Skill Detail

Run bounded metric-improvement experiments with MiMoCode

Run MiMoCode’s opt-in experiment workflow against a fixed evaluation budget, then review kept changes, measured deltas and an independent audit.

Developer ToolsCustom Agents
Developer Tools Custom Agents Security Reviewed
⭐ 13.8k GitHub stars
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill run-bounded-metric-improvement-experiments-mimocode Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
At a glance
Tools required
MiMoCode workflow runtime; configured provider; Git; disposable repository checkout; fixed-budget evaluator and explicit editable scope
Install & setup
Use a reviewed build containing commit 676c654d7cd6fe83e064365b1461d567ab3c0102. For source setup inspect upstream requirements, check out that commit, use the repository-declared Bun 1.3.14 toolchain, install dependencies and launch the documented bun run dev entry with MIMOCODE_EXPERIMENTAL_WORKFLOW_TOOL=true. Configure an authorized provider and confirm workflow is offered. Supply the documented research-experiment args and use a disposable checkout. Installation and execution were not tested.
Author
XiaomiMiMo
Publisher
Organization
Last updated
Nov 13, 2026
Quick brief

Use this workflow when an operator has one mechanically measurable codebase objective, a fixed-budget evaluation command and an explicit editable-file scope. The agent records a baseline, tests small hypotheses and returns measured changes with an experiment report. Invoke it when ordinary coding conversation would make comparisons and stopping rules difficult to audit.

How it works

What this skill actually does

Start MiMoCode in a disposable checkout with MIMOCODE_EXPERIMENTAL_WORKFLOW_TOOL=true. Ask its agent to invoke the workflow tool with operation: run, name: research-experiment, an absolute workspace and an actual JSON args object. Required args are dir, goal, metric, evalCmd and editable; dir must equal workspace. Choose maxIters, lowerIsBetter, guardCmd and targetValue explicitly when applicable. The script keeps improvements only when its metric and guard gates pass, escalates failures and requests a separate metric-gaming audit.

Retain PLAN.md, artifacts/results.tsv, artifacts/AUDIT.md and REPORT.md. Review source changes and trace reported numbers to recorded evaluations. The scope boundary is one bounded experiment, including automatic trial commits and reverts inside the disposable checkout; exclude deployment, general research and evaluator modification. Custom Agents is appropriate because invocation depends on MiMoCode’s own runtime, even with different model providers. The cited development snapshot has an experimental opt-in gate; confirm the installed build exposes this same contract. An audit result does not guarantee correctness.