Agent skill

Coupling Full Review

by nwiizo in nwiizo/cargo-coupling

Review a Rust project's architecture across coupling, change risks, and idiomatic code.

MITAuto-check passedDevelopment

Install Coupling Full Review

skills CLI
$ npx skills add nwiizo/cargo-coupling --skill coupling-full-review -a claude-code

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

GitHub CLI
$ gh skill install nwiizo/cargo-coupling coupling-full-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/nwiizo/cargo-coupling.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/coupling-full-review .claude/skills/coupling-full-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
coupling-full-review
GitHub stars
112
Token cost
~443 tokens
SKILL.md length
210 words
Files
2
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Review a Rust project's architecture across coupling, change risks, and idiomatic code.

  • Comprehensive code reviews
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Use coupling-review for module boundaries alone

What it does

Coupling Full Review is an agent skill from nwiizo/cargo-coupling. Review a Rust project's architecture across coupling, change risks, and idiomatic code. Use for comprehensive code reviews; use coupling-review for module boundaries alone.

Its SKILL.md is about 440 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `output-template.md`).

It sits in Development, covering Code review. It works with Rust. The repository describes itself as: A coupling analysis tool for Rust projects - measuring the 'right distance' in your code. The licence is MIT.

When your agent uses it

  • Comprehensive code reviews
  • Use coupling-review for module boundaries alone

Example prompts

  • “/coupling-full-review”

What it can do on your machine

Read from SKILL.md and the folder at commit 8ef1441. 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.

Context cost

Coupling Full Review loads about 443 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 210 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
~443

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 nwiizo/cargo-coupling at commit 8ef1441, republished under its MIT licence (© nwiizo). 210 words, ~443 tokens.

Download SKILL.mdSave it as .claude/skills/coupling-full-review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
coupling-full-review
description
Review a Rust project's architecture across coupling, change risks, and idiomatic code. Use for comprehensive code reviews; use coupling-review for module boundaries alone.
argument-hint
[path]

Full Architecture Review

Review the requested scope (default ./src) and produce evidence-backed priorities. Use coupling-review for coupling analysis, then inspect the relevant architecture boundaries and Rust implementation. Reuse current analysis results.

Consider coupling balance, architectural change risks, and Rust idioms as review perspectives. Apply each where it can reveal a consequential problem; named personas, separate agents, numeric expert scores, and fixed schedules are not required. Delegate only when the user or applicable instructions request delegation, with a bounded subtask for each agent.

Use history or a baseline when the question concerns trends or a PR. Run tests, lint, or structural diagnostics when needed to substantiate findings or required by repository policy. Report which checks actually ran and any missing coverage; do not run duplicate output modes or repeat unchanged passing checks as phases.

Consolidate findings with source locations, impact, confidence, and concrete next actions. Separate automated signals from conclusions verified in code. Preserve good boundaries, stable hubs, and the analysis blind spots. Use the report example when a structured report helps, adapting it to the request and omitting unsupported scores or empty sections.

Complete the review with supported findings and limits. If fixes are also requested, apply and verify the agreed scope without treating the report as a mandatory pause.

© nwiizo, MIT. 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 1 other file in .agents/skills/coupling-full-review of nwiizo/cargo-coupling.

  • SKILL.md
  • output-template.md

Open the folder on GitHubat commit 8ef1441

Compare with similar skills

Coupling Full 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.

Coupling Full Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Coupling Full Review this skillnwiizo/cargo-coupling112—~443Automated safety check: PassMIT
Worktrunk Tend CI Guidancemax-sixty/worktrunk9.2k—~6.4kAutomated safety check: PassCustom licence
SeekDB Code Reviewoceanbase/seekdb3.1k—~2.1kAutomated safety check: PassApache-2.0
PR Reviewjaemk/self_update961—~1.5kAutomated safety check: NotesMIT
PR Reviewjaemk/cached2.1k—~2.5kAutomated safety check: NotesMIT
Cross-Language Coding Standardszereight/gitlab-mcp2k1 repos~1.4kAutomated safety check: PassMIT

Similar skills

  • Worktrunk Tend CI Guidance

    max-sixty/worktrunk

    Adds Worktrunk-specific rules to the tend CI workflows: Codecov polling, Rust test commands, labels and review criteria for pull requests handled in CI.

    9.2k GitHub stars~6.4k tokensUpdated today
    DevelopmentAuto-check passed
  • SeekDB Code Review

    oceanbase/seekdb

    Reviews seekdb pull requests and diffs for real defects in correctness, resources, concurrency, security and tests, reporting only Blocker or Major findings.

    3.1k GitHub stars~2.1k tokensUpdated today
    DevelopmentAuto-check passed
  • PR Review

    jaemk/self_update

    Targeted, read-only review of a PR or checked-out branch. An agent skill from jaemk/self_update.

    961 GitHub stars~1.5k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes
  • PR Review

    jaemk/cached

    Targeted, read-only review of a PR or checked-out branch. An agent skill from jaemk/cached.

    2.1k GitHub stars~2.5k tokensUpdated 9 days ago
    DevelopmentAuto-check: notes
  • Shared reference for naming, function size, complexity and error handling rules that reviewer agents apply across TypeScript, Python, Go, Rust, Java, C# and Swift.

    2k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed
  • Resolve PR Review

    shencangsheng/easydb_app

    Resolve pull request code review comments end-to-end. An agent skill from shencangsheng/easydb_app.

    590 GitHub stars~2.4k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from nwiizo/cargo-coupling

All 14 skills in this repo
  • Balanced Coupling

    nwiizo/cargo-coupling

    Interpret coupling tradeoffs using Khononov's strength, distance, and volatility model.

    112 GitHub stars~530 tokensUpdated today
    Auto-check passed
  • Release

    nwiizo/cargo-coupling

    Prepare or publish a cargo-coupling version when the user requests a release.

    112 GitHub stars~514 tokensUpdated today
    Auto-check passed
  • Similarity

    nwiizo/cargo-coupling

    Inspect Rust duplicate-code candidates with similarity-rs. An agent skill from nwiizo/cargo-coupling.

    112 GitHub stars~492 tokensUpdated today
    Auto-check passed
  • Cargo Coupling

    nwiizo/cargo-coupling

    Explain cargo-coupling CLI options and .coupling.toml configuration.

    112 GitHub stars~301 tokensUpdated today
    Auto-check passed
  • Check Balance

    nwiizo/cargo-coupling

    Check a Rust project's cargo-coupling health grade or run a requested CI gate.

    112 GitHub stars~323 tokensUpdated today
    Auto-check passed
  • Coupling Review

    nwiizo/cargo-coupling

    Review Rust module boundaries and implicit coupling using cargo-coupling and source evidence.

    112 GitHub stars~425 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Coupling Full Review

What does Coupling Full Review do?

Review a Rust project's architecture across coupling, change risks, and idiomatic code. Coupling Full Review is an agent skill from nwiizo/cargo-coupling. Review a Rust project's architecture across coupling, change risks, and idiomatic code.

When should I use Coupling Full Review?

Coupling Full Review fits situations like: comprehensive code reviews; use coupling-review for module boundaries alone.

How do I install Coupling Full Review in Claude Code?

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

How do I install Coupling Full Review in Codex?

Run `npx skills add nwiizo/cargo-coupling --skill coupling-full-review -a codex`. Or copy the skill folder (.agents/skills/coupling-full-review in nwiizo/cargo-coupling) into .agents/skills/coupling-full-review in your project. Codex loads it when a task matches its description.

Can I use Coupling Full 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 nwiizo/cargo-coupling --skill coupling-full-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/coupling-full-review, .gemini/skills/coupling-full-review, .github/skills/coupling-full-review and .opencode/skills/coupling-full-review in your project.

What does Coupling Full Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Coupling Full Review is instructions for the agent only.

Does Coupling Full Review 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 Coupling Full 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 Coupling Full Review use?

Coupling Full Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Coupling Full Review use?

About 443 tokens (SKILL.md is roughly 1.8k 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 Coupling Full Review?

Skills that share tags, products or a category with Coupling Full Review: Worktrunk Tend CI Guidance (max-sixty/worktrunk, 9.2k stars), SeekDB Code Review (oceanbase/seekdb, 3.1k stars), PR Review (jaemk/self_update, 961 stars) and PR Review (jaemk/cached, 2.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Coupling Full Review?

nwiizo (a GitHub user) maintains it in nwiizo/cargo-coupling, which has 112 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 10, 2026.

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