patentfig
Generate patent-office-compliant figures via the PatentFig AI API — patent line art from text (PNG or SVG), vectorize drawings to SVG/DXF/vector PDF, AI-upscale images, and convert to filing-ready TIFF/PDF/PNG. Use when the user asks for patent drawings, patent figures, invention diagrams, USPTO/EPO-compliant line art, vectorizing a drawing for CAD, or preparing figures for a patent filing. Requires a PATENTFIG_API_KEY environment variable.
- License 许可
- MIT
- 最近更新
- 2026-10-13
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- patentfig
- tags
- [ "Patent", "Patent Drawings", "Line Art", "SVG", "Vectorize", "DXF", "USPTO", "Image Generation", "API" ]
- author
- TopLocalAI
- license
- MIT
- version
- 1.0.0
- metadata
- { "docs": "https://patentfig.ai/docs", "homepage": "https://patentfig.ai" }
- description
- Generate patent-office-compliant figures via the PatentFig AI API — patent line art from text (PNG or SVG), vectorize drawings to SVG/DXF/vector PDF, AI-upscale images, and convert to filing-ready TIFF/PDF/PNG. Use when the user asks for patent drawings, patent figures, invention diagrams, USPTO/EPO-compliant line art, vectorizing a drawing for CAD, or preparing figures for a patent filing. Requires a PATENTFIG_API_KEY environment variable.
02 资源文件 1
- 参考文档references/endpoints.md3.2 KB
03 SKILL.md 正文
PatentFig AI API
Generate and convert patent figures through the PatentFig AI REST API.
- Base URL:
https://patentfig.ai/api/v1 - Auth:
Authorization: Bearer $PATENTFIG_API_KEY - All endpoints are synchronous and return JSON:
{ "success": true, "data": {...} }on success,{ "success": false, "error": { "code", "message" } }on failure. - Generated files are returned as URLs on
https://cdn.patentfig.ai— pass them to the user or feed them into follow-up calls.
Setup
The key comes from the PATENTFIG_API_KEY environment variable. Never hardcode it, print it, or write it into files or logs.
If the variable is not set, tell the user to create a key at https://patentfig.ai/settings/api-keys (requires a PatentFig AI account; keys start with pfig_) and export it:
export PATENTFIG_API_KEY="pfig_..."
Verify connectivity and credit balance (free call):
curl -s https://patentfig.ai/api/v1/credits \
-H "Authorization: Bearer $PATENTFIG_API_KEY"
# → { "success": true, "data": { "balance": 500 } }
Generate a patent figure (10 credits)
POST /figures — the core endpoint. One prompt → one figure. Views, diagram type, and composition are all controlled through the prompt; for a multi-view set (front/side/top), make one call per view.
curl -s -X POST https://patentfig.ai/api/v1/figures \
-H "Authorization: Bearer $PATENTFIG_API_KEY" \
-H "Content-Type: application/json" \
--max-time 300 \
-d '{
"prompt": "Exploded view of a wireless earbud charging case showing lid, hinge, charging coil, and battery",
"output": "svg",
"labeled": true
}'
output:"png"(raster figure) or"svg"(stroke-based line art, CAD-friendly). Default"png".labeled: trueadds patent-style numeric reference callouts (100, 102, …).referenceImageUrls: up to 4 public image URLs (sketch/photo/prior figure) used as the structural baseline.- Response
data.urlis the figure; withoutput: "svg"the full SVG source is also indata.svg.
Prompting tips: name the parts to draw (names tell the model WHAT to draw, not what to label); for flowcharts/block diagrams, name every node explicitly.
Convert an existing image
All three endpoints accept either JSON with imageUrl (public URL) or multipart/form-data with a file field (PNG/JPEG/WebP/TIFF, ≤10 MB).
Vectorize (20 credits) — raster → SVG / DXF / vector PDF:
curl -s -X POST https://patentfig.ai/api/v1/vectorize \
-H "Authorization: Bearer $PATENTFIG_API_KEY" \
-H "Content-Type: application/json" \
--max-time 300 \
-d '{ "imageUrl": "https://example.com/drawing.png", "format": "dxf", "engine": "lineart" }'
engine: "lineart" (default) redraws as clean single-stroke patent line art — use for CAD/DXF. engine: "trace" reproduces the input pixels faithfully, preserving fills — use when output must match the original.
Enhance (20 credits) — AI super-resolution: POST /enhance with scale (2 or 4, controls pixels) and dpi (300 or 600, metadata stamp only).
Convert (20 credits) — filing-ready raster: POST /convert with format (png/tiff/pdf) and dpi (300 or 600).
Full parameter tables for every endpoint: see references/endpoints.md. Machine-readable spec: https://patentfig.ai/api/openapi.yaml
Operational rules
- Set a client timeout of at least 300 seconds — generation and vectorization take from ~20s up to a few minutes.
- Credits are charged only on success; retrying a failed call never double-bills.
- Rate limit: 60 requests/minute per key. On
429back off (start at 5s) and retry. - On
402 INSUFFICIENT_CREDITS, stop and tell the user to top up at https://patentfig.ai/pricing. - On
500 GENERATION_FAILED, one retry is reasonable; persistent failures usually mean the input doesn't suit the pipeline (e.g., a photo sent for line-art vectorization — suggestPOST /figureswith the photo asreferenceImageUrlsinstead). - Before a batch of billable calls, check
GET /creditsand confirm the balance covers it.
04 同仓库更多 Skills
zapier-make-patterns
No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points. This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power
yeet
Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).
workflow-automation
Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off. This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation. Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility
trigger-dev
Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.
slack-automation
Automate Slack workspace operations including messaging, search, channel management, and reaction workflows through Composio's Slack toolkit.
rote
Compile a proven agent skill (a SKILL.md plus references) into a deterministic pipeline that runs without an LLM in the loop, then serve it back to Claude as an MCP tool. Use when: rote, compile this skill, turn this skill into a workflow, make this skill deterministic, make this skill cheaper or faster, harden this skill for production, run this skill as a background job.