text-replace — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited text-replace (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.
Bulk replace text content across Figma designs. Supports localization, real data filling, and content updates. Works in chunks with visual verification to prevent overflow and truncation.
text(method: "set_range") directly.ping → verify plugin connection
text_scan(nodeId: "...") → discover all text nodes in target frame/pageIf `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.
Categorize discovered text by role:
Group text nodes by proximity (same parent frame = one chunk):
For each chunk:
text(method: "set_content", nodeId: "...", content: "new text")Key considerations:
export_image(scale: 2) on the parent frame to verify visuallyAfter replacing each chunk, check:
If issues found: adjust text content or container width before proceeding to next chunk.
lint_fix_all → catch text overflow or layout issues
export_image(scale: 1) → full design screenshot for final review| Purpose | Scale |
|---|---|
| Full page overview | 1 |
| Section check | 2 |
| Individual text detail | 3 |
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.