agentsclimarketplace

Ship review

Skill aksheyw/claude-code-ship-gate/plugins/ship-gate/skills/ship-review

Pre-push quality gate for Claude Code that runs above git, so git push --no-verify can't skip it. Tests, code review, security, and a secret scan must pass before any push to your protected branch. Say 'ship it' to run it.

Install
npx -y skills add aksheyw/claude-code-ship-gate --skill ship-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

Ship Gate code-review gate, runs /code-review then applies the distilled checklist and emits Approve/Warning/Block.

SKILL.md

1.0 KB, 202 tokens by cl100k_base, as published. Nobody here has run it

Ship Review

  1. Invoke the /code-review skill on the current diff vs the protected branch (usually main; if the repo uses master or a configured trunk, diff against that: bash "${CLAUDE_PLUGIN_ROOT}/scripts/ship-gate.sh" protected-branch . resolves it when the full plugin is installed). If /code-review is unavailable, dispatch the bundled ship-reviewer agent (via the Task tool) instead. If that agent is also absent (a bare skills install ships only this file and its references), skip this step: step 2's checklist is the review.
  2. Apply references/code-review-checklist.md to the diff for anything /code-review missed.
  3. Emit a verdict: Block (any CRITICAL/HIGH), Warning (only LOW/MEDIUM), or Approve.
  4. Return the verdict and the findings table. Do not push: the orchestrator decides.

What ships with it: 1 file

4.2 KB alongside SKILL.md

references/

Gives 0 of the 12 instructions most review quality skills give in 202 tokens

Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07

  • Ask questions one at a timein 81 of 1048, across 64 files
  • Provide a recommended answer for each questionin 73 of 1048, across 50 files
  • Explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
  • Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
  • Interview the user relentlessly about the planin 38 of 1048, across 13 files
  • Order findings by severityin 31 of 1048
  • Resolve each branch of the decision treein 27 of 1048, across 5 files
  • Run a grilling sessionin 26 of 1048, across 5 files
  • Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
  • Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
  • Create documentation files lazilyin 24 of 1048, across 5 files
  • Assign severity to every findingin 24 of 1048

Said here and by no other author read

  • invoke code-review on the diff vs protected branch
  • skip review invocation if bundled agent is absent
  • apply the code-review checklist to the diff
  • emit a verdict of block warning or approve
  • warn for only low or medium findings
  • return the verdict and findings table

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 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.