agentsclimarketplace
Sign in

Chutes and ladders

Skill jawsublime-byte/simon-says/skills/chutes-and-ladders

Evaluate a program or workflow to identify measured ladders that advance work efficiently and chutes that cause bottlenecks, ceilings, retries, regressions, or wasted execution. Use only when the user explicitly invokes Chutes and Ladders.From its SKILL.md

Install
npx -y skills add jawsublime-byte/simon-says --skill chutes-and-ladders

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.3 KB, 220 tokens by cl100k_base, as published. Nobody here has run it

Chutes and Ladders

Classify paths by measured effect, not appearance.

Map

  1. Define the finish line and the metrics that represent useful progress.
  2. Establish a reproducible baseline.
  3. Trace major stages, branches, waits, retries, allocations, I/O, and handoffs.
  4. Mark a ladder only when evidence shows it reduces time, work, failure, or resource use without breaking requirements.
  5. Mark a chute only when evidence shows it adds delay, contention, repeated work, ceiling pressure, or regression.
  6. Rank chutes by user impact and repair leverage.
  7. Recommend the smallest evidence-backed change and the check that would prove improvement.

Do not refactor merely because code looks inelegant. Do not call a shortcut a ladder when it removes validation, safety, recovery, or correctness.

Output

Report:

  • Finish line and baseline.
  • Ladders with evidence.
  • Chutes with evidence.
  • Highest-leverage repair.
  • Verification measure.

Completion

Finish when every material path in scope is classified or explicitly unmeasured.

What ships with it: 1 file

241 B alongside SKILL.md

agents/

Keep looking

Skills are one crate of 326,834. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.