agentleFS
Sign inStart free
Dragoon0xDragoon0x/taste-skills/skills/evaluation/field-notes/SKILL.md

field-notes

Skill5 starsChanged 8 months agoMITView on GitHub

Structured taste breakdowns of real products. The format for making taste observations legible and shareable. Use when analyzing products, writing case studies, documenting design observations, or teaching through example.

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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:

    MUST be specific. Reference actual elements, sizes, and interactions.

    line 26
  2. Distinctive:

    MUST connect every observation to a principle.

    line 27
  3. Distinctive:

    MUST include at least one thing that doesn't work.

    line 28
  4. Distinctive:

    SHOULD be under 500 words.

    line 29
  5. Distinctive:

    NEVER write a field note about a product you haven't actually used.

    line 30

≈ “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

Field Notes

The format for making taste observations legible.

How to use

  • /field-notes Write a structured taste breakdown of a product in this conversation.
  • /field-notes <product> Analyze the specified product using the field notes format.

Constraints

Field Note Structure

  1. Product name, URL, date, category
  2. What it's trying to be (2-3 sentences. Not what it does. What experience it's trying to create.)
  3. Three things that work (specific decisions with principles behind them)
  4. One thing that doesn't (specific decision with reasoning and impact)
  5. The taste principle (one sentence: "This product demonstrates that...")
  6. Tags (principle-based tags for the reference library)

Writing Rules

  • MUST be specific. Reference actual elements, sizes, and interactions.
  • MUST connect every observation to a principle.
  • MUST include at least one thing that doesn't work. No product is perfect.
  • SHOULD be under 500 words. Concise analysis is harder and more useful than exhaustive analysis.
  • NEVER write a field note about a product you haven't actually used.

Anti-Patterns

  • Writing only about famous products everyone has already analyzed
  • Describing what the product does instead of how it feels to use
  • Listing features instead of evaluating decisions
  • Being uniformly positive (honest analysis includes what falls short)

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