agentsclimarketplace
Sign in

Prepare agent release review

Skill TopicalitySummit/summit-decision-assurance/skills/prepare-agent-release-review

Run a public-safe release review that combines Summit Decision Receipt preflight with governed-output declaration checks. Use before an agent report, recommendation, decision artifact, or consequential output is released. Do not use this workflow as an approval, certification, or substitute for human judgment.From its SKILL.md

Install
npx -y skills add TopicalitySummit/summit-decision-assurance --skill prepare-agent-release-review

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

3 things to look at

  • 28 days oldThe repository was created 28 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.
  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 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

1.7 KB, 284 tokens by cl100k_base, as published. Nobody here has run it

Prepare Agent Release Review

Produce a bounded readiness review from the two public Summit checks.

Workflow

  1. Establish scope. Accept only public or synthetic inputs; request a redacted or synthetic substitute for anything sensitive.
  2. Call summit_public_capabilities. Stop if the profile is not public-read-only-v1, the exact three public tools are not present, or the response describes a write-capable surface.
  3. When a Decision Receipt Object Draft is present, follow $preflight-decision-receipt and retain every unresolved issue.
  4. For the output itself, follow $check-governed-output. Send only declaration metadata, never claim text or source content.
  5. Reconcile both results into one release review:
    • ready_for_human_review: both checks report no blocking declaration or structural issue;
    • needs_revision: one or more correctable issues remain;
    • out_of_scope: input classification or requested assurance exceeds the public profile.
  6. List evidence gaps, required human decisions, and concrete next actions. For consequential output, require an actual human review declaration.

Required wording

Describe a passing result as ready for human review, not approved, certified, compliant, admissible, or true. State that Summit's public checks do not validate source truth, signatures, revocation, policy compliance, legal admissibility, or human-review quality.

What ships with it

Read from the repository

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

Gives 0 of the 12 instructions most context ai engineering skills give in 284 tokens

Counted across 1,193 of the 1,976 authors here whose files we hold, read 2026-08-07

  • Dispatch a fresh implementer subagent per taskin 48 of 1193, across 19 files
  • Dispatch a final code reviewer after all tasksin 33 of 1193, across 8 files
  • Provide full task text to the subagentin 30 of 1193, across 9 files
  • Review spec compliance before code qualityin 27 of 1193, across 10 files
  • Make the hook script executablein 26 of 1193, across 8 files
  • Re-snapshot after navigation or DOM changesin 25 of 1193, across 19 files
  • Read files before editing themin 22 of 1193, across 11 files
  • Answer subagent questions before proceedingin 22 of 1193, across 7 files
  • Mark task complete in TodoWrite after approvalin 22 of 1193, across 6 files
  • Merge hook into existing settingsin 21 of 1193, across 3 files
  • Ask if installation is global or projectin 20 of 1193, across 2 files
  • Copy the hook script to target locationin 20 of 1193, across 2 files

Said here and by no other author read

  • establish scope using only public or synthetic inputs
  • call summit_public_capabilities
  • stop if the profile is not public-read-only-v1
  • stop if the three public tools are not present
  • stop if a write-capable surface is present
  • retain every unresolved issue from preflight

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 326,144. 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.