agentleFS
Sign inStart free
Dragoon0xDragoon0x/taste-skills/skills/perception/detail-observation/SKILL.md

detail-observation

Skill5 starsChanged 8 months agoMITView on GitHub

Micro-decision analysis. Catalog the border radii, spacing scales, type sizes, and state coverage that most people miss. Use when auditing design systems, evaluating craft quality, or training granular perception.

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    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:

    MUST count the actual number of type sizes in use (not what the system says, what's on screen)

    line 17
  2. Very specific:

    MUST identify the spacing scale (is it 4/8/16/24/32 or random values?)

    line 18
  3. Distinctive:

    MUST note border radius consistency (same across buttons, cards, inputs, or varying?)

    line 19
  4. Distinctive:

    MUST check weight usage (how many font weights, and is each one serving a clear purpose?)

    line 20
  5. Distinctive:

    SHOULD identify the color count and role of each color (primary, neutral, accent, semantic)

    line 21
  6. Distinctive:

    SHOULD check hover, focus, active, disabled, loading, empty, error, and success states

    line 22
  7. Distinctive:

    MUST use specific values: "16px margin" not "generous spacing"

    line 25
  8. Distinctive:

    MUST note inconsistencies with evidence: "buttons use 4px radius, cards use 8px, inputs use 6px"

    line 26
  9. Distinctive:

    NEVER say "it feels inconsistent" without pointing to the specific inconsistency

    line 27
  10. Distinctive:

    SHOULD compare observed values against the design system if one exists

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Detail Observation

Catalog the micro-decisions nobody else notices.

How to use

  • /detail-observation Apply detail-level analysis constraints to this conversation.

Constraints

What to Catalog

  • MUST count the actual number of type sizes in use (not what the system says, what's on screen)
  • MUST identify the spacing scale (is it 4/8/16/24/32 or random values?)
  • MUST note border radius consistency (same across buttons, cards, inputs, or varying?)
  • MUST check weight usage (how many font weights, and is each one serving a clear purpose?)
  • SHOULD identify the color count and role of each color (primary, neutral, accent, semantic)
  • SHOULD check hover, focus, active, disabled, loading, empty, error, and success states

Precision Over Opinion

  • MUST use specific values: "16px margin" not "generous spacing"
  • MUST note inconsistencies with evidence: "buttons use 4px radius, cards use 8px, inputs use 6px"
  • NEVER say "it feels inconsistent" without pointing to the specific inconsistency
  • SHOULD compare observed values against the design system if one exists

Anti-Patterns

  • Stopping at the surface level ("the typography looks good")
  • Treating every inconsistency as an error (some breaks are intentional)
  • Spending time on details that don't affect the user experience

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