agentsclimarketplace

Trust me bro

Skill paranoidandroid2124/sounds-like-a-skill-issue/skills/trust-me-bro

Three meme-sized agent skills to audit stale SKILL.md files, demand paired evidence, and catch model drift.

Install
npx -y skills add paranoidandroid2124/sounds-like-a-skill-issue --skill trust-me-bro

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

  • 23 days oldThe repository was created 23 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.
  • 1 stars1 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.

What its author says it does

Copied from the file, not written here

Run controlled, paired evaluations of an Agent Skill against a no-skill baseline or previous revision, using isolated contexts, raw artifacts, deterministic verification, and blind comparison. Use when validating a new or edited skill, testing whether instructions improve pass rate enough to justify tokens or latency, resolving competing skill versions, or producing reproducible efficacy evidence. Do not use for a quick structural lint or an upgrade-only smoke check.

SKILL.md

3.1 KB, 568 tokens by cl100k_base, as published. Nobody here has run it

Trust Me, Bro

Measure the marginal value of one skill. Keep the task and environment fixed; change only the skill condition.

“Trust me” is not a control condition.

Design

  1. Name one capability claim. Reject vague claims such as "works better."
  2. Pin task inputs, repository revision, model, harness, permissions, tools, reasoning setting, verifier, and timeout.
  3. Select real trigger cases and nearby failures. Start with three to five tasks for a smoke trial. Require repeated runs before publishing a performance claim.
  4. Define conditions:
    • baseline: no candidate skill content;
    • candidate: the selected skill revision;
    • previous: optional prior revision.
  5. Read references/trial-format.md for the result record and blind comparator contract.

Run

  1. Randomize condition order.
  2. Use a fresh context for each task-condition-trial. Do not let baseline workers discover the candidate skill or prior conclusions.
  3. Give every worker the same task-local context, tools, permissions, and budget. Give only candidate workers the candidate skill.
  4. Capture raw outputs, diffs, logs, timings, token counts when available, and user interventions. Do not grade from worker self-reports.
  5. Prevent live external writes unless the user explicitly authorizes the exact target. Prefer fixtures, sandboxes, or drafts.

Judge

  1. Use deterministic acceptance checks first.

  2. For subjective output, anonymize and randomize artifacts before giving them to a fresh comparator. The comparator receives the original task and rubric, but no condition labels, expected winner, or implementer analysis.

  3. Record failures as well as successes. Do not repair candidate output before grading it.

  4. Aggregate JSONL results with:

    node scripts/summarize-trials.mjs results.jsonl
node scripts/summarize-trials.mjs results.jsonl --reference previous --comparison candidate

Decide

  • Keep when the gain or risk reduction justifies instruction, token, latency, and intervention cost.
  • Trim and rerun when only part of the skill appears causal.
  • Delete or disable when baseline is equal and cheaper.
  • Block release when the candidate introduces a safety or correctness regression.

One run can catch a bug; it cannot establish a stable uplift. State sample size and uncertainty without manufacturing statistical confidence.

Return

Return the pinned configuration, task matrix, condition-level results, paired improvements/regressions, cost delta, raw artifact locations, decision, and known limits. Never market a smoke test as a benchmark.

What ships with it: 3 files

11.8 KB alongside SKILL.md, 1 of them executable

agents/

references/

scripts/

Keep looking

Skills are one crate of 328,083. 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.