CtrlK
BlogDocsLog inGet started
Tessl Logo

mimocode-docs

Use whenever the user asks about MiMoCode itself: features, TUI or CLI commands, configuration, file locations, providers, models, authentication, or custom OpenAI-compatible or Anthropic-compatible API endpoints. Especially trigger when a prompt supplies or asks to configure a base URL/baseURL, API key/apiKey, model name or ID, provider, Anthropic Messages API, or global/project mimocode.json/jsonc. Use this skill to inspect existing config safely, make minimal changes, and verify them without guessing schema fields or model capabilities.

77

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%

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

The body is lean, actionable, and built around a clearly sequenced, validated configuration workflow. The main weakness is progressive disclosure: the skill routes to @reference/*.md files that are not present in the bundle, so its otherwise-excellent navigation cannot be verified or followed.

Suggestions

Ship the referenced bundle files (references/providers.md, config.md, guide.md, commands.md, permissions.md, workflows.md) so the @reference routing actually resolves, or remove routes to files that do not exist.

If any routed reference is not yet authored, note it explicitly in the routing section rather than implying the file is available.

Consider whether the large feature-map table belongs inline in SKILL.md or would be better split into a one-level-deep reference file to tighten the overview further.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — it never explains what a CLI/TUI/MCP/LSP is — and every section is task-relevant rather than padded with basics, fitting the lean-and-efficient anchor.

3 / 3

Actionability

Gives concrete guidance: an exact config snippet, specific redaction keys ('apiKey', 'token', 'secret', 'password'), exact paths, and the rule to put 'provider/model' at the front of recent-model state — not abstract direction.

3 / 3

Workflow Clarity

The 'Helping the User Configure' section is a 7-step numbered sequence ending in an explicit validation/checkpoint step ('Validate the parsed configuration with the narrowest relevant command and report the config ... files changed'), matching the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

The 'Reference routing' section is excellently structured and clearly signals one-level-deep @reference/*.md files, but no references/ bundle directory exists, so the referenced files (providers.md, config.md, guide.md, etc.) cannot actually resolve. It is above the monolithic anchor but below 3 because the navigation points to missing files.

2 / 3

Total

11

/

12

Passed

Description

100%

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 strong across all dimensions: it states concrete actions, includes rich natural trigger terms with useful spelling variants, explicitly covers both what and when, and is narrowly scoped to one tool. It is a model description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'inspect existing config safely, make minimal changes, and verify them' — in third person, matching the anchor for listing several specific concrete actions rather than merely naming a domain.

3 / 3

Completeness

Explicitly answers both 'when' ('Use whenever the user asks about MiMoCode itself: ...') and 'what' ('Use this skill to inspect existing config safely, make minimal changes, and verify them...').

3 / 3

Trigger Term Quality

Covers natural user phrasings including spelling variants a user would actually type — 'base URL/baseURL', 'API key/apiKey', 'mimocode.json/jsonc', plus features, configuration, providers, models, authentication.

3 / 3

Distinctiveness Conflict Risk

Scoped to a single named tool ('asks about MiMoCode itself', 'mimocode.json/jsonc', 'OpenAI-compatible or Anthropic-compatible API endpoints'), giving it a clear niche unlikely to trigger the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
XiaomiMiMo/MiMo-Code
Reviewed

Table of Contents

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.