skill-creator

Interactive guide for creating, reviewing, and improving agent skills (SKILL.md folders). Use when the user wants to build a new skill ('create a skill', 'make a skill for X', 'write a SKILL.md', 'turn this workflow into a skill'), review or improve an existing skill, fix a skill that never triggers or triggers too often, or validate a skill folder before sharing it. Do NOT use for general prompt writing, MCP server development, or editing arbitrary markdown files.

Quality

96%

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

92%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 well-structured, actionable, and uses progressive disclosure effectively with real bundle files linked one level deep. Its only weakness is minor verbosity in a couple of asides that could be tightened for token efficiency.

Suggestions

Tighten the Step 6 aside ('this gives faster signal than broad testing') and condense the disable-model-invocation paragraph, moving deeper detail to references/frontmatter.md to improve conciseness.

Consider moving the review-workflow failure-mode table into a reference file so the creation workflow stays the lean core path.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence without explaining basic concepts, but a few asides ('this gives faster signal than broad testing', extended discussion of the disable-model-invocation flag) could be trimmed. Not a 5 because minor over-explanation remains; not a 3 because the body is largely efficient throughout.	4 / 5
Actionability	Provides executable commands (python scripts/validate_skill.py), concrete frontmatter templates, before/after weak-vs-strong description examples, and literal trigger phrasing — copy-paste ready guidance covering common cases.	5 / 5
Workflow Clarity	Six-step numbered sequence with an explicit validation checkpoint in Step 5 (run validator, fix ERRORs, expect PASS), an iteration loop in Step 6, and a delivery checklist with feedback loops for error recovery.	5 / 5
Progressive Disclosure	Body links to verified one-level-deep references (references/frontmatter.md, references/patterns.md, references/testing.md) and a bundled scripts/validate_skill.py, with detail appropriately split out and clearly signaled navigation.	5 / 5
	Total	19 / 20 Passed

Description

100%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 exemplary: it states concrete capabilities, provides natural trigger phrases with synonyms, includes explicit negative triggers, and cleanly separates what from when. Minimal conflict risk with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — creating, reviewing, improving, fixing trigger behavior, and validating skill folders — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both WHAT (interactive guide for creating/reviewing/improving skills) and WHEN with concrete literal trigger phrases and a 'Do NOT use for' clause.	5 / 5
Trigger Term Quality	Rich natural trigger phrases ('create a skill', 'make a skill for X', 'write a SKILL.md', 'turn this workflow into a skill') plus synonyms and explicit negative triggers users would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear skill-authoring niche with distinct triggers, and negative triggers exclude general prompt writing, MCP server dev, and arbitrary markdown editing, minimizing overlap.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: XiaomiMiMo/MiMo-Code
Path: packages/opencode/src/skill/builtin/.bundle/skill-creator/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.