Aboudjem

Full project design audit that orchestrates all agents, scores across 12 dimensions, generates prioritized action plan

Accessibility audit covering WCAG 2.2, contrast, focus, keyboard, screen reader, touch targets

Color-only audit to extract, evaluate, and recommend improvements for the project's color system

Component consistency audit covering state coverage, hierarchy, patterns

Interactive pre-launch design quality checklist

Compare current design against a reference or competitor

Quick design score card covering 12 dimensions, top 5 improvements, under 2 minutes

Generate or improve a complete design token system covering color, typography, spacing, radius, shadows, motion

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 delays, or troubleshoot metadata fetch failures for a chain. Defaults to default_ism app context if not specified.

Detects 53 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 for publication, when auditing prose for AI tells, or when editing a Markdown file in place. Triggers on phrases like "humanize this", "make this sound less AI", "make this sound human", "remove AI tells", "does this read like ChatGPT", and "rewrite so it does not sound AI-generated". Pure Markdown, zero dependencies, no network calls.

Set up a big coding task to run on its own without the plan dying at `/clear`: in this session goalify scopes the work, locks the few real decisions, and writes a self-contained `/goal` file whose finish line is wired to commands the run can check, so a fresh, full-context session executes the whole job and verifies every success criterion before it calls the task done (the file then deletes itself on success). Use when the user says "goalify", "goalify this", "goalify <task>", "/goalify <task>", "prep a goal", "prepare a goal file", "make an md for /goal", or "set up an autonomous run to launch later". This skill AUTHORS the handoff file now; it does NOT execute the work in this session. For a task to be done immediately here, use autopilot, ultrawork, or ralph instead, not goalify.

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 data-transfer costs, S3 storage and lifecycle, CloudWatch log retention, untagged or unexplained spend, per-resource cost attribution ("what is this costing me and why"), or building a savings plan or cost dashboard. Triggers include "AWS bill too high", "cut/lower AWS costs", "FinOps", "Cost Explorer", "where is my money going", "unused AWS resources", and "cloud cost audit".