agentleFS
wrg32786wrg32786/aigent-design-system/skills/design-forensics/SKILL.md

design-forensics

Skill4 starsChanged 3 months agoMITView on GitHub

Inspect live websites, screenshots, motion references, or structured design files and convert the evidence into normalized Design DNA without copying source expression.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill before asking an agent to apply inspiration from an existing design.

    line 8
  2. Distinctive:

    Prefer a live public URL.

    line 12
  3. Distinctive:

    Stop before implementation unless the task also invokes reference synthesis.

    line 17
  4. Distinctive:

    Do not infer exact implementation details that the evidence does not support.

    line 36
  5. Distinctive:

    Never store authenticated or private references without explicit authority.

    line 37
  6. Very specific:

    Keep local captures under .aigent/inspiration.

    line 38
  7. Distinctive:

    Every source must have:

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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 Forensics

Use this skill before asking an agent to apply inspiration from an existing design.

Default order

  1. Prefer a live public URL.
  2. Capture desktop, tablet, and mobile evidence.
  3. Record DOM hierarchy, geometry, computed styles, interactions, media, animations, responsive changes, and errors.
  4. Generate design-dna.json and report.html.
  5. Mark uncertain dimensions explicitly.
  6. Stop before implementation unless the task also invokes reference synthesis.

Command

node scripts/inspire.mjs add <url-or-file> --label <name>

For a screenshot, video, Figma export, or other file, provide a structured annotation when exact browser evidence is unavailable:

node scripts/inspire.mjs add reference.png --analysis reference-design-dna.json

Evidence rules

  • A URL may support high-confidence structure, type, material, interaction, media, and motion evidence.
  • A screenshot cannot prove hidden states, breakpoints, exact fonts, DOM order, accessibility, or animation timing.
  • A motion clip cannot prove source code, interaction semantics, or responsive behavior.
  • Do not infer exact implementation details that the evidence does not support.
  • Never store authenticated or private references without explicit authority.
  • Keep local captures under .aigent/inspiration; do not commit third-party screenshots or extracted private data.

Output contract

Every source must have:

  • source identity and origin
  • capture timestamp
  • source kind
  • evidence list
  • confidence by dimension
  • structure, typography, material, motion, interaction, media, and responsive DNA
  • copy fingerprint, not copied copy
  • human-readable report

The output describes a design. It does not authorize reuse of source assets or expression.

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.