Okx Task Watch

okx/onchainos-skills

This is OKX's live task monitoring system that uses long polling instead of cron jobs or sleep loops. It watches your user session task inbox and fires off notifications or decision requests when something changes. The documentation is very explicit about routing: when you say "monitor task progress" or "帮我盯着任务", it kicks off a single long poll call that waits for events, not a recurring check. It handles backlog drain for history too. The skill owns the watch loop itself but punts actual business actions like apply, deliver, or dispute to a separate okx-agent-task skill. Socket warns and Snyk fails on the audit front, so worth checking what those flags are about before you wire this into production.

skills.sh installs

2.3K

GitHub stars

347

last updated

Aug 21, 2026

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Recommended

More DevOps & CI/CD

1self-improvementpskoett/pskoett-ai-skillsCaptures learnings, errors, corrections, and feature requests to enable continuous improvement. Use when: (1) User corrects Claude ('No, that's wrong...', 'Actu2.1Kskills.sh installs

2nemotron-speechnvidia/skillsRoutes NVIDIA Nemotron Speech (Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted.2.1Kskills.sh installs

3scrapy-web-scrapingmindrally/skillsExpert guidance for building web scrapers and crawlers using the Scrapy Python framework with best practices for spider development, data extraction, and pipeli2Kskills.sh installs

4huggingface-vision-trainerhuggingface/skillsTrains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, 2Kskills.sh installs

5neurokit2k-dense-ai/scientific-agent-skillsUse NeuroKit2 to build or audit reproducible research workflows for physiological time-series preprocessing, event/interval analysis, multimodal alignment, vari2Kskills.sh installs

6phylogeneticsk-dense-ai/scientific-agent-skillsBuild and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree2Kskills.sh installs