Validates and improves agentic skills by running isolated executor agents against test briefs, scoring confusion, fixing unclear instructions, and rerunning until stop criteria pass. Use when asked to test or evaluate a skill, find skill failure modes, or harden a skill before reuse. Inspired by Karpathy's…
Write OpenAPI examples that work with Microcks dispatchers for API mocking. Covers example pairing rules, JSON body dispatching, Groovy script dispatching, and dispatcher configuration via the Microcks API.
Applies Computer Love's official brand colors and typography to any sort of artifact that may benefit from having Computer Love's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Use when someone wants to genuinely understand something and have it stick — a topic, mechanism, paper, theorem, algorithm, domain, or real code — not just get an answer. Fires on comprehension intent even without the word "understand": "help me understand X", "derive X from first principles", "why does this behavior…
Create, revise, and explain Wire Lang .wire schematic source. Use when writing electronic schematics, converting circuit descriptions into Wire Lang, fixing Wire Lang syntax, or giving good and bad examples of Wire Lang authoring.
A tool for creating, improving, and reviewing skills and agents for OpenClaw. It has separate workflows for creating a skill, creating an agent, or improving an existing one.
Observe an authorized Android test device through read-only ADB commands. Capture the foreground app, focused window, UIAutomator semantic tree, and optional screenshot as a timestamped SituationSnapshot with stable fingerprints. Use this skill to understand the current device screen, investigate an app that appears…
A Chinese-language workflow for designing and preparing Douyin AR effects, which are interactive camera effects for ByteDance's Douyin video platform. It takes an idea through research, concept development, effect creation, testing, troubleshooting, and preparation for submission.
Generate a complete design system (design.md, design-guidelines.md, design-components.md) from any reference materials — images, PDFs, links, or descriptions.
Generates a complete custom AI Operating System for any small business — master prompt + workflow superprompts + 30-day deployment roadmap — across 21+ verticals (dental, contractor, salon, real estate, restaurant, law, vet, photographer, fitness, insurance, CPA, and more). Use when a small business owner asks for…
Execute one bounded task using baseline evidence, narrow implementation, verification, evidence capture, and tracker updates. Use when the user invokes /build-right-execution, wants to work the next issue, run an evidence-driven implementation loop, verify a task, update task state, or continue execution from a…
Control the user's real Chrome browser with their logged-in sessions, cookies, and extensions. Triggers include "open a website", "click a button", "fill a form", "take a screenshot", "check my email", "browse as me", or any task requiring the user's authenticated browser.
Discover available Scoop shims and identify valuable command-line tools. Use when the user asks about available tools, what commands they can use, or wants to explore their Scoop environment.
Rebuild a tangled feature branch into a small set of reviewer-friendly logical commits while preserving its final tree byte-for-byte. Use when asked to regroup, squash, tidy, or rewrite a branch with many interleaved feature, fixup, review, merge, or formatting commits. Resolve the actual PR base, plan groups with the…
Designing and building AI agents — tool design, agent loops, context management, permissions/guardrails, memory, multi-agent orchestration, MCP, and agent evaluation. Use when building an agent that takes actions (calls tools/APIs, writes files, automates workflows), designing tool schemas, debugging agent…
Create, extend, or repair semantic Flutter design systems covering tokens, themes, typography, color, spacing, geometry, motion, and component contracts. Use for ThemeData work, design-token extraction, dark mode, component standardization, UI consistency, or migration away from scattered visual constants.
Generates a standalone, interactive HTML map of your Claude Code automation setup: a radial SVG mind-map of your skills grouped into departments, a schedule view of every scheduled task, and a feedback panel that turns flagged issues into copy-ready fix prompts. Best if you run several skills and/or scheduled agents.…
Use when the user provides a Skill, SKILL.md, prompt workflow, agent instructions, marketplace page, or skill directory and asks to analyze, reverse-engineer, compare, improve, rewrite, trigger-test, port, or package it as a reusable agent skill.
Groom a fuzzy request and the smallest relevant source set into a bounded PRE-SPEC ASSEMBLY packet for mini-spec, using optional read-only research fan-out while separating evidence, tensions, decisions, assumptions, and blockers before contract language is written.
Authors and executes git work end to end — Conventional Commits messages, pull-request content, release notes, and pull-request review, plus the repository operations an engineer runs daily: branching, rebasing, squashing, cherry-picking, reverting, merge-conflict resolution, stashes, tags, remotes, and recovery…
Review React, Next.js App Router, TypeScript, Tailwind CSS, shadcn/ui, TanStack Query, and frontend UI code. Use when reviewing a PR, branch, diff, page, component, hook, Server Action, route handler, or API client; debugging frontend behavior; assessing production readiness; or checking runtime bugs, client/server…
Use when the user explicitly asks to generate, produce, plan, revise, QC, or deliver an AI short-drama pipeline, project package, episode, assets-to-video workflow, prompt pack, clips, edit, or release pack.
A personal reference skill for keeping profiles of people, including their key ideas, notable works, quotations, and suitable questions to ask them about.
★not rated 4 27d agoA0 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: