Install
$ agentstack add skill-sergekostenchuk-ui-ux-agent-skill-system-figma-context-reader ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Figma Context Reader
Use this skill to turn Figma context into an evidence-backed design brief. This is a read-only skill; route mutations to figma-canvas-editor or figma-design-system-sync.
Modes
frame-brief: summarize a selected frame or page.component-brief: summarize components, variants, props, and constraints.token-brief: summarize variables, styles, color roles, spacing, radius, typography, and effects.audit-input: collect enough Figma evidence forux-audit-skillordesign-critic-skill.handoff: prepare context for implementation specialists.
Workflow
- Confirm the input type: Figma URL, selected node, file key, screenshot/export, or connected MCP selection.
- Apply
../../shared/privacy-policy.md. - If a
use_figmacall is needed, first invoke the installedfigma:figma-useskill. - Read only the needed nodes, variables, components, styles, and assets. Avoid broad file scans unless the user asks for library/system work.
- Produce a structured context brief with evidence labels. Distinguish direct Figma metadata from visual inference.
- If MCP access is unavailable, ask for an export, screenshot, node metadata, or manual Figma details as fallback.
Output Shape
Use [assets/context-brief-template.md](assets/context-brief-template.md).
Evidence Rules
Figma metadata: node names, type, layout fields, variables, styles, component names, asset references.Visual inference: hierarchy, attention, density, likely intent, visual polish.Missing: anything not available from the current Figma context.
Do not claim DOM, runtime behavior, accessibility scan, or implementation evidence from Figma context alone.
Validation And Eval
- Check that the final brief names the evidence source and privacy mode.
- Check that every implementation claim is traceable to Figma metadata, visual inference, or an explicit missing-context note.
- Use
evals/evals.jsonfor forward tests that distinguish connected Figma context from screenshot-only input.
Resources
- Read
$CODEX_SKILLS_DIR/senior-figma-orchestrator/references/figma-mcp-compatibility.mdwhen tool availability is unclear. - Use [assets/context-brief-template.md](assets/context-brief-template.md) for reports.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: sergekostenchuk
- Source: sergekostenchuk/ui-ux-agent-skill-system
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.