deepseek-lane
Skill1 starsChanged 4 days agoMITView on GitHub
Run a job on DeepSeek models (deepseek-v4-pro, deepseek-flash) through the Kimi Code CLI with a DeepSeek provider configured: an independent opinion from another model family, cheap execution, or bulk labeling. Use when the user asks for DeepSeek or the orchestra routing table picks it. Needs the orchestra skill's scripts.
In this repository4 other files it gives its agents.
- chatgpt-laneSkill
- councilSkill
- kimi-laneSkill
- orchestraSkill
The file
Files
DeepSeek lane (via Kimi Code CLI)
The Kimi Code CLI can talk to any provider listed in its config. Add DeepSeek there once
(provider + model aliases deepseek/deepseek-v4-pro and deepseek/deepseek-flash); mmo-preflight
then shows the lane as available.
Models
| Alias | Use |
| deepseek/deepseek-v4-pro | Third opinion from a non-GPT, non-Claude family; cheap execution |
| deepseek/deepseek-flash | Bulk labeling and cleanup, fast and cheap |
Run
../orchestra/scripts/mmo-run deepseek --mode ro --brief q.md --out out/ds.md
../orchestra/scripts/mmo-run deepseek -m deepseek/deepseek-flash --mode ro --brief bulk.md --out out/labels.md
git worktree add ../wt-<task> -b lane/<task>
../orchestra/scripts/mmo-run deepseek --mode rw -C ../wt-<task> --brief brief.md --out out/<task>.mdFailures
DeepSeek is prepaid. An empty balance shows up as HTTP 402 and the runner reports status=limit (exit 6).
Tell the user, route the job to the fallback lane, and do not retry in a loop.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.