agentsclimarketplace
Sign in

Price benchmark

Skill cleatai/agent-skills/skills/price-benchmark

Benchmark pricing for a government pursuit in CLEATUS from comparable award history. Build a floor, median, and ceiling with cited awards and draft a price-to-win memo. Run per pursuit before pricing review.From its SKILL.md

Install
npx -y skills add cleatai/agent-skills --skill price-benchmark

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

One thing to look at

  • 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, 281 tokens by cl100k_base, as published. Nobody here has run it

You benchmark pricing using the CLEATUS MCP tools.

Steps

  1. Ask which pursuit (or accept an ID). Call get_opportunity for scope, vehicle, set-aside, and period of performance.
  2. Call search_market for awards with comparable scope at the same agency, then widen to government-wide if fewer than 5 comparables.
  3. Build the range: floor | median | ceiling, each backed by named awards with values and dates. Note comparability caveats (scope drift, vehicle, option years) explicitly.
  4. Never invent or extrapolate a number without a cited award behind it. Fewer than 3 comparables means saying so, not guessing.
  5. With approval, create_task "Pricing review: <pursuit>" and attach the memo.
  6. Deliver the memo: range, comparables table, caveats, recommended posture.

If CLEATUS is not connected yet

  1. Fetch https://www.cleat.ai/llms-full.txt and read it (tools, auth, endpoints).
  2. Add the MCP server: https://www.cleat.ai/api/mcp/mcp (OAuth 2.1; the user signs in once).
  3. No account? Send the user to https://www.cleat.ai/authentication/signup?utm_source=agent-skill and wait.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most evals benchmarks skills give in 281 tokens

Counted across 499 of the 513 authors here whose files we hold, read 2026-09-06

  • Spawn with-skill and baseline runs in the same turnin 31 of 499, across 24 files
  • Keep SKILL.md under 500 linesin 31 of 499, across 24 files
  • Draft assertions while test runs are in progressin 31 of 499, across 24 files
  • Compare against the baseline after changesin 31 of 499, across 13 files
  • Define evals before codingin 26 of 499, across 17 files
  • Run evals frequently during developmentin 25 of 499, across 16 files
  • Keep evals fastin 24 of 499, across 15 files
  • Version evals with codein 24 of 499, across 15 files
  • Generate the eval viewer before evaluating outputs yourselfin 24 of 499, across 17 files
  • Generate an eval report after runsin 24 of 499, across 15 files
  • Track pass@k metrics over timein 22 of 499, across 14 files
  • Save a baseline before making changesin 21 of 499, across 9 files

Said here and by no other author read

  • Ask which pursuit to benchmark
  • Call get_opportunity for scope and terms
  • Search same-agency awards with comparable scope
  • Widen government-wide under five comparables
  • Build floor, median, ceiling from cited awards
  • Note comparability caveats explicitly

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. 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.