agentleFS
Sign inStart free
jezwebjezweb/vite-flare-starter/skills/compare-options/SKILL.md

compare-options

Skill49 starsChanged 3 months agoMITView on GitHub

Evaluate multiple choices side-by-side based on relevant criteria, then present a comparison the user can act on. Use when the user asks to compare options, choose between alternatives, or weigh up X vs Y.

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 7 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use specific values where possible (price, dates, sizes)

    line 26
  2. Distinctive:

    Use boolean for present/absent features

    line 27
  3. Distinctive:

    Use short text ("excellent", "limited", "good") for qualitative

    line 28
  4. Very specific:

    Use show_comparison with each option as a card, features as the criteria

    line 36
  5. Very specific:

    Add cta buttons so the user can pick

    line 38
  6. Distinctive:

    Don't recommend an option you didn't research

    line 54
  7. Distinctive:

    Don't hide trade-offs to make a recommendation cleaner

    line 55
  8. Distinctive:

    Don't add features to the comparison that none of the options have ("Option A doesn't support X, but neither do the others — drop it")

    line 56
  9. Distinctive:

    Don't make a single-choice comparison ("X is good") — comparison requires alternatives

    line 57

≈ “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

Compare Options

When to use

  • "Compare X and Y"
  • "Which is better, A or B?"
  • "Help me choose between..."
  • "What are the trade-offs of...?"

Steps

  1. Identify the options and criteria:
    • Options: what's being compared? If unclear, ask via ask_questions.
    • Criteria: what matters to the user? Common ones: price, quality, speed, ease of use, support. If unclear, propose 3-5 via ask_questions (multi-select).
  2. Research each option in parallel:
    • For products/services: web_search for reviews + browser_extract on official pages for specs
    • For technical choices: web_research skill on each option
    • For internal options: use information already in context
  3. Score each option against each criterion:
    • Use specific values where possible (price, dates, sizes)
    • Use boolean for present/absent features
    • Use short text ("excellent", "limited", "good") for qualitative
    • For a weighted ranking, don't do the arithmetic yourself — run run_skill_script with this skill and path scripts/score.js, passing {"weights": {...}, "options": [{"name", "scores": {...}}]} as stdin (scores 0-10). It returns the ranked totals, winner, and margin deterministically.
  4. Display the comparison:
    • Use show_comparison with each option as a card, features as the criteria
    • Highlight the one that scored best overall (set highlight: true)
    • Add cta buttons so the user can pick
  5. Add a recommendation — one paragraph explaining your top pick and why, including who would prefer the alternative. Be specific about the trade-offs.
  6. Offer to dig deeper via offer_choices:
    • "Tell me more about [winner]"
    • "Compare additional criteria"
    • "Add another option"
    • "I'll go with [winner]"

Style

  • Be balanced. Even your top pick has downsides — name them.
  • Quantify where possible. "Costs 30% more" beats "expensive".
  • Match the user's stakes — for a casual choice, keep it brief; for a major decision, be thorough.

What not to do

  • Don't recommend an option you didn't research
  • Don't hide trade-offs to make a recommendation cleaner
  • Don't add features to the comparison that none of the options have ("Option A doesn't support X, but neither do the others — drop it")
  • Don't make a single-choice comparison ("X is good") — comparison requires alternatives

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