Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Skill Claude CodeCodex
Guia designers sem experiência em código desde a instalação do Storybook até visualizar componentes do Figma funcionando como um catálogo interativo. Use esta skill quando o designer chamar explicitamente com /ds-to-code ou pedir para iniciar o fluxo de configuração do Storybook com o Figma.
minsu-kang/make-custom-app-skill
Skill Claude CodeCodex
Build and edit Make.com custom app IMLJSON code. Use when working with Make Internal App extension, editing IMLJSON files, creating modules, connections, RPCs, webhooks, or any Make custom app development. Triggers on imljson files, Make app references, or IML expressions.
Skill Claude CodeCodex
A tested library of 15 prompts for technical-writing tasks: auditing docs pages, walking quickstarts as a hostile first-time user, building error catalogs, drafting API references from OpenAPI specs, writing release notes, extracting glossaries, style-checking, rating pages for agent readers, Diataxis classification…
Skill Claude CodeCodex
A deep-reading workflow for books, long articles, research reports, and academic papers. It turns detailed reading into structured notes, small reusable notes, and linked ideas.
Skill Codex
Download, organize, check, incrementally sync, and zip public Behance project or moodboard URLs. Use when the user provides a public Behance project link or moodboard link and wants local image extraction, update checks, incremental downloads, stable moodboard folders, or ZIP packaging.
Skill Claude CodeCodex
Benchmark collection and evaluation workflow for agent model assignment reviews. Use when pulling benchmarks, evaluating cost/performance, or deciding which models to use for which agents.
sirius-zuo/design-pattern-skill
Skill Claude CodeCodex
Use when reviewing a project's architecture for design pattern applicability -- either validating a design document before implementation, or analyzing an existing codebase for pattern improvement opportunities.
Skill Claude CodeCodex
Run SQL with mysql-cli: SELECT queries, DML (INSERT/UPDATE/DELETE), DDL (CREATE/ALTER/DROP), and multi-statement atomic transactions. Use when the user asks to run SQL, query data, insert/update/delete rows, execute transactions, or perform DDL. Read-only JSON output by default, stable exit codes, and tiered gating…
Skill Claude CodeCodex
Read, search, create, and edit notes in your Obsidian vault via the Obsidian MCP Server plugin.
shan8065/novel-writing-agent-platform
Skill Claude CodeCodex
A coordinator for AI-assisted novel writing that connects tools for handling source material, characters, story settings, drafting, continuation, and consistency checks.
Skill Claude CodeCodex
Audit and fix security vulnerabilities in "vibe-coded" apps — projects built fast with AI assistance, especially on Supabase, Firebase, or other BaaS backends. Trigger when building, reviewing, debugging, or deploying a web app with a BaaS backend, or when code touches databases, API keys, authentication, environment…
yanjumlinnb-boop/scientific-agent-skills
Skill Claude CodeCodex
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
Ding-Ding-Projects/lowlevel-computer-use-mcp
Skill Claude CodeCodex
Drive the desktop with the lowlevel-computer-use MCP server — mouse, keyboard, shell, window management, processes, screenshots, cropping, screen recording, BACKGROUND/unfocused window targeting (no focus stealing), headless-with-GUI (Windows off-screen desktop / Linux Xvfb), show-for-login, AutoHotkey, ephemeral WSL…
Skill Claude CodeCodex
A skill for assigning programming and writing tasks to Pi, a separate coding subagent. It defines how to split work into stages, review the plan, and keep internet access and file changes under controlled responsibility.
Skill Claude CodeCodex
Use at the end of a session (or midway through a long one) to deliberately capture what was learned — lessons, decisions, workflows, state changes, and facts — into the knowledge base. The nightly harvest is a safety net for lessons; unless the host opted into KBHARVESTFACTS, /debrief is the only thing that records…
Skill Codex
Query the current AI mathematics frontier, audit solution claims and verification boundaries, find replay-ready opportunities, compare methods, or export a problem to Low-Hanging Fruit. Use for questions such as what AI solved recently, which claims are only candidates, which results are Lean- or expert-verified, what…
Skill Codex
Use when the user says deepsearch, asks for deep research, asks to investigate thoroughly, compare sources, find primary evidence, trace claims, verify current facts, synthesize scattered information, or perform multi-pass search across web, local files, GitHub, Shuiyuan, Gmail, or other available tools.
Skill Claude CodeCodex
Publish blog posts from AI agents to WordPress via Notion. One API call handles page creation, markdown conversion, image uploads, featured image generation, and SEO metadata.
compnew2006/browser-controller
Skill Claude CodeCodex
Control the user's real browser via Browser Controller. Use when asked to interact with web pages, test UIs, fill forms, or read page content.
Skill Claude CodeCodex
Unofficial Fitbit data for AI agents. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Fitbit data or actions through an agent.
Skill Claude CodeCodex
Prepare a Proton Mail draft, optionally with user-supplied attachments, after explicit in-conversation confirmation; the user always reviews and sends it in Proton Mail.
Skill Codex
Compile branching decisions outside model generation, route virtualized specialist skills, and minimize model input/output across tools, files, history, images, subagents, search, and recall. Use for token-heavy or reasoning-heavy work or reversible skill-vault management.
wgwtest/novel-project-strategy
Skill Codex
Use when a novel or longform fiction project needs stable cross-session workflow, chapter-state tracking, manuscript-layer discipline, structured reload order, or coordination between outline, setting, timeline, and prose.
Skill Claude CodeCodex
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
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: