Agent skill

Review Duplicates

by nwiizo in nwiizo/ccswarm

Duplicate code detection using similarity-rs. An agent skill from nwiizo/ccswarm.

MITAuto-check passedDevelopment

Install Review Duplicates

skills CLI
$ npx skills add nwiizo/ccswarm --skill review-duplicates -a claude-code

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

GitHub CLI
$ gh skill install nwiizo/ccswarm review-duplicates --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/ccswarm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/review-duplicates .claude/skills/review-duplicates && 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
review-duplicates
GitHub stars
153
Token cost
~327 tokens
SKILL.md length
114 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Duplicate code detection using similarity-rs. An agent skill from nwiizo/ccswarm.

  • Tasks that involve Refactoring
  • Calls cargo

What it does

Review Duplicates is an agent skill from nwiizo/ccswarm. Duplicate code detection using similarity-rs. Identifies refactoring candidates based on semantic similarity.

Its SKILL.md is about 330 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 Development, covering Refactoring. The repository describes itself as: Multi-agent orchestration system using Claude Code with Git worktree isolation and specialized AI agents for collaborative development. The licence is MIT.

When your agent uses it

  • Tasks that involve Refactoring

Example prompts

  • “/review-duplicates”

What it can do on your machine

Read from SKILL.md and the folder at commit 611bf15. 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:

    • cargo

    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

Review Duplicates loads about 327 tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 114 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~327

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/ccswarm at commit 611bf15, republished under its MIT licence (© nwiizo). 114 words, ~327 tokens.

Download SKILL.mdSave it as .claude/skills/review-duplicates/SKILL.md (or your agent's skills folder).
name
review-duplicates
description
Duplicate code detection using similarity-rs. Identifies refactoring candidates based on semantic similarity.
user-invocable
true
context
fork
agent
code-refactor-agent

When subagents are enabled in Codex, prefer delegating this workflow to the code-refactor-agent custom agent.

Detect duplicate code in the ccswarm codebase using similarity-rs.

bash
similarity-rs crates/ --threshold 0.80

For Rust code, also consult cargo coupling so duplicate cleanup is prioritized by architectural impact, not only by textual similarity.

bash
cargo coupling . --summary --exclude-tests
cargo coupling . --hotspots=12 --exclude-tests

If a duplicate cluster is located in a coupling hotspot, high-risk boundary, or cycle-related module, raise its refactoring priority accordingly.

Classify results by priority:

PriorityConditionAction
High95%+ similarity, 10+ linesExtract to common function
Medium90-95% similarity, 5+ linesConsider trait or macro
Low85-90% similarityEvaluate structural similarity
SkipTest code, config structsAllow intentional duplication

Output a JSON report with high_priority, medium_priority, low_priority, and ignored sections.

© 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

Just SKILL.md in .agents/skills/review-duplicates of nwiizo/ccswarm.

Open the folder on GitHubat commit 611bf15

Compare with similar skills

Review Duplicates 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.

Review Duplicates compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review Duplicates this skillnwiizo/ccswarm153—~327Automated safety check: PassMIT
Guidelinesakash-network/node1.1k20 repos~577Automated safety check: PassMIT
Migrate Core Code to Submodulestinyhumansai/openhuman42k—~2.6kAutomated safety check: PassGPL-3.0
Component Refactoringlangflow-ai/langflow155k—~3.5kAutomated safety check: PassMIT
Ponytail Lazy Developer ModeDietrichGebert/ponytail160k1 repos~873Automated safety check: PassMIT
ast-grep Structural Searchcode-yeongyu/oh-my-openagent70k—~3.3kAutomated safety check: PassMIT

Similar skills

  • Guidelines

    akash-network/node

    Behavioral guidelines to reduce common LLM coding mistakes. An agent skill from akash-network/node.

    1.1k GitHub starsUsed in 20 repos~577 tokens
    DevelopmentAuto-check passed
  • Migrate Core Code to Submodules

    tinyhumansai/openhuman

    Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.

    42k GitHub stars~2.6k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Component Refactoring

    langflow-ai/langflow

    Refactor high-complexity React components in Langflow frontend.

    155k GitHub stars~3.5k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Ponytail Lazy Developer Mode

    DietrichGebert/ponytail

    Makes the agent pick the laziest solution that works: skip unneeded work, reuse what exists, prefer the standard library and platform features, and keep diffs small.

    160k GitHub starsUsed in 1 repo~873 tokens
    DevelopmentAuto-check passed
  • ast-grep Structural Search

    code-yeongyu/oh-my-openagent

    Searches and rewrites code by syntax-tree shape across 25 languages with ast-grep, for codemods, structural queries and YAML lint rules, using a Python wrapper script.

    70k GitHub stars~3.3k tokensUpdated today
    DevelopmentAuto-check passed
  • Systematic Code Refactoring

    luongnv89/claude-howto

    Guides refactoring in phases based on Martin Fowler's method: research, test coverage check, planning and small tested steps, with your approval at each phase.

    42k GitHub stars~3k tokensUpdated 10 days ago
    DevelopmentAuto-check passed

More from nwiizo/ccswarm

All 12 skills in this repo
  • Deploy Workflow

    nwiizo/ccswarm

    Release deployment process for ccswarm. An agent skill from nwiizo/ccswarm.

    153 GitHub stars~582 tokensUpdated yesterday
    Auto-check passed
  • Review Fix

    nwiizo/ccswarm

    Review uncommitted changes, fix actionable correctness issues, and verify the result.

    153 GitHub stars~596 tokensUpdated yesterday
    Auto-check passed
  • Review Fix

    nwiizo/ccswarm

    Code review with automatic fix. An agent skill from nwiizo/ccswarm.

    153 GitHub stars~640 tokensUpdated yesterday
    Auto-check passed
  • Review Fix

    nwiizo/ccswarm

    Code review with automatic fix. An agent skill from nwiizo/ccswarm.

    153 GitHub stars~576 tokensUpdated yesterday
    Auto-check passed
  • Nwiizo Coding Style

    nwiizo/ccswarm

    nwiizoの方針でコードを実装・修正し、過剰設計をレビューする。最小実装・YAGNIの依頼にも使う。Rustでは型・所有権・依存の選定、Edition・MSRVに応じた機能選択と構造診断を行う。

    153 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Benchmark Runner

    nwiizo/ccswarm

    Run performance benchmarks with criterion. An agent skill from nwiizo/ccswarm.

    153 GitHub stars~199 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Review Duplicates

What does Review Duplicates do?

Duplicate code detection using similarity-rs. An agent skill from nwiizo/ccswarm. Review Duplicates is an agent skill from nwiizo/ccswarm. Duplicate code detection using similarity-rs.

When should I use Review Duplicates?

Review Duplicates fits situations like: tasks that involve Refactoring.

How do I install Review Duplicates in Claude Code?

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

How do I install Review Duplicates in Codex?

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

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

What does Review Duplicates need to run?

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

Does Review Duplicates 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 Review Duplicates 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 Review Duplicates use?

Review Duplicates 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 Review Duplicates use?

About 327 tokens (SKILL.md is roughly 1.3k 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 Review Duplicates?

Skills that share tags, products or a category with Review Duplicates: Guidelines (akash-network/node, 1.1k stars), Migrate Core Code to Submodules (tinyhumansai/openhuman, 42k stars), Component Refactoring (langflow-ai/langflow, 155k stars) and Ponytail Lazy Developer Mode (DietrichGebert/ponytail, 160k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review Duplicates?

nwiizo (a GitHub user) maintains it in nwiizo/ccswarm, which has 153 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 9, 2026.

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