Agent skill

Branch Review

by luxury-yacht in luxury-yacht/app

Review a Luxury Yacht branch for merge readiness, production readiness, PR-summary quality, or current-diff risk using read-only git state, repo contracts, and validation evidence

GPL-3.0Auto-check passedDevOps & Cloud

Install Branch Review

skills CLI
$ npx skills add luxury-yacht/app --skill branch-review -a claude-code

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

GitHub CLI
$ gh skill install luxury-yacht/app branch-review --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/luxury-yacht/app.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/branch-review .claude/skills/branch-review && 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
branch-review
GitHub stars
444
Token cost
~1.7k tokens
SKILL.md length
599 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
GPL-3.0

At a glance

Review a Luxury Yacht branch for merge readiness, production readiness, PR-summary quality, or current-diff risk using read-only git state, repo contracts, and validation evidence

  • Works in 3 steps: Use origin/main...HEAD unless the user… → Review committed and working-tree… → Changed docs or plans that claim…
  • DevOps & Cloud work in your project
  • SKILL.md covers Goal, Scope the diff, Contract audit and Validation, plus 1 more section
  • Calls git and mise

What it does

Branch Review is an agent skill from luxury-yacht/app. Review a Luxury Yacht branch for merge readiness, production readiness, PR-summary quality, or current-diff risk using read-only git state, repo contracts, and validation evidence

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud. It works with Git. The repository describes itself as: Luxury Yacht - A cross-platform app for managing Kubernetes clusters and resources. The licence is GPL-3.0.

When your agent uses it

  • DevOps & Cloud work in your project

Example prompts

  • “/branch-review”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Use origin/main...HEAD unless the user gives another base or range. If it
  2. Review committed and working-tree changes; do not skip modified, staged, or
  3. Changed docs or plans that claim completion are hints, not proof; inspect

What it can do on your machine

Read from SKILL.md and the folder at commit 7001a03. 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

    Shell commands in SKILL.md call:

    • git
    • mise

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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.

Context cost

Branch Review loads about 1.7k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 599 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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 luxury-yacht/app at commit 7001a03, republished under its GPL-3.0 licence (© luxury-yacht). 599 words, ~1,671 tokens.

Download SKILL.mdSave it as .claude/skills/branch-review/SKILL.md (or your agent's skills folder).
name
branch-review
description
Review a Luxury Yacht branch for merge readiness, production readiness, PR-summary quality, or current-diff risk using read-only git state, repo contracts, and validation evidence

Branch Review

Use this when the user asks whether a branch is production-ready, merge-ready, an actual improvement, or asks for a branch/PR review or PR summary grounded in the current diff. Stay in read-only review mode unless the user asks for fixes.

Goal

Return a concrete merge-readiness verdict from the code, tests, and current validation state. Findings lead; summaries are secondary. Answer whether the work is complete, correct, safe to merge and release, and a real improvement for users or the codebase, and whether anything important was missed.

Scope the diff

  1. Use origin/main...HEAD unless the user gives another base or range. If it cannot be resolved, inspect remotes and the default branch read-only and state the exact base assumption before reviewing.

  2. Review committed and working-tree changes; do not skip modified, staged, or untracked files because the branch range is empty:

    sh
    git status --short && git branch --show-current
    git diff --stat origin/main...HEAD && git diff --name-only origin/main...HEAD
    git diff --stat && git diff --cached --stat
    git ls-files --others --exclude-standard
  3. Changed docs or plans that claim completion are hints, not proof; inspect the contract paths the diff touches.

Contract audit

Check every meaningful change against the root and scoped AGENTS.md contracts already in context, then read the owning contract for each touched area and verify its review points:

Change areaOwning contractAlso verify
Cross-layer contracts, generated bindings, enum/metadata driftshared-contractsNo parallel frontend/backend enum, descriptor, schema, or registry without a parity test
Multi-cluster, scopes, selected/background clusters, cache keysmulti-cluster, cluster-auth-lifecycleAuth, recovery, operations, streams, and cleanup stay scoped to the affected cluster
Auth failure, recovery, kubeconfig, client lifecycleauth, cluster-auth-lifecycle
Refresh, snapshots, streams, diagnosticsrefresh-system, data-layer, refresh-subsystemDomain metadata, behavior classes, timing, backend/frontend registration, diagnostics, and tests align through the shared domain contract
Query-backed resource streams and WebSocket signalsdata-freshness, data-layerStream messages stay liveness signals; rows, filtering, sorting, facets, totals, and page metadata stay on the HTTP query path; snapshots and signals agree on identity, scope, liveness, and permissions
Identity, status, lifecycle, links, facts, object refsshared-resource-model, skillPrimary status projects status, statusState, statusPresentation, and optional statusReason; relationship navigation uses ResourceLink.ref and catalog-backed identity, never frontend kind/name reconstruction
Kind vocabulary, generated dispatch, per-kind behaviorresource-kind-registry, add-resource
Browse, catalog, discovery, namespace metadata and LIST rowscatalog, refresh-system, browse-tables
Frontend resource reads, app-state reads, storesdata-access
Permissions, capabilities, RBAC UIpermissions, skillPermission-denied and restricted-RBAC behavior stays visible in diagnostics
Tables, query-backed pages, large datasetsgridtable, large-data
Object panel details, YAML, actions, docked panelsobject-panel, yaml-editing, yaml-editor, dockable-panelsYAML read/save/merge/ownership keeps full cluster and GVK identity and the shared field-policy contract
Logs, shell/debug, port-forward, drain, runtime operationsoperations-workflows, logs, shell-debug, operation-lifecycle
Object mapobject-map skill, object-map
UI shell, settings, modals, keyboard, tabsapp-shell, relevant docs/frontend/*.md
Show full SKILL.md (171 more words)Show less

Validation

Run focused checks first when the branch has clear areas:

  • Backend shared, resource-model, or refresh changes: focused mise exec -- go test packages.
  • Frontend changes: targeted Vitest specs and mise exec -- npm run typecheck --prefix frontend.
  • Runtime operations (logs, shell, port-forward, drain): focused backend workflow tests plus affected frontend lifecycle/orchestrator tests.
  • Broad frontend/shared changes: mise exec -- wails3 task qc:knip.

A "ready" verdict requires the root final gate plus git diff --check and git status --short (documentation/comment-only branches may skip qc:prerelease, not the other two). If the gate cannot run or fails, report the exact command and first concrete failure and do not call the branch ready.

Output

  • Findings first, ordered by severity; each gives file/line, problem, impact, and concrete fix direction. Then open questions or assumptions, validation state, and a short verdict.
  • No findings: say no merge-blocking issues were found, exactly what was validated, and the residual risk or untested areas.
  • PR summaries: use the real diff/range; describe user-visible behavior and operational impact; omit touched-file inventories, commit hashes, and unverified claims.

© luxury-yacht, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/branch-review of luxury-yacht/app.

Open the folder on GitHubat commit 7001a03

Compare with similar skills

Branch Review 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.

Branch Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Branch Review this skillluxury-yacht/app444—~1.7kAutomated safety check: PassGPL-3.0
Repo Mirror Sourcesnetdata/netdata81k—~1.2kAutomated safety check: NotesGPL-3.0
CI Failure Triage and RepairChachamaru127/claude-code-harness3.2k1 repos~1.1kAutomated safety check: NotesMIT
Bfe Rd Workflowbfenetworks/bfe6.3k—~1.3kAutomated safety check: PassApache-2.0
Ssh Skillbadseal/ssh-skill538—~2.4kAutomated safety check: NotesNone
GreptimeDB Release RunbookGreptimeTeam/greptimedb6.7k—~1.4kAutomated safety check: PassApache-2.0

Similar skills

  • Repo Mirror Sources

    netdata/netdata

    Inspect Netdata-org source checkouts under NETDATAREPOSDIR, or set up and synchronize that mirror when requested.

    81k GitHub stars~1.2k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • CI Failure Triage and Repair

    Chachamaru127/claude-code-harness

    Diagnoses failing CI pipelines and tests, deciding first whether the test or the implementation is at fault, and hands hard cases to a dedicated fixer subagent.

    3.2k GitHub starsUsed in 1 repo~1.1k tokens
    DevOps & CloudAuto-check: notes
  • Bfe Rd Workflow

    bfenetworks/bfe

    引导用户在 bfe 代码库中完成一次完整的功能研发流程,包括需求对齐、文档修改、代码实现、集成测试与回归验证. An agent skill from bfenetworks/bfe.

    6.3k GitHub stars~1.3k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Ssh Skill

    badseal/ssh-skill

    A skill your agent uses when a task requires SSH or SCP/SFTP behavior, a remote server, server alias/IP/hostname/user@host, bastion or jump-host access, remote command execution, upload/download…

    538 GitHub stars~2.4k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check: notes
  • GreptimeDB Release Runbook

    GreptimeTeam/greptimedb

    Runbook for publishing a GreptimeDB version: pick the release branch, verify the Cargo version, then tag, create the GitHub release and open the docs note PR.

    6.7k GitHub stars~1.4k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Crabbox Quickstart

    openclaw/crabbox

    Gets you running your repository's tests in a disposable Docker or Podman container on your own machine with Crabbox, with no account and no cloud spend.

    1.5k GitHub stars~1.6k tokensUpdated today
    DevOps & CloudAuto-check: notes

More from luxury-yacht/app

All 17 skills in this repo
  • Improve Backend

    luxury-yacht/app

    A skill your agent uses when wanting to systematically improve the Go backend - scans for security vulnerabilities, stability risks, performance issues, and code simplification opportunities, then…

    444 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Improve Frontend

    luxury-yacht/app

    A skill your agent uses when wanting to systematically improve the React/TypeScript frontend - scans for security vulnerabilities, stability risks, performance issues, and code simplification…

    444 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Eliminate representable-but-invalid Luxury Yacht states with discriminated unions, required identity, typed status, validated constructors, or one boundary chokepoint; use for "make impossible…

    444 GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Add Resource

    luxury-yacht/app

    Add or extend support for a Kubernetes resource kind across the required catalog, refresh, detail, object-panel, object-map, permission, documentation, and test surfaces

    444 GitHub stars~704 tokensUpdated today
    Auto-check passed
  • App Review

    luxury-yacht/app

    Audit broad Luxury Yacht systems or cross-cutting concerns for structural simplification, hardening, optimization, or refactoring; use for app-wide reviews and phased structural plans, not branch…

    444 GitHub stars~818 tokensUpdated today
    Auto-check passed
  • Browse Tables

    luxury-yacht/app

    Change cluster or namespace views, Browse/catalog surfaces, shared GridTable behavior, filters, pagination, large datasets, metrics columns, or refresh-backed resource tables

    444 GitHub stars~518 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Branch Review

What does Branch Review do?

Review a Luxury Yacht branch for merge readiness, production readiness, PR-summary quality, or current-diff risk using read-only git state, repo contracts, and validation evidence. Branch Review is an agent skill from luxury-yacht/app.

When should I use Branch Review?

Branch Review fits situations like: devOps & Cloud work in your project.

How do I install Branch Review in Claude Code?

Run `npx skills add luxury-yacht/app --skill branch-review -a claude-code`. Or copy the skill folder (.agents/skills/branch-review in luxury-yacht/app) into .claude/skills/branch-review in your project. Claude Code loads it when a task matches its description.

How do I install Branch Review in Codex?

Run `npx skills add luxury-yacht/app --skill branch-review -a codex`. Or copy the skill folder (.agents/skills/branch-review in luxury-yacht/app) into .agents/skills/branch-review in your project. Codex loads it when a task matches its description.

Can I use Branch Review 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 luxury-yacht/app --skill branch-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/branch-review, .gemini/skills/branch-review, .github/skills/branch-review and .opencode/skills/branch-review in your project.

What does Branch Review need to run?

Going by SKILL.md and its folder, Branch Review needs the command-line tools its instructions call (git and mise).

Does Branch Review access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Branch Review 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 Branch Review use?

Branch Review is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Branch Review use?

About 1.7k tokens (SKILL.md is roughly 6.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Branch Review?

Skills that share tags, products or a category with Branch Review: Repo Mirror Sources (netdata/netdata, 81k stars), CI Failure Triage and Repair (Chachamaru127/claude-code-harness, 3.2k stars), Bfe Rd Workflow (bfenetworks/bfe, 6.3k stars) and Ssh Skill (badseal/ssh-skill, 538 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Branch Review?

luxury-yacht (a GitHub organization) maintains it in luxury-yacht/app, which has 444 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 10, 2026.

Source: luxury-yacht/app on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.