drive-mimo

Use when developing or testing the MiMoCode repository and you need to programmatically drive another MiMoCode (mimo) process. Supports headless `mimo run` with JSON events and interactive TUI via tmux for behavior, integration, and visual regression testing. Covers an installed `mimo` binary or a dev build launched from source with `bun dev`; do not use it for ordinary MiMoCode task execution.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a dense, executable reference with strong validation-laden workflows and clean single-file organization. Its main weaknesses are modest redundancy in the dev-mode messaging and a somewhat monolithic structure where bulk reference material could be offloaded to separate files.

Suggestions

Consolidate the dev-build substitution guidance into one place (the Dev Mode section) and have other sections reference it once, instead of restating 'replace mimo with bun dev' in the Overview, Dev Mode, and a separate substitution-rule note.

Move the full JSON event-type catalog and the five scenario scripts into a references/ file (e.g. events.md and scenarios.sh), keeping SKILL.md as an overview with one-level-deep links, to improve progressive disclosure.

Tighten the Part 1 headless Launch section with an inline validate-on-failure note mirroring the TUI flow's feedback loop, so both interfaces show explicit error-recovery before the scenarios.

Dimension	Reasoning	Score
Conciseness	Mostly lean and command-dense with no over-explanation of concepts Claude already knows, but the dev-mode substitution rule is restated across the Overview table, a dedicated Dev Mode section, and a 'substitution rule' note, so minor trimming would reach anchor 5.	4 / 5
Actionability	Fully executable, copy-paste-ready bash throughout — launch commands, a flags table, concrete JSON event lines, grep/jq validation patterns, tmux send-keys/capture-pane recipes, and self-contained scenario functions (S1-S5) that run as-is, matching anchor 5.	5 / 5
Workflow Clarity	Clear sequenced workflows (Launch → Send → Wait → Capture → Verify → Cleanup) with explicit validation checkpoints (exit-code checks, grep/jq assertions, file-existence checks), per-scenario PASS/FAIL checklists, and error-recovery early returns, fitting anchor 5.	5 / 5
Progressive Disclosure	Well-organized into clearly signaled sections with one real one-level-deep bundle reference (scripts/wait-for-text.sh) and a Quick Reference for navigation, but the JSON event catalog and all five scenarios are inlined in a single ~450-line file rather than split into reference files, keeping it at anchor 4 rather than 5.	4 / 5
	Total	18 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concrete, trigger-rich, and cleanly bounded: it states what the skill does, when to use it, and explicitly when not to. Its only weak spot is that the enumerated capabilities emphasize interfaces over a fully exhaustive list of concrete test actions.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — headless `mimo run` with JSON events, interactive TUI via tmux, behavior/integration/visual regression testing, installed binary, and dev build via `bun dev` — with only minor gaps in enumerating concrete test actions, fitting anchor 4 rather than the exhaustive 5.	4 / 5
Completeness	Explicitly answers both what (drive a separate mimo process via headless/TUI) and when ('Use when developing or testing the MiMoCode repository'), with concrete trigger phrases and a negative boundary ('do not use it for ordinary MiMoCode task execution'), matching anchor 5.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('testing', 'drive another mimo process', 'JSON events', 'TUI', 'tmux', 'visual regression testing', 'bun dev') that a developer would naturally say, though a few synonyms are missing, so it sits at anchor 4 rather than the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow niche — programmatically driving a separate mimo process for testing — and the explicit exclusion of ordinary task execution minimizes conflict risk, matching anchor 5's minimal-conflict profile.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: XiaomiMiMo/MiMo-Code
Path: .mimocode/skills/drive-mimo/SKILL.md
Commit: ec3f989

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.