industryby openakita
skills@baidu Yijian
openakita/skills@baidu-yijian
Baidu Yijian visual management skill for industrial scenarios. Provides visual recognition capabilities across 20+ industries including retail, energy, mining, ports, chemical, and steel.
What it changes
Passed 13 of 18 test cases with the skill, and 4 of 18 without it.
Without skill22%
With skill74%
Checks it passed that the model alone missed
- Executes python3 scripts/yijian.py report "钢铁厂质检报告"
- Executes python3 scripts/yijian.py report "变电站巡检分析"
- Executes python3 scripts/yijian.py report "港口设备监测报告"
and 9 more in the full report
12 fixed5 passed either way6 still failing0 broke
- Pass-rate lift
- +52 pp
- Tokens
- -50%
- Agent turns
- 0%
- Response time
- -45%
Model gemini-3.6-flashMeasured 8/13/2026v117 of 23 cases passed with skill · 18 comparable
See it in action
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptRun a visual defect analysis command on the storage tank photo located at `/chem/tank_wall_04.jpg`.
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Executes python3 scripts/yijian.py detect --image /chem/tank_wall_04.jpg | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md20 lines2 filesincludes scripts
百度一见
让 OpenClaw 具备视觉管理能力,覆盖零售餐饮、能源电力、矿山、港口、化工、钢铁等 20+ 行业。
功能
- 工业视觉检测
- 多行业场景覆盖
- 实时监控与告警
- 视觉分析报告
预置脚本
scripts/yijian.py
工业视觉检测(百度千帆 AppBuilder),需设置 APPBUILDER_TOKEN。
python3 scripts/yijian.py detect --image /path/to/product.jpg
python3 scripts/yijian.py report "产线质检分析"
Track record
Benchmark
13 / 18
test cases passed, vs 4 / 18 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
ImportedLicense MITImported 8/3/2026Version v1Bundled 1 file · scripts