DeepSeek Harness
SkillWeb & browsingThis skill lets your AI delegate bounded coding analysis or implementation work on a repository to DeepSeek Harness. Once added, your AI can hand off a specific task and DeepSeek Harness will run it headlessly, meaning without a user interface. The outcome is completed analysis or code work for the task your AI assigned.
Available today. Use it from your connected AI after setup.
No other account needed.
After adding this skill, ask your AI to delegate a specific analysis or implementation task on a repository to DeepSeek Harness.
Then ask your AI: use the DeepSeek Harness skill
What your AI can do with it
- Delegate coding analysis on a repository to DeepSeek Harness
- Delegate implementation tasks on a repository to DeepSeek Harness
- Run DeepSeek Harness headlessly, without a user interface
- Keep delegated work scoped to bounded, defined tasks
What this skill tells your AI
The instructions your AI receives, as published by cherryhq/cherry-studio in resources/code-cli-skills/code-mate-deepseek-harness/SKILL.md and read by ahel’s review.
Run
- Set the Bash working directory to the exact project the user named and set a finite timeout, normally 10 minutes.
- Check availability with
command -v dsh. If it is missing, stop and ask the user to install DeepSeek Harness in Code Mate. - Run one headless task:
dsh --profile headless "<prompt>"
Pass the prompt as one quoted argument. Treat stdout as final text, not JSON. Exit zero means success; exit one means the task failed or did not complete. Never start the interactive UI or a login flow.
Authentication And Permissions
If DSH reports a missing provider, model, or API configuration, stop and ask the user to configure DeepSeek Harness in Code Mate. Never request, read, print, or copy credentials.
Headless DSH can write to the workspace and creates a persistent session. For read-only work, explicitly tell it not to modify files and inspect the repository diff afterward. Allow modifications only when the user explicitly requested workspace changes, and restrict the working directory to the intended project.
Example: ask DSH to diagnose a test failure without editing, run it in the repository, confirm exit zero and a clean diff, then summarize its final text.
Signals
- GitHub stars
- 52k
- Forks
- 5k
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
code-mate-deepseek-harness- Source
- github.com/cherryhq/cherry-studio