agentleFS
Sign inStart free
Dragoon0xDragoon0x/taste-skills/skills/judgment/tradeoff-assessment/SKILL.md

tradeoff-assessment

Skill5 starsChanged 8 months agoMITView on GitHub

Name what was prioritized, what was sacrificed, and whether the tradeoff was right. Every design decision trades something. Use when evaluating design decisions, defending choices, or helping teams understand what they're giving up.

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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 name both sides: "This prioritizes X at the cost of Y"

    line 17
  2. Distinctive:

    MUST evaluate whether the tradeoff serves the primary user goal

    line 18
  3. Distinctive:

    MUST avoid false binaries.

    line 19
  4. Distinctive:

    NEVER present a decision as having no downsides.

    line 20
  5. Distinctive:

    SHOULD rate tradeoffs as: well-made (right thing was prioritized), questionable (unclear if the right thing was prioritized), or poor …

    line 30
  6. Distinctive:

    MUST explain the rating with reference to user goals, not personal preference

    line 31
  7. Distinctive:

    SHOULD suggest how to mitigate the downside of a well-made tradeoff

    line 32

≈ “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

Tradeoff Assessment

Name what was chosen. Name what was lost. Decide if the trade was worth it.

How to use

  • /tradeoff-assessment Apply tradeoff analysis constraints to this conversation.

Constraints

Tradeoff Structure

  • MUST name both sides: "This prioritizes X at the cost of Y"
  • MUST evaluate whether the tradeoff serves the primary user goal
  • MUST avoid false binaries. Often there's a third option that reduces the tradeoff.
  • NEVER present a decision as having no downsides. Every choice trades something.

Common Design Tradeoffs

  • Density vs. clarity (more information per screen vs. easier scanning)
  • Speed vs. polish (shipping fast vs. refining details)
  • Flexibility vs. simplicity (more options vs. fewer decisions)
  • Consistency vs. context (following the system vs. breaking it for a specific case)
  • Innovation vs. convention (novel interactions vs. familiar patterns)

Evaluation

  • SHOULD rate tradeoffs as: well-made (right thing was prioritized), questionable (unclear if the right thing was prioritized), or poor (wrong thing was prioritized)
  • MUST explain the rating with reference to user goals, not personal preference
  • SHOULD suggest how to mitigate the downside of a well-made tradeoff

Anti-Patterns

  • Pretending a design has no tradeoffs
  • Treating every tradeoff as equally important (some are critical, some are cosmetic)
  • Optimizing for secondary concerns while neglecting primary ones

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.

Reviews can't be read right now.

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