Real Skill packageSource verifiedClawHub registry

siliconflow-ocr

使用 SiliconFlow API（OpenAI 兼容接口）做图片/PDF 文字识别。默认走 PaddleOCR-VL-1.5（文档 OCR SOTA，速度比 Qwen3-VL 快 40%、表格公式更强）。支持本地路径或 URL、单页/批量并发、坐标 token 清洗。密钥通过 OpenClaw secret-egress-proxy 注入，需保留 `requests`+网关 proxy。

Identity and source

Publisher attributionLeonrardregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 56% rule confidence
Package forminstruction with code3 recorded files
Canonical sourceClawHub registryclawhub:leonrard:siliconflow-ocr
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/26/2026.claude/skills/siliconflow-ocr

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/26/2026.agents/skills/siliconflow-ocr

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/26/2026skills/siliconflow-ocr

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @leonrard/siliconflow-ocr
clawhub inspect @leonrard/siliconflow-ocr --version 1.0.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
3 / 3 inspected as text
Checked
9/26/2026, 4:25:41 PM
Scanner
0.1.3
Policy
1.0.3
5 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
  • external write action — automatically inferred
2 dependency and API indicators
  • api: api.siliconflow.cn
  • api: clawhub.ai
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
9/26/2026, 10:17:21 AM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:195507fa129e31b4beb03dcf479f3d99c38ac67f59f84c0475d68fde07dffb63
Show up to 3 recorded paths
  • scripts/ocr.py
  • skill-card.md
  • SKILL.md

Source changelog

siliconflow-ocr 1.0.0 - Initial release of the SiliconFlow OCR skill, leveraging the SiliconFlow API for high-accuracy text extraction from images and PDFs. - Uses PaddleOCR-VL-1.5 by default for document OCR (OmniDocBench SOTA), with faster speed and improved table/formula extraction over Qwen3-VL. - Supports both local image/PDF paths and URLs, with single-page and concurrent multi-page processing capabilities. - Built-in coordinate token cleaning and robust error handling (timeouts, proxy, and auth errors). - Environment-specific key injection via OpenClaw and enforced use of requests plus gateway proxy for API calls. - Includes guidance for optimal model selection and PDF page rendering (using pymupdf) for best results.