Ai skills
Prompt craft, model choice, and evaluation patterns for getting better answers from language models.
Ads
When to open Ai
Open AI listings when the work is about prompting, routing models, or tightening how the assistant thinks, not a domain role.
Current listings include ache-life-to-comic-skill, agent-causal-decision-tool, agent-ready-skills, and agent-skills-vrc-udon, plus 105 more. Open a skill for the full body, flags, and install command.
What you get from a listing
AI skills are about prompts, routing, and evals. Use a listing when the job is how the model thinks, not a product domain.
Skills in this category
Ai
launchworthy
A Claude Code skill that plays bouncer at the door of production: audits AI-built apps (Lovable, Bolt, v0, Cursor) across 5 domains and hands you a scored punch list with copy-paste fixes. MIT.
Ai
mac-migration-operator-skill
Agent Skill for safer Mac-to-Mac migrations with rollback and validation
Ai
manim-skill
Claude Code Skill for creating animations with Manim. Claude Code autonomously plans scenes, writes Manim code, renders videos, and refines based on feedback.
Ai
material-design-3-ui-skill
A reusable Agent Skill for designing, reviewing, and implementing UI/UX with Google Material Design 3, Material You, M3 Expressive, accessibility, adaptive layouts, and semantic design tokens.
Ai
minto-pyramid-skill
Agent Skill: make Claude write in Barbara Minto's Pyramid Principle - answer first, grouped reasons, evidence under each.
Ai
nano-banana-ecommerce-skill
Skill for Nano Banana - photos suited for Ecommerce sites
Ai
native-subtitle-quote-image
保留视频内嵌字幕,精确取帧并生成 3:4 社交长图的 Agent Skill
Ai
nextjs-app-router-audit
Claude skill: audit a Next.js App Router codebase for RSC boundary bugs, request waterfalls, and Core Web Vitals risks — with a zero-dependency scanner.
Ai
no-no-debug
No-No Debug — Self-evolution system for AI coding assistants. 10 minutes writing code, 2 hours debugging? This skill makes your AI remember all its bugs.
Ai
oi-owarasero
書籍「おい、とりあえず終わらせろ」の5ステップで、内省と次の一歩を支えるClaude Code / Codex向けAgent Skill
Ai
old-coder
An old coder's strategy for the agent era: don't read the code — make it run the gauntlet. Evidence-first development skill for coding agents, inspired by Uncle Bob.
Ai
open-ontologies
Plan, apply and roll back changes to a production ontology, with a blast radius report and a proof an auditor can re-check.
Ai
personalized-travel-guide-skill
Open-source AI Agent skill for generating personalized, mobile-friendly travel handbook webpages.
Ai
photo-to-anime-skill
Photo to anime agent skill for Claude Code, Codex & OpenClaw: restyle a photo as anime, manga, cartoon, watercolor, clay, or character art while people, pets, and products stay recognizable, with one look reused across a set. 照片转漫画 · 动漫风 · AI转绘
Ai
private-house-code-v2.5
让 Codex 少烧 Token、少造复杂度,同时不降智的代码约束 Skill
Ai
prompt-architect
Claude Code skill that transforms vague prompts into structured, expert-level prompts using 7 research-backed frameworks (CO-STAR, RISEN, RISE, TIDD-EC, RTF, CoT, CoD)
Ai
prompt-refine-skill
Agent Skill that silently refines prompts for the currently running model
Ai
public-skills-builder
Generate Claude Code bug bounty skills from public HackerOne reports and GitHub writeups — 18 vuln classes, no private reports needed
Ai
quicksilver
Claude Code skill: hand bulk judgment calls to Jev. 86% fewer Claude tokens on a 12-task benchmark, up to 20x faster. One-line npx install.
Ai
qwoted-seo-backlinks-skill
Claude Code skill: find PR/backlink opportunities on Qwoted, build a sourced statistics page as a linkable asset, and pitch journalists — all from your AI agent.
Ai
remote-gpu-trainer
An Agent Skill for the DL experiment lifecycle: RUN (a GPU you own or rent) → VERIFY the number is real → DELIVER reproducible, single-source figures and tables.
Ai
research-field-onboarding
A reusable research-onboarding skill for Claude, ChatGPT, Codex, and other instruction-following agents.
Ai
review-it
The QA front door of the DevOtts lifecycle family — plan-it plans, fable-it builds, review-it verifies. Runs the plan-phase Test Contract against the build and enforces an 11-rule gate catalog that makes false-VERIFIED claims un-shippable.
Ai
review-skills
Two-model debate review of PRs and MRs, plus a babysitter that works the review rounds. Skills for any coding agent.
Page 3 of 5
Other skill groups
Related and neighboring groups you can open from Ai.
Prefer a flat search? Browse all skills. Role files in the same group: Ai agents.