design-blueprint

Produces a structured design specification (DESIGN.md + structural layout + Decision Trace) before any visual artifact is built — the "blueprint" phase that keeps AI-generated design from feeling templated. Use this skill whenever the user asks to design, plan, mock up, or restructure any visual output — PPT / slides / decks, landing pages, dashboards, posters, charts, infographics, marketing pages, UI components, prototypes, illustrations — even when they only say "make a slide about X" or "help me put together a page for Y". Also trigger on requests to critique or improve an existing design when the user wants a principled, spec-driven pass rather than just cosmetic tweaks. Do NOT trigger when the user has already handed you a completed DESIGN.md and only wants code implementation (defer to frontend-design or implement directly).

Quality

89%

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

78%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 well-organized, actionable blueprint workflow with strong sequencing, validation, and progressive disclosure. Its main weakness is conciseness — several motivational 'Why' paragraphs and conceptual framings restate things Claude could infer, adding tokens that don't all earn their place.

Suggestions

Trim the motivational framing (e.g. the 'slop median' opening and the 'Why this is non-negotiable' paragraph) to one-line rationale notes; Claude can infer the motivation from the concrete move.

Move the full 'six-layer model' explanation out of the body entirely — it is meta context that belongs only in the reference file, leaving a one-line pointer.

Add one compact worked example of a completed Decision Trace entry and one filled DESIGN.md section inline, so the format is unambiguous without the user opening the reference.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-structured, but several 'Why:' rationales and motivational passages (e.g. the 'slop median' framing and the non-negotiable Decision Trace paragraph) explain concepts and motivations Claude could infer, adding padding beyond the executable guidance.	3 / 5
Actionability	Provides concrete, executable structure — an identity table with artifact routing, a fillable template path, a JSON Decision Trace schema, and a fixed output shape — with only minor gaps (no inline worked example of a completed DESIGN.md section or trace entry).	4 / 5
Workflow Clarity	Clear numbered Move 0–5 sequence with explicit branching (Branch A/B in Move 2, Critique mode reordering), a self-check validation pass with named anti-slop patterns, and feedback loops (fix-in-place or trace-with-justification) before shipping.	5 / 5
Progressive Disclosure	Clean overview in SKILL.md with six real one-level-deep reference files (all verified present) plus one asset template, each clearly signaled with a short purpose line in the Reference files section; no nested-reference chains.	5 / 5
	Total	17 / 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 excellent: it states concrete deliverables, covers an exhaustive set of natural trigger phrases, explicitly separates the what/when, and draws a clear boundary against implementation skills. It is long but every clause earns its place for trigger routing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete deliverables (DESIGN.md, structural layout, Decision Trace) and specific artifact types (PPT/decks, landing pages, dashboards, posters, charts, UI components), giving comprehensive coverage of what the skill produces.	5 / 5
Completeness	Explicitly answers both 'what' (produces a structured design specification) and 'when' (Use this skill whenever the user asks to design/plan/mock up/restructure visual output, plus trigger phrases and a Do NOT trigger boundary).	5 / 5
Trigger Term Quality	Comprehensive natural terms and synonyms users actually say — 'make a slide about X', 'help me put together a page for Y', 'design, plan, mock up, restructure' — plus the full artifact vocabulary and a negative-trigger example.	5 / 5
Distinctiveness Conflict Risk	Clear niche — the blueprint/spec phase before visual artifacts — with an explicit Do NOT trigger clause deferring completed-DESIGN.md implementation to frontend-design, minimizing conflict risk.	5 / 5
	Total	20 / 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: packages/opencode/src/skill/builtin/.bundle/design-blueprint/SKILL.md
Commit: bed9b0b

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.