FreePublished on GitHub
unblind
Routes images to Mimo/OpenAI vision API for text-only models. Use this skill when the user sends an image, asks "what's in this picture", says "analyze this screenshot", requests "OCR" or "extract text", reviews UI designs, reads charts, or uses Chinese triggers like 识别图片/看图. Self-healing setup on first run. Does NOT handle video, audio, or PDFs.
The English summary is being prepared. Showing the original description.
Santazuki/unblind24 stars(GitHub 24 + cccskills 0)
Works withOpenAI
Run score Not tested
See how to installFiles included (75)
- SKILL.md3.3 KB
- .github/workflows/ci.yml747 B
- .github/workflows/publish.yml377 B
- .gitignore509 B
- display/2026-05-30-provider-v3-protocol-driven-design.md9.1 KB
- display/provider-optimization.md18.6 KB
- docs/test-results/gpt-rebuttal-report.md8.1 KB
- docs/test-results/step1-logger-errorHandler.md696 B
- docs/test-results/step10-cache.md906 B
- docs/test-results/step11-health-config.md3.6 KB
- docs/test-results/step12-cache-granularity.md1.1 KB
- docs/test-results/step13-openai-provider.md1.9 KB
- docs/test-results/step14-phase0-silent.md12.2 KB
- docs/test-results/step15-validation-tests.md2.9 KB
- docs/test-results/step16-ci-circuitbreaker-fix.md326 B
- docs/test-results/step17-phase3-chain-registry.md18.0 KB
- docs/test-results/step18-phase5-test.md7.7 KB
- docs/test-results/step19-gemini-provider.md2.8 KB
- docs/test-results/step2-config.md2.4 KB
- docs/test-results/step3-credentialManager.md3.0 KB
- docs/test-results/step4-retry.md4.8 KB
- docs/test-results/step5-imageProcessor.md5.7 KB
- docs/test-results/step6-provider-mimo.md6.9 KB
- docs/test-results/step7-orchestrator.md3.4 KB
- docs/test-results/step8-cli.md13.2 KB
- docs/test-results/step9-regression.md13.2 KB
- install.sh1.8 KB
- LICENSE1.0 KB
- package.json632 B
- README.md8.0 KB
- resources/best_practices.md1.8 KB
- resources/phase0-details.md2.3 KB
- resources/troubleshooting.md3.3 KB
- scripts/install.js3.1 KB
- scripts/lib/cache.js3.7 KB
- scripts/lib/config.js3.7 KB
- scripts/lib/credentialManager.js1.7 KB
- scripts/lib/errorHandler.js2.3 KB
- scripts/lib/httpClient.js2.8 KB
- scripts/lib/imageProcessor.js4.2 KB
- scripts/lib/logger.js722 B
- scripts/lib/orchestrator.js7.0 KB
- scripts/lib/providers/generic-provider.js5.2 KB
- scripts/lib/providers/protocols.js5.4 KB
- scripts/lib/providers/provider.js2.8 KB
- scripts/lib/providers/registry.js3.8 KB
- scripts/lib/retry.js3.4 KB
- scripts/unblind.mjs5.3 KB
- settings.example.json199 B
- templates/chain_of_thought.md1.1 KB
- templates/output_formats/csv.md510 B
- templates/output_formats/json.md989 B
- templates/output_formats/yaml.md715 B
- TEST.md12.6 KB
- tests/evals.json2.4 KB
- tests/sample_images/README.md1.5 KB
- tests/scenarios.md2.5 KB
- tests/test-cache.js2.4 KB
- tests/test-cli.js5.7 KB
- tests/test-config.js2.6 KB
- tests/test-credentialManager.js1.4 KB
- tests/test-docs.js4.5 KB
- tests/test-errorHandler.js1.4 KB
- tests/test-generic-provider.js9.6 KB
- tests/test-imageProcessor.js3.0 KB
- tests/test-install.js3.1 KB
- tests/test-logger.js1.5 KB
- tests/test-mimo.js2.6 KB
- tests/test-multi-image.js9.6 KB
- tests/test-orchestrator.js2.0 KB
- tests/test-protocols.js11.6 KB
- tests/test-registry.js4.2 KB
- tests/test-retry.js3.7 KB
- tests/test-security.js10.4 KB
- tests/test-version.js1.3 KB
SKILL.md (original)
Review the instructions the agent will receive before you install.
<!-- LEVEL 1: Metadata above (~180 tokens, always loaded) -->
<!-- LEVEL 2: Instructions below (~550 tokens, loaded on trigger) -->
Unblind
Route images to vision API. Never pretend to see. Never Read/Edit settings.json.
Iron Rules
- Phase 0 mandatory every invocation
- NEVER Read/Edit
~/.claude/settings.json - Config via CLI (
--config,--set-model) ornode -e, never via tools - Never preamble. Never hallucinate. Always invoke bundled script.
- Tool reads API key from env automatically
Quick Start
User sends image → Unblind routes to Mimo/OpenAI → returns text. OCR → extracts all text. ui-review → critiques layout/UX. describe → detailed description.
Phase 0: Self-Healing
0.1 Health check
node -e "const fs=require('fs');const os=require('os');const p=require('path').join(os.homedir(),'.claude','settings.json');const s=JSON.parse(fs.readFileSync(p,'utf8'));const issues=[];if(!s.env?.MIMO_API_KEY) issues.push('KEY_MISSING');if(!s.env?.MIMO_VISION_MODEL||s.env.MIMO_VISION_MODEL==='mimo-v2.5-pro') issues.push('MODEL_MISSING');const a=s.permissions?.allow||[];if(!a.some(x=>x.includes('unblind'))) issues.push('PERM_MISSING');if(issues.length) console.log(issues.join(' '));" 2>/dev/null
- Empty → healthy, skip to Phase 1
KEY_MISSING→ 0.3 |MODEL_MISSING→ 0.5 |PERM_MISSING→ 0.4
0.2 Version check
cd ~/.claude/skills/unblind && git fetch 2>/dev/null && behind=$(git rev-list HEAD..origin/master --count 2>/dev/null) && [ "$behind" -gt 0 ] && echo "NEEDS_UPDATE $behind"
NEEDS_UPDATE <N>→ 🐌unblind 有 N 个更新没拿... git pull 一下嘛~（不阻塞）
0.3-0.9 Repair → Phase 1
See resources/phase0-details.md. All healthy → Phase 1.
Phase 1-4: Analyze
- Detect image path from
[Image: source: <path>]. Must be absolute, supported ext, no shell metacharacters. - Classify mode:
describe(default),ocr,ui-review,chart-data,object-detect,compare. - Execute:
node ~/.claude/skills/unblind/scripts/unblind.mjs '<path>' <mode>— no preamble. - Report: print stdout. API key error → back to 0.3.
Resources
resources/phase0-details.md— 完整 Phase 0 流程、CLI 参考、边缘场景resources/troubleshooting.md— 修复命令、常见错误、Node.js 配置resources/best_practices.md— 模型选择、token 优化、调试README.md— 安装指南、安全验证
Reviews
No reviews yet. Tell others what you thought.
Comments
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.