New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Ship It

by Smana in Smana/cloud-native-ref

Take a finished branch through the full pre-merge pipeline in one pass — rebase onto origin/main, simplify, prune prose, run the repo's validators and cite their output, review the diff, act on…

Apache-2.0Auto-check passedDevelopment

Install Ship It

skills CLI
$ npx skills add Smana/cloud-native-ref --skill ship-it -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Smana/cloud-native-ref ship-it --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Smana/cloud-native-ref.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/ship-it .claude/skills/ship-it && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ship-it
GitHub stars
103
Token cost
~1.1k tokens
SKILL.md length
510 words
Files
3 (incl. references)
Skills in repo
6
Repo updated
First seen
Licence
Apache-2.0

At a glance

Take a finished branch through the full pre-merge pipeline in one pass — rebase onto origin/main, simplify, prune prose, run the repo's validators and cite their output, review the diff, act on…

  • Works in 8 steps: Commit what exists → Rebase → Simplify → …
  • The user says ship it
  • SKILL.md covers 1. Commit what exists, 2. Rebase, 3. Simplify and 4. Prune prose, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ship It is an agent skill from Smana/cloud-native-ref. Take a finished branch through the full pre-merge pipeline in one pass — rebase onto origin/main, simplify, prune prose, run the repo's validators and cite their output, review the diff, act on findings, then commit and open the PR. Use when the user says "ship it", "ready to merge", "open the PR", "this is done", "review and ship", or when implementation is complete and the next step is getting it reviewed and merged.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/evidence.md` and `references/prose.md`). Compatibility notes: Requires git, gh, and the repo's validation scripts

It sits in Development, covering Code review. The repository describes itself as: Opiniated Cloud Native Platform Reference. The licence is Apache-2.0.

When your agent uses it

  • The user says ship it
  • Review and ship
  • Implementation is complete and the next step is getting it reviewed and merged

Example prompts

  • “ship it”
  • “ready to merge”
  • “open the PR”
  • “/ship-it”

Requirements

  • Compatibility (from SKILL.md): Requires git, gh, and the repo's validation scripts

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Commit what exists
  2. Rebase
  3. Simplify
  4. Prune prose
  5. Evidence gate
  6. Review
  7. Act on findings
  8. Commit, push, open the PR

What it can do on your machine

Read from SKILL.md and the folder at commit e5ee7e1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires git, gh, and the repo's validation scripts

    From compatibility in the SKILL.md frontmatter.

Context cost

Ship It loads about 1.1k tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 108 tokens; SKILL.md has 510 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~108
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Smana/cloud-native-ref at commit e5ee7e1, republished under its Apache-2.0 licence (© Smana). 510 words, ~1,134 tokens.

Download SKILL.mdSave it as .claude/skills/ship-it/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
ship-it
description
Take a finished branch through the full pre-merge pipeline in one pass — rebase onto origin/main, simplify, prune prose, run the repo's validators and cite their output, review the diff, act on findings, then commit and open the PR. Use when the user says "ship it", "ready to merge", "open the PR", "this is done", "review and ship", or when implementation is complete and the next step is getting it reviewed and merged.
compatibility
Requires git, gh, and the repo's validation scripts

Ship it

One ordered pipeline from "implementation done" to "PR open". The order is the point: each stage feeds the next, and running them out of order wastes the work of the ones before it.

1. commit          get the work onto the branch, so nothing can be stranded
2. sync-branch     rebase onto origin/main, so every later stage sees the real merge base
3. simplify        quality cleanup, while the diff is still yours to reshape
4. prune prose     comment + doc concision pass
5. evidence gate   run the validators, cite the output
6. review          the reviewer sees the final shape, not a draft
7. act on findings fix, then re-run the evidence for whatever moved
8. commit + push + PR

Stop at any stage that fails. A stage that cannot pass is a finding, not something to note and carry forward.

1. Commit what exists

Run the commit skill on whatever is uncommitted. This comes first for a mechanical reason: sync-branch refuses to rebase a dirty tree, so the pipeline cannot reach stage 2 from the state it is normally invoked in — implementation finished, nothing committed yet.

If the work is already committed, skip straight to stage 2.

2. Rebase

Run the sync-branch skill. A review against a stale merge base reviews code that will not merge.

Do not let it push here. Stages 3–7 will rewrite the branch again; publishing now would force-push twice and diverge anyone else's checkout for no reason. The push belongs to stage 8.

3. Simplify

Reuse, simplification, efficiency, altitude. Quality only — this is not the bug hunt.

Host mapping: /simplify in Claude Code; otherwise review the diff yourself against those four axes. Keep it to code you actually changed.

4. Prune prose

Apply the gauntlet in references/prose.md to every comment, doc and message this branch adds or touches. The bar is asymmetric: deleting a real warning costs more than leaving a mediocre comment, so keep anything you are unsure about and flag it.

5. Evidence gate

No "done / fixed / passing / ready" claim without a fresh command run in the same response. Previous runs do not count — file and cluster state drift.

The claim-to-command table is in references/evidence.md. Identify which claims this branch makes, run those commands now, and cite the output inline as numbers or an exit code, never as prose.

Show full SKILL.md (208 more words)Show less

6. Review

Match effort to blast radius, not to diff size:

ChangeEffort
Single-file fix, version bump, doc editlow
New manifest, chart values, claimmedium
New stack, composition pin, security or network policyhigh
Anything touching PKI, IAM, or the OpenBao lineagemax

Host mapping: /code-review <effort> in Claude Code. Elsewhere, dispatch a reviewer with crafted context — the diff, the requirements, the base and head SHAs — never the session history. The reviewer should evaluate the work product, not your reasoning about it.

7. Act on findings

Fix the real ones. Push back, with technical reasoning, on the ones that are wrong — a reviewer being confidently mistaken is common, and implementing a bad suggestion to seem agreeable is worse than arguing.

Check the reviewer's arithmetic before repeating it, and check your own. A number in a commit message or an ADR is a permanent claim; re-derive it from the source rather than from an earlier summary of it.

Any file you touch here re-enters stage 5. Re-run its evidence command.

8. Commit, push, open the PR

Run the commit skill for everything stages 3–7 produced, then create-pr, which pushes. Both already carry the repo's conventions; do not restate them here.

Report

One line per stage, with the evidence:

committed 3 files
rebased 4 commits onto origin/main (a1b2c3d), not pushed
simplify: 2 changes
prune: 11 comments deleted, 1 flagged
validate-manifests.sh: exit 0, Invalid: 0, Skipped: 0
review (high): 3 findings, 2 fixed, 1 disputed
PR #1234

© Smana, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in .agents/skills/ship-it of Smana/cloud-native-ref.

  • SKILL.md
  • references/evidence.md
  • references/prose.md

Open the folder on GitHubat commit e5ee7e1

Compare with similar skills

Ship It next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ship It compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ship It this skillSmana/cloud-native-ref103—~1.1kAutomated safety check: PassApache-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Backend Code Reviewlangflow-ai/langflow156k—~3.5kAutomated safety check: NotesMIT
Understand Diff AnalysisEgonex-AI/Understand-Anything86k1 repos~1.4kAutomated safety check: PassMIT
Mole Bug Patternstw93/Mole70k—~2kAutomated safety check: PassGPL-3.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Backend Code Review

    langflow-ai/langflow

    Review backend code for quality, security, maintainability, and best practices based on established checklist rules.

    156k GitHub stars~3.5k tokensUpdated today
    DevelopmentAuto-check: notes

  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    86k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed

  • Mole Bug Patterns

    tw93/Mole

    A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.

    70k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed

  • Backend Code Review

    langgenius/dify

    Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.

    158k GitHub stars~676 tokensUpdated today
    DevelopmentAuto-check passed

More from Smana/cloud-native-ref

  • Commit

    Smana/cloud-native-ref

    Run pre-commit validation before committing. An agent skill from Smana/cloud-native-ref.

    103 GitHub stars~778 tokensUpdated today
    Auto-check passed

  • Sync Branch

    Smana/cloud-native-ref

    Rebase the current branch onto the latest origin/main before pushing, reviewing, or opening a PR.

    103 GitHub stars~966 tokensUpdated today
    Auto-check passed

  • Create PR

    Smana/cloud-native-ref

    Create or update a Pull Request with AI-generated description, mermaid diagram, file walkthrough, and automatic design-doc detection.

    103 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Spec Research

    Smana/cloud-native-ref

    Research patterns, ecosystem tools, and best practices before writing a design.

    103 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Verify Spec

    Smana/cloud-native-ref

    Verify that a merged design's success criteria are actually met in the live cluster.

    103 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

Categories

Questions about Ship It

What does Ship It do?

Take a finished branch through the full pre-merge pipeline in one pass — rebase onto origin/main, simplify, prune prose, run the repo's validators and cite their output, review the diff, act on…. Ship It is an agent skill from Smana/cloud-native-ref. Take a finished branch through the full pre-merge pipeline in one pass — rebase onto origin/main, simplify, prune prose, run the repo's validators and cite their output, review the diff, act on findings, then commit and open the PR.

When should I use Ship It?

Ship It fits situations like: the user says ship it; review and ship; implementation is complete and the next step is getting it reviewed and merged.

How do I install Ship It in Claude Code?

Run `npx skills add Smana/cloud-native-ref --skill ship-it -a claude-code`. Or copy the skill folder (.agents/skills/ship-it in Smana/cloud-native-ref) into .claude/skills/ship-it in your project. Claude Code loads it when a task matches its description.

How do I install Ship It in Codex?

Run `npx skills add Smana/cloud-native-ref --skill ship-it -a codex`. Or copy the skill folder (.agents/skills/ship-it in Smana/cloud-native-ref) into .agents/skills/ship-it in your project. Codex loads it when a task matches its description.

Can I use Ship It in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Smana/cloud-native-ref --skill ship-it -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ship-it, .gemini/skills/ship-it, .github/skills/ship-it and .opencode/skills/ship-it in your project.

What does Ship It need to run?

SKILL.md names no scripts, command-line tools or credentials: Ship It is instructions for the agent only. Compatibility (from SKILL.md): Requires git, gh, and the repo's validation scripts.

Does Ship It access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ship It safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ship It use?

Ship It is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ship It use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.8k tokens, read only when the agent opens those files.

What are the alternatives to Ship It?

Skills that share tags, products or a category with Ship It: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Backend Code Review (langflow-ai/langflow, 156k stars) and Understand Diff Analysis (Egonex-AI/Understand-Anything, 86k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ship It?

Smana (a GitHub user) maintains it in Smana/cloud-native-ref, which has 103 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 8, 2026.

Source: Smana/cloud-native-ref on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.