agentleFS
Sign inStart free
Dragoon0xDragoon0x/taste-skills/skills/reference-building/library-architecture/SKILL.md

library-architecture

Skill5 starsChanged 8 months agoMITView on GitHub

Build a reference system that returns the right reference in under 60 seconds. Use when setting up a design reference library, reorganizing existing collections, or helping teams build shared reference systems.

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 11 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    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 use one tool, not three.

    line 17
  2. Distinctive:

    MUST support tags and search.

    line 18
  3. Distinctive:

    MUST save screenshots, not bookmarks.

    line 19
  4. Distinctive:

    SHOULD include a cropped detail of the specific thing that caught your eye alongside the full screenshot

    line 20
  5. Distinctive:

    MUST collect decisions, not aesthetics.

    line 23
  6. Distinctive:

    MUST collect from outside your domain.

    line 24
  7. Distinctive:

    MUST collect across time. Include work from the 1950s alongside work from this month.

    line 25
  8. Distinctive:

    SHOULD collect problems too.

    line 26
  9. Distinctive:

    MUST prune ruthlessly. 200 strong references beats 2,000 unsorted screenshots.

    line 31
  10. Distinctive:

    Only saving work from your own domain

    line 35
  11. Distinctive:

    Never revisiting or pruning the library

    line 36

≈ “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

Library Architecture

A reference library is only as good as your ability to find the right reference at the right time.

How to use

  • /library-architecture Apply library design constraints to this conversation.

Constraints

System Requirements

  • MUST use one tool, not three. Pick one and commit.
  • MUST support tags and search. If you can't find a reference in 60 seconds, the system is failing.
  • MUST save screenshots, not bookmarks. URLs die. Products redesign. Screenshots are permanent.
  • SHOULD include a cropped detail of the specific thing that caught your eye alongside the full screenshot

Content Rules

  • MUST collect decisions, not aesthetics. A checkout flow screenshot is more useful than a beautiful hero.
  • MUST collect from outside your domain. At most 40% should be from your own industry.
  • MUST collect across time. Include work from the 1950s alongside work from this month.
  • SHOULD collect problems too. A well-crafted design that fails at some level teaches more than obvious success.

Maintenance

  • Monthly: add minimum 10 new references, remove 5 that aren't earning their place
  • Quarterly: review tags. Are you using all of them? Are there missing categories?
  • MUST prune ruthlessly. 200 strong references beats 2,000 unsorted screenshots.

Anti-Patterns

  • Saving everything without curation (hoarding is not collecting)
  • Only saving work from your own domain
  • Never revisiting or pruning the library
  • Using multiple tools with no single source of truth

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