ideate

Generate image-based alternatives, remixes, or new design directions from a Product Design brief. Use when the user asks for design variants, visual exploration, remixes, or image-generated approaches from provided context.

Quality

82%

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

81%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.

Highly actionable and well-sequenced ideation workflow with strong validation checkpoints and a reusable prompt template. The main weakness is repetition of the dimension list and ordering rules across sections, which inflates token cost without adding clarity.

Suggestions

De-duplicate the target-dimension list: keep it once (ideally in the Image Gen Prompt) and reference it from Workflow step 5 instead of repeating all values.

Consolidate the option-ordering rules: the Rules list and the Output section both restate Promise.all/request-order guidance — merge into one authoritative block.

Trim peripheral restating of obvious constraints (e.g. 'Each option must be its own Image Gen result' vs 'Do not put multiple ideas into a single image generation') to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but noticeably duplicates material — the target-dimension list appears in both Workflow step 5 and the Image Gen Prompt, and option-ordering rules are restated across the Rules and Output sections — placing it at 'mostly efficient but could be tightened' rather than 4.	3 / 5
Actionability	Fully executable guidance: exact dimensions (390 x 844, 1440 x 1024), a copy-paste Image Gen prompt template, concrete attach-image rules, and a literal selection message ('Which option should I build: 1, 2, or 3?') covering the common cases.	5 / 5
Workflow Clarity	An explicit 8-step sequence with validation checkpoints — 'Do not generate images until $get-context has satisfied the minimum required design brief', access-gap stops, 'stop for the user's selection before any build work', and a retry-missing-generations gate — plus a Feedback Loop for error recovery.	5 / 5
Progressive Disclosure	Clear section structure with one-level-deep, well-signaled references ([$index], [$critical-overrides], [$user-context], $image-to-code) and no bundle files to misorganize; minor gap is the inlined/duplicated dimension guidance that could live in a single referenced block.	4 / 5
	Total	17 / 20 Passed

Description

83%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.

A strong, third-person description that clearly states capability and explicit usage triggers with natural vocabulary. Minor gains are available from broadening trigger synonyms and enumerating more concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'Generate image-based alternatives, remixes, or new design directions' — but stops short of a fully comprehensive action list, fitting the 'several specific actions; minor gaps' anchor rather than 5.	4 / 5
Completeness	Explicitly answers both what ('Generate image-based alternatives, remixes, or new design directions from a Product Design brief') and when ('Use when the user asks for design variants, visual exploration, remixes, or image-generated approaches from provided context') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user-facing terms 'design variants, visual exploration, remixes, or image-generated approaches' give good coverage, though common synonyms like 'mockups' or 'concepts' are absent, keeping it just below 5.	4 / 5
Distinctiveness Conflict Risk	The image-generation design-ideation niche is clearly carved out with distinct triggers, with only minor overlap risk against adjacent Product Design skills (e.g. image-to-code), matching the 'mostly distinct' anchor.	4 / 5
	Total	17 / 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
relative_links	Relative link issues: 4 suspicious	Warning

	Total	15 / 16 Passed

Repository: XiaomiMiMo/MiMo-Code
Path: packages/opencode/src/skill/builtin/.bundle/product-design/workflows/ideate/SKILL.md
Commit: ec3f989

Reviewed: 5 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.