spec-compare — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited spec-compare (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Compare a DTCG (W3C Design Token Community Group) JSON spec against Figma Library variables. Categorizes differences and recommends sync actions. Pairs with token-sync for the actual sync step.
reverse_sync_tokens directly after load_toolset("tokens").ping → verify plugin connectionIf `ping` fails (plugin not connected): STOP. Do not fall back to other MCP servers. Tell user: open Figma → Plugins → FigCraft → wait for connection, then retry.
Ask the user for the DTCG JSON file path (e.g., tokens/design-tokens.json).
load_toolset("tokens") → enable DTCG token toolslist_tokens(filePath: "...") → parse and preview DTCG tokensOptional: filter by type (e.g., type: "color") to focus on specific token categories.
diff_tokens(filePath: "...", collectionName: "...") → compare DTCG vs Figma variablesReturns tokens categorized as:
Present a structured diff report:
📊 Token Comparison:
- In-sync: X tokens
- DTCG-ahead: Y tokens (DTCG has updates)
- Figma-ahead: Z tokens (Figma has updates)
- Missing in Figma: N tokens
- Missing in DTCG: M tokensRecommend actions for each category:
sync_tokens to push DTCG values to Figmareverse_sync_tokens to export Figma values to DTCG, or update DTCG manuallysync_tokens to create new variablesAsk the user if they want to sync to resolve differences. If yes, hand off to the token-sync workflow.
spec-compare → token-sync
(audit) (sync)Run spec-compare first to understand the gap, then token-sync to resolve it.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.