Agent skill

React Refactor Tournament

by ragnar-pwninskjold in ragnar-pwninskjold/tech-snacks

Review React/Next.js code against the real vercel-react-best-practices skill, backlog the performance findings keyed to actual rule ids + impact tiers, rank the most over-subscribed tiers, then fix…

MITAuto-check passedDevelopment

Install React Refactor Tournament

skills CLI
$ npx skills add ragnar-pwninskjold/tech-snacks --skill react-refactor-tournament -a claude-code

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

GitHub CLI
$ gh skill install ragnar-pwninskjold/tech-snacks react-refactor-tournament --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/ragnar-pwninskjold/tech-snacks.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/tech-snacks/skills/react-refactor-tournament .claude/skills/react-refactor-tournament && 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
react-refactor-tournament
GitHub stars
137
Token cost
~1.3k tokens
SKILL.md length
614 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Review React/Next.js code against the real vercel-react-best-practices skill, backlog the performance findings keyed to actual rule ids + impact tiers, rank the most over-subscribed tiers, then fix…

  • Works in 6 steps: Preflight — resolve the… → Scope — detect the framework and group… → Discover — parallel reviewers invoke the… → …
  • The user wants to systematically harvest and fix React/Next.js PERFORMANCE refactors (waterfalls
  • SKILL.md covers Requirements (check first), Resolve the bundled workflow…, Gather inputs and Run it, plus 1 more section
  • Calls git

What it does

React Refactor Tournament is an agent skill from ragnar-pwninskjold/tech-snacks. Review React/Next.js code against the real vercel-react-best-practices skill, backlog the performance findings keyed to actual rule ids + impact tiers, rank the most over-subscribed tiers, then fix + test the top N in isolated worktrees. Use when the user wants to systematically harvest and fix React/Next.js PERFORMANCE refactors (waterfalls, bundle size, RSC fetching, re-renders, JS perf), or says "react refactor tournament", "find React performance refactors", "/react-refactor-tournament".

Its SKILL.md is about 1.3k 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, React components and Git worktrees. It works with React, Next.js and Vercel. The repository describes itself as: A skill library for vibe coders that make cool stuff. The licence is MIT.

When your agent uses it

  • The user wants to systematically harvest and fix React/Next.js PERFORMANCE refactors (waterfalls
  • Says react refactor tournament
  • Find React performance refactors
  • /react-refactor-tournament

Example prompts

  • “react refactor tournament”
  • “find React performance refactors”
  • “/react-refactor-tournament”
  • “/react-refactor-tournament”

Requirements

  • Pre-approved tools (allowed-tools): Workflow, Bash(echo *)

Workflow steps

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

  1. Preflight — resolve the vercel-react-best-practices skill install path; abort if missing.
  2. Scope — detect the framework and group React component dirs into disjoint review areas.
  3. Discover — parallel reviewers invoke the skill and emit candidates keyed to real rule ids
  4. Backlog — dedup, assign stable ids, and write .pro-brown/refactors/BACKLOG.{json,md}.
  5. Rank — order by impact tier (free); a single lazy tie-break ranker re-orders only an
  6. Fix (skipped when n=0) — fix the top N in isolated worktrees, write tests where feasible,

What it can do on your machine

Read from SKILL.md and the folder at commit 2d9a73b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Workflow
    • Bash(echo *)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    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

React Refactor Tournament loads about 1.3k tokens when it runs. Until then it costs about 131 tokens; SKILL.md has 614 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~131
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 ragnar-pwninskjold/tech-snacks at commit 2d9a73b, republished under its MIT licence (© ragnar-pwninskjold). 614 words, ~1,278 tokens.

Download SKILL.mdSave it as .claude/skills/react-refactor-tournament/SKILL.md (or your agent's skills folder).
name
react-refactor-tournament
description
Review React/Next.js code against the real vercel-react-best-practices skill, backlog the performance findings keyed to actual rule ids + impact tiers, rank the most over-subscribed tiers, then fix + test the top N in isolated worktrees. Use when the user wants to systematically harvest and fix React/Next.js PERFORMANCE refactors (waterfalls, bundle size, RSC fetching, re-renders, JS perf), or says "react refactor tournament", "find React performance refactors", "/react-refactor-tournament".
allowed-tools
Workflow, Bash(echo *)
disable-model-invocation
true

react-refactor-tournament

Harvest React/Next.js performance refactor candidates straight from the vercel-react-best-practices skill, persist them as a tracked backlog keyed to the skill's real rule ids and impact tiers, rank the most contested tiers, then auto-fix the worst N (each in an isolated git worktree, with tests, committed but not pushed). This runs a bundled dynamic workflow that fans out skill-backed reviewers in parallel, then ranks and fixes under a hard 500k-output-token cap.

It only proposes and fixes on isolated worktree branches — it never pushes or merges, and it refuses to run at all if the vercel-react-best-practices skill isn't installed (no hand-written stand-in).

Requirements (check first)

This skill drives Claude Code's dynamic workflows feature. Before running, confirm:

  • Claude Code v2.1.154+ and a paid plan (Pro/Max/Team/Enterprise) or API access.
  • Workflows are enabled (/config → Dynamic workflows, or disableWorkflows not set, and CLAUDE_CODE_DISABLE_WORKFLOWS unset).
  • The vercel-react-best-practices skill is installed (project or user scope, .claude/skills or .agents/skills). The workflow's first phase hard-checks this and aborts with an actionable message if it's missing — do not try to work around it.

If workflows are disabled, the Workflow tool call below will fail. If it does, tell the user to enable Dynamic workflows in /config and re-run — do not fall back to doing the review inline (the whole point is the parallel skill-backed harness + token cap).

Resolve the bundled workflow path

The orchestration script ships inside this plugin. Resolve its absolute path now — this works whether the plugin is installed at the personal, project, or plugin level, and regardless of the current working directory:

echo "${CLAUDE_SKILL_DIR}/../../workflows/react-refactor-tournament.workflow.js"

Use the path printed above as the scriptPath argument. Do not retype or guess it.

Gather inputs

Determine the workflow args before launching:

  • repoPath (optional): absolute path to the repo root to review. Default to the current project root (${CLAUDE_PROJECT_DIR} or the cwd) unless the user named a different repo.
  • n (optional, default 3): how many top-ranked candidates the fix loop processes. n=0 ranks only and skips the fix loop entirely.
  • scope (optional): a glob/dir hint to constrain the review (e.g. src/components/dashboard). Omit to auto-detect the React component areas.

If repoPath is ambiguous, ask the user once. Otherwise proceed with the current project.

Show full SKILL.md (256 more words)Show less

Run it

Call the Workflow tool with:

  • scriptPath: the absolute path resolved above.
  • args: an object, e.g. { "n": 3 }, { "n": 0 } for rank-only, or { "n": 3, "scope": "src/components", "repoPath": "/abs/path/to/repo" }.

The run executes in the background across these phases:

  1. Preflight — resolve the vercel-react-best-practices skill install path; abort if missing.
  2. Scope — detect the framework and group React component dirs into disjoint review areas.
  3. Discover — parallel reviewers invoke the skill and emit candidates keyed to real rule ids (async-parallel, bundle-barrel-imports, …), with severity = the rule's impact: tier.
  4. Backlog — dedup, assign stable ids, and write .pro-brown/refactors/BACKLOG.{json,md}.
  5. Rank — order by impact tier (free); a single lazy tie-break ranker re-orders only an over-subscribed tier (more candidates than remaining fix slots).
  6. Fix (skipped when n=0) — fix the top N in isolated worktrees, write tests where feasible, and commit each (no push, no merge).

Watch progress with /workflows. When it finishes, present the ranking + backlog paths to the user. Fixes live on isolated worktree branches — point the user at git worktree list / git branch to review, and let them merge/PR. Do not push or merge on their behalf.

What counts as a good candidate

A candidate qualifies only if it is a genuine violation of a specific vercel-react-best-practices rule, pinned to a real file:line, with ruleId taken from the skill (never invented) and severity taken from that rule's static impact:. Generic React hygiene the skill doesn't cover (naming, alt text, design-system nits) does not qualify. Quality over quantity — a clean codebase reporting zero candidates is a valid result.

© ragnar-pwninskjold, 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 plugins/tech-snacks/skills/react-refactor-tournament of ragnar-pwninskjold/tech-snacks.

Open the folder on GitHubat commit 2d9a73b

Compare with similar skills

React Refactor Tournament 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.

React Refactor Tournament compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
React Refactor Tournament this skillragnar-pwninskjold/tech-snacks137—~1.3kAutomated safety check: PassMIT
React Performanceaffaan-m/ECC276k1 repos~4.5kAutomated safety check: PassMIT
Vercel React Best Practicessanity-io/sanity6.4k129 repos~1.6kAutomated safety check: PassMIT
React Best Practicesryokun6/ryos1.3k—~2kAutomated safety check: PassMIT
Vercel React Best Practicesgambitph/Stackable351—~2kAutomated safety check: PassMIT
React Best Practicesmajiayu000/spellbook287—~1.1kAutomated safety check: PassMIT

Similar skills

  • React Performance

    affaan-m/ECC

    React and Next.js performance optimization patterns adapted from Vercel Engineering's React Best Practices (https://github.com/vercel-labs/agent-skills).

    276k GitHub starsUsed in 1 repo~4.5k tokens
    DevelopmentAuto-check passed
  • Official

    React and Next.js performance optimization guidelines from Vercel Engineering.

    6.4k GitHub starsUsed in 129 repos~1.6k tokens
    Frontend & DesignAuto-check passed
  • React performance optimization guidelines from Vercel Engineering (vercel-labs/agent-skills).

    1.3k GitHub stars~2k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Vercel React Best Practices

    gambitph/Stackable

    React performance optimization guidelines from Vercel Engineering.

    351 GitHub stars~2k tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed
  • React Best Practices

    majiayu000/spellbook

    React and Next.js performance playbook distilled from Vercel Engineering guidance.

    287 GitHub stars~1.1k tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed
  • React Best Practices

    shapeshift/web

    Comprehensive React and Next.js performance optimization guide with 40+ rules for eliminating waterfalls, optimizing bundles, and improving rendering.

    206 GitHub starsUsed in 1 repo~2k tokens
    DevelopmentAuto-check passed

More from ragnar-pwninskjold/tech-snacks

  • Prd To UX

    ragnar-pwninskjold/tech-snacks

    A skill your agent uses when translating a PRD, feature spec, or raw product idea into screen-level prompts for web UX generators (Google Stitch, Figma AI, Pencil.dev, Claude Design, v0, or similar).

    137 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Scaffold Claude

    ragnar-pwninskjold/tech-snacks

    A skill your agent uses when the user wants to create, draft, or scaffold a CLAUDE.md (or AGENTS.md) file for their project.

    137 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed
  • UI Cloner

    ragnar-pwninskjold/tech-snacks

    A skill your agent uses when user provides a URL and wants to replicate or clone a website's UI, design, or visual style for their own product.

    137 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Mine Claude Md

    ragnar-pwninskjold/tech-snacks

    Mine recent Claude Code sessions for non-obvious, multi-file CLAUDE.md candidates, adversarially verify them, and propose paste-ready additions.

    137 GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed
  • Caveman Search

    ragnar-pwninskjold/tech-snacks

    A skill your agent uses when the user wants a terse, opinionated, research-backed answer to a "what tech/tools/stack do I need for X" question, or asks how to approach building something.

    137 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Lite Prd

    ragnar-pwninskjold/tech-snacks

    A skill your agent uses when the user hands you a vague or half-formed feature ask and wants it turned into a lightweight PRD, or asks to "write a PRD", "spec this feature", "flesh this out", or…

    137 GitHub stars~853 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about React Refactor Tournament

What does React Refactor Tournament do?

Review React/Next.js code against the real vercel-react-best-practices skill, backlog the performance findings keyed to actual rule ids + impact tiers, rank the most over-subscribed tiers, then fix…. React Refactor Tournament is an agent skill from ragnar-pwninskjold/tech-snacks.js code against the real vercel-react-best-practices skill, backlog the performance findings keyed to actual rule ids + impact tiers, rank the most over-subscribed tiers, then fix + test the top N in isolated worktrees.

When should I use React Refactor Tournament?

React Refactor Tournament fits situations like: the user wants to systematically harvest and fix React/Next.js PERFORMANCE refactors (waterfalls; says react refactor tournament; find React performance refactors; /react-refactor-tournament.

How do I install React Refactor Tournament in Claude Code?

Run `npx skills add ragnar-pwninskjold/tech-snacks --skill react-refactor-tournament -a claude-code`. Or copy the skill folder (plugins/tech-snacks/skills/react-refactor-tournament in ragnar-pwninskjold/tech-snacks) into .claude/skills/react-refactor-tournament in your project. Claude Code loads it when a task matches its description.

How do I install React Refactor Tournament in Codex?

Run `npx skills add ragnar-pwninskjold/tech-snacks --skill react-refactor-tournament -a codex`. Or copy the skill folder (plugins/tech-snacks/skills/react-refactor-tournament in ragnar-pwninskjold/tech-snacks) into .agents/skills/react-refactor-tournament in your project. Codex loads it when a task matches its description.

Can I use React Refactor Tournament 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 ragnar-pwninskjold/tech-snacks --skill react-refactor-tournament -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/react-refactor-tournament, .gemini/skills/react-refactor-tournament, .github/skills/react-refactor-tournament and .opencode/skills/react-refactor-tournament in your project.

What does React Refactor Tournament need to run?

Going by SKILL.md and its folder, React Refactor Tournament needs the command-line tools its instructions call (git). Its frontmatter pre-approves these tools: Workflow, Bash(echo *).

Does React Refactor Tournament 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 React Refactor Tournament 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 React Refactor Tournament use?

React Refactor Tournament 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 React Refactor Tournament use?

About 1.3k tokens (SKILL.md is roughly 5.1k 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 React Refactor Tournament?

Skills that share tags, products or a category with React Refactor Tournament: React Performance (affaan-m/ECC, 276k stars), Vercel React Best Practices (sanity-io/sanity, 6.4k stars), React Best Practices (ryokun6/ryos, 1.3k stars) and Vercel React Best Practices (gambitph/Stackable, 351 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains React Refactor Tournament?

ragnar-pwninskjold (a GitHub user) maintains it in ragnar-pwninskjold/tech-snacks, which has 137 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on August 18, 2026.

Source: ragnar-pwninskjold/tech-snacks on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.