Dokimi — Testing skill for Claude Code

Dokimi — agent measurement framework

[](https://intel.github.io/dokimi/) [](https://codecov.io/gh/intel/dokimi)

**Documentation: ** — guides, plus a [CLI reference](https://intel.github.io/dokimi/reference/cli/) and an [API reference](https://intel.github.io/dokimi/reference/api/dokimi/) generated from the code.

**dokimi** — Greek *δοκιμή*, "test, proof". The name is the method: an artifact does not get trusted because it was written or because it is popular, it gets trusted because it passed a test that could have failed.

Documentation, skills, MCP doc sources and agent persona prompts are cheap to write and easy to over-claim. This repository is the framework that measures whether any of them actually helps a coding agent: change one thing, hold everything else fixed, run the same question or task set, and report the delta together with its p-value.

The measurement is the deliverable. An artifact ships with the scorecard that earned it — a deliberate contrast to popularity-ranked marketplaces, which structurally bury niche HPC and numerical-accuracy tooling.

The framework is vendor-neutral: any model reachable through LiteLLM, any docs, skills or tasks.

What it measures

1. Does it help? Enabled vs disabled arms

An *arm* is one context condition. Every arm runs the same question or task set against the same model, and the report gives the per-arm delta against the baseline with paired statistics. Arms are given as specs (`dokimi arms run --arms …`):

Arm	What the agent gets
baseline	nothing extra
docs:	product documentation (local Markdown, URLs, Context7)
mcp:	an MCP documentation server it can call
`skill:<pa