AI技能编排新增|RAG知识库观察:知识库 RAG 私有问答方向这几个技能值得先试(2026-11-16)
知识库 RAG 私有问答方向近期新上架了一批 AI 技能,这里挑出 10 个按平台真实数据整理。(私有问答实测)
1. ruview-model-training
作者: ruvnet | 来源: github | 下载量: 104,356
Train RuView models — camera-free WiFlow pose (10 sensor signals, no labels), camera-supervised pose (MediaPipe + ESP32 CSI → 92.9% PCK@20, ADR-079), RuVector
2. cli-backup-sync
作者: cheaper-inference | 来源: github | 下载量: 87,743
Backup and restore OmniRoute data from the CLI. Trigger incremental snapshots, sync to cloud storage, manage backup schedules, and restore from archive files.
3. omni-sync-cloud
作者: cheaper-inference | 来源: github | 下载量: 87,743
Synchronise OmniRoute configuration, provider connections, and settings to/from cloud storage. Manage cloud worker authentication and remote backup targets.
4. regression-suite
作者: Donchitos | 来源: github | 下载量: 39,532
"Map test coverage to GDD critical paths, find fixed bugs lacking regression tests, flag drift from new features.
5. test-evidence-review
作者: Donchitos | 来源: github | 下载量: 39,532
"Quality review of test files and evidence — goes beyond existence, evaluates assertion coverage. ADEQUATE/INCOMPLETE/MISSING/NOT ASSESSED per story.
6. adr-hshare
作者: HKUDS | 来源: github | 下载量: 38,274
ADR/H-share/A-share cross-listing premium analysis — track pricing gaps between US-listed ADRs, HK-listed H-shares, and A-shares for arbitrage signals
7. bottleneck-hunter
作者: HKUDS | 来源: github | 下载量: 38,274
"Supply-chain bottleneck arbitrage. Given a super-trend (AI infra, energy transition, defense, semiconductor reshoring, space economy), decompose its physical
8. crypto-derivatives
作者: HKUDS | 来源: github | 下载量: 38,274
Crypto-derivatives strategies — perpetual funding-rate arbitrage, futures term-structure contango/backwardation trading, and option volatility-smile / Greeks
9. hk-connect-flow
作者: HKUDS | 来源: github | 下载量: 38,274
Stock Connect (Shanghai/Shenzhen-Hong Kong) fund flow analysis — Northbound (foreign into A-shares), Southbound (mainland into HK), sector allocation tracking
10. liquidation-heatmap
作者: HKUDS | 来源: github | 下载量: 38,274
Liquidation level analysis and heatmap interpretation — identify leveraged position concentration, liquidation cascades, stop-hunt zones, and use liquidation
直达链接
- 查看详情:ruview-model-training
- 查看详情:cli-backup-sync
- 查看详情:omni-sync-cloud
- 查看详情:regression-suite
- 查看详情:test-evidence-review
- 查看详情:adr-hshare
- 查看详情:bottleneck-hunter
- 查看详情:crypto-derivatives