DeepSeek Research Harness (DSRH) is an out-of-tree research capability bundle for [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness). It adds three model-invocable skills and a deterministic Python MCP sidecar while leaving model access, sessions, shell execution, jobs, sandboxing, and approvals under Harness control.
Meteora0720/Deepseek-Research-Harness
Skill Claude CodeCodex
Use this skill to verify bibliographic metadata and assess whether cited local evidence supports manuscript claims. Unresolved metadata is not automatically a hallucination.
Meteora0720/Deepseek-Research-Harness
Skill Claude CodeCodex
Use this skill to plan and supervise reproducible experiments without creating a second shell runtime. DSRH tools validate and normalize data; Harness filesystem, shell, job, permission, approval, and sandbox capabilities perform execution.
Meteora0720/Deepseek-Research-Harness
Skill Claude CodeCodex
Use this skill to analyze a born-digital research paper. Keep every important technical statement traceable to evidence returned by the DSRH paper tools.