | Default, Hover, Active, Disabled, Loading, Error, Empty |
Flag missing designs: "Warning: Error state not designed — needed before build"
4. Spacing and Layout Notes
Fixed vs fluid elements, scroll behaviour, breakpoints, safe areas.
5. Content and Copy Rules
Character limits, dynamic vs static content, truncation rules, empty states.
6. Accessibility Annotations
Touch targets, screen reader labels, focus order, colour contrast, motion preferences.
7. Edge Cases and Developer Questions
- [Unresolved question for developer to flag]
Quality Checks
- Every interactive element has all states defined
- State inventory flags missing designs
- Accessibility covers touch targets and screen reader labels
- Empty states specified
- Edge cases listed as actionable questions
Anti-Patterns
- Do not annotate only the happy path — error states, loading states, and empty states must all be documented
- Do not use vague spacing descriptions like "some padding" — specify exact pixel values or token names
- Do not skip accessibility annotations — focus order, ARIA labels, and colour contrast ratios must be included
- Do not leave interaction behaviour undescribed — every interactive element needs a documented response
- Do not produce annotations without edge cases — developers need to know what happens at boundaries
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.
- 7d ago First seen · 72 lines · 69 tokens per session scan A 778843425893
figma-annotation-guide is a skill published in the GitHub repository cnfeat/top-pm-skills (48 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 654 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 $ralph 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.