agentsclimarketplace

Repo launch readiness review

Skill alexzhu0/agent-ready-skills/skills/repo-launch-readiness-review

Ten practical AI-agent skills for turning messy work into clear context, evals, reviews, and launch-ready artifacts.

Install
npx -y skills add alexzhu0/agent-ready-skills --skill repo-launch-readiness-review

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.

What its author says it does

Copied from the file, not written here

Use when reviewing a small repository before public launch for README clarity, examples, license, metadata, validation commands, issue hygiene, release notes, and obvious trust gaps.

SKILL.md

1.5 KB, as published. Nobody here has run it

Repo Launch Readiness Review

Purpose

Check whether a small repository is understandable, usable, and safe to publish.

Fit

  • Use when a repo is close to public release and needs a final trust/readiness review.
  • Do not use when the repo still lacks a working artifact or the task is deep implementation.

Inputs

  • Repository README, file tree, metadata, examples, license, and release notes.
  • Target audience, launch channel, and install path if available.
  • Known validation commands and open issues.

Workflow

  1. Review whether a new visitor can understand the repo in under one minute.
  2. Check install, quickstart, examples, license, security, and contribution paths.
  3. Identify missing trust signals and confusing claims.
  4. Score readiness and list launch blockers separately from polish.
  5. Recommend the smallest changes before publishing.

Output

Produce Markdown with:

  • Readiness Score
  • Visitor Summary
  • Launch Blockers
  • Trust And Metadata Checks
  • Example Quality
  • Polish Tasks
  • Recommendation

Validation

  • Score rationale is visible.
  • Blockers are separated from nice-to-have tasks.
  • Claims in README are checked against files.
  • Missing license or unsafe instructions are treated as blockers.
  • Recommendations are small and release-oriented.

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.