agentleFS
Sign inStart free
int2t05int2t05/engineering-skills/skills/03-design/design-research/SKILL.md

design-research

Skill3 starsChanged 31 days agoMITView on GitHub

Retrieve and analyze real visual references for a design decision. Triggers on "design references", "设计参考".

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search accessible product pages and public galleries.

    line 18

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Design Research

When to use

  • Retrieve and analyze real visual references for a design decision.

Not for: research for technical comparisons; imagegen for generated references.

Steps

  1. Define audience, category and the specific interface or brand question.
  2. Search accessible product pages and public galleries; verify availability and report blocked sources.
  3. Inspect visuals where available; separate visual observation from text-only descriptions and record source evidence.
  4. Curate a purposeful set with what to borrow, avoid and why; do not enforce gallery quotas.

Output: Suggested paths, subject to human audit: docs/design/references.md when a durable board is needed.

Verify

  • Sources and actual visual access are traceable; selection serves a concrete decision.

References

  • engineering-principles.md — shared decision boundaries, scope and verification.
  • design-principles.md — design discipline (CRAP, hierarchy before decoration, consistency from systems)
  • human-audit.md — document consent, readability and human review.
  • references/sources.md — 5 free public sources (coverage, category URL patterns, WebFetch feasibility) + routing matrix + capability boundary (iOS per-screen, markdown-not-pixels)
  • references/query-patterns.md — brief → category URL path + search term, with per-goal example queries (fintech landing, SaaS hero, onboarding flow, error/empty states)
  • references/analysis-framework.md — extraction axes (layout/grid/spacing/type/density/accent, text-descriptive) + 8 analysis lenses + 3 output frameworks (Reference Board / Competitive Comparison / Decision Log)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free