Aboudjem

Accessibility audit covering WCAG 2.2, contrast, focus, keyboard, screen reader, and touch targets. Use when the user asks for an accessibility audit, an a11y review, a WCAG check, an accessibility check, or an a11y audit.

Color-only audit that extracts, evaluates, and recommends improvements for the project's color system. Use when the user asks to audit colors, run a color review or color audit, fix their colors, or work on the color palette or color system.

Component consistency audit covering state coverage, hierarchy, and patterns. Use when the user asks for a component audit, a component review, or a check of UI consistency.

Full project design audit that orchestrates all agents, scores across 12 dimensions, and generates a prioritized action plan. Use when the user asks to audit their design, run a design review or UX audit, review their UI, or asks how their design looks.

Interactive pre-launch design quality checklist. Use when the user asks for a design checklist, a launch checklist, or a pre-launch design pass.

Compare the current design against a reference product or competitor. Use when the user asks to compare designs, run a design compare, or benchmark against another product.

Quick design score card covering 12 dimensions with the top 5 improvements, in under 2 minutes. Use when the user asks for a design score, to score their design, to rate their UI, or for a quick audit.

Generate or improve a complete design token system covering color, typography, spacing, radius, shadows, and motion. Use when the user asks for design tokens, to generate tokens, or to build a token system.

Use when the user types /recap setup, /recap config, or asks Recap Studio to "configure", "initialize", or "set defaults". Writes recap-studio.config.ts with safe defaults and validates env.

Use when the user types /recap validate, asks Recap Studio to "score the page", "run validation", "qa the recap", or wants the multi-agent quality report regenerated. Dispatches the validation board and writes a structured report.

Use when the user types /recap session, /recap repo, /recap session --deep, or asks Recap Studio to "explain my coding session", "summarize this branch", "wrap up what we built", or "explain what changed". Produces a one-page page that explains a large coding…

Use when the user types /recap, /recap topic, /recap "<subject>", or asks Recap Studio to "make a one-page explainer", "summarize a topic", or "build a visual page about X". Routes to /recap session when the input is "session", "repo", or empty inside a git…

Review code changes using Hyperlane monorepo coding standards. Use when reviewing PRs, checking your own changes, or doing self-review before committing.

Post a single consolidated PR review with summary and inline comments. Use this skill to deliver code review feedback as one unified review per run.

A skill that allows a user to validate that a warp route deployment will be in the expected state after applying some configuration

Debug validator checkpoint inconsistencies where some validators are behind others. Use when alerts mention "checkpoint inconsistency", "validators behind", or "inconsistent latest checkpoints", or when asked to debug validator sets, investigate validator…

Scan the project and auto-fix safe issues (remove debugger statements, console.log calls, and other auto-fixable problems).

Show the results from the last sniff scan.

Use when the user types /sniff, or asks to "scan this project for bugs", "find bugs in my app", "QA my site", or "walk my app and tell me what's broken". For a running web app, finds real, reproducible issues (broken pages/links, console & network errors,…

Detects 55 AI writing patterns and rewrites text in five voice profiles so it reads like a specific human wrote it, with an optional 0-100 AI-tell score. Use when text sounds AI-generated or like a chatbot, when preparing a blog post, README, or LinkedIn post…

Use when a user wants to audit, understand, reduce, or optimize their AWS bill or cloud costs, finding idle, unused, or orphaned resources, rightsizing over-provisioned compute, checking Savings Plans / Reserved Instance coverage, NAT gateway and…

Find what a stranger can take from your app. Then close it and prove it closed. Every finding carries the command that shows the hole and the output it produced, so nothing is reported that cannot be demonstrated. Nothing is fixed until you approve it, one…

Hand Claude a huge task. Come back to proof it's done — not a promise that it is. goalify writes the brief (a file with the instructions the run works from) and the condition (a short string you paste into `/goal`), because `/goal` takes a condition string,…

Tell every coding agent how your repo works. Then prove it is still true. Use when the user says "contextify", "contextify this repo", "write an AGENTS.md", "generate CLAUDE.md", "agent context", or "context file is stale", or when a repo has no instruction…

Hand Claude a job that repeats. Come back to a log of what every tick did, not a loop you have to babysit. loopify writes the brief (a standing file the loop re-reads every tick) and the line (one short `/loop` string you paste into Claude Code's built-in…