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.
Identify opportunities for DDD Factory pattern and guide their implementation. Use when encountering complex constructors, scattered creation logic, multiple overloaded constructors, or when the user mentions "factory", "factory pattern", "complex creation", "builder pattern", or asks to simplify object construction.
Build a high-quality Claude Code skill from one or more PDFs using vision-based page-by-page extraction. Use when converting reference material (technical manuals, certificates, policy documents, magazines, books, regulations) into a skill with structured markdown chapters, bundled diagrams, and a navigable SKILL.md.…
Master index for EVM smart contract security audit skills. Load this FIRST for every audit to determine which specialized skills to load. Contains routing table and audit methodology.
Author a new SIGN document from a concept, notes, or requirements — interactively and spec-compliant. Use when an operator asks Claude Code to write, draft, or create a SIGN document (a std / pol / ref / proc / xwalk doc), produce a Layer 1 index entry, or hand-write SIGN structure. For converting an EXISTING source…
Reference library of 58 world-class design systems from companies like Linear, Stripe, Vercel, Apple, Notion, Spotify, and more. Use when designing UI components, choosing visual direction, implementing design tokens, or when asked to match a specific company's design aesthetic. Each reference includes typography…
Bash scripting best practices for production-grade scripts, CLI tools, and Makefiles. Covers strict mode, error handling, portability, performance patterns, and argument parsing. Use when working with .sh files, Makefiles, shell scripts, or when asking about Bash, shell scripting, CLI design, or command-line tools.
Stochastic wind field simulation library (JAX / PyTorch / NumPy) with stationary and nonstationary support. Use this skill whenever working in this repository — it covers both usage (running simulations, benchmarks, validation) and development (architecture, adding backends, modifying the algorithm, config system).…
Quick read-only health check — session context, workspace mounts, tool availability, and task snapshot. Use when the user asks for system status or runs /status.
A Chinese writing skill for long WeChat articles. It supports a discussion stage for questions and outlines, followed by drafting, editing, rewriting, or restructuring.
Evidence-driven project thinking and software engineering derived from Mario Zechner's broader work, the actual Pi codebase, and verified rewrites. Use proactively for defining a project's core philosophy, non-goals, architecture, or first vertical slice, and for non-trivial implementation, debugging, refactoring, or…
Use when analyzing competitors in the F&B industry, comparing brand positioning or pricing strategies, identifying market gaps in Vietnamese F&B, or needing competitive intelligence to make strategic decisions about expansion, repositioning, or product launches.
Search and download podcast episodes from Apple Podcasts. Use when user wants to find podcasts, download podcast episodes, get podcast information, or mentions Apple Podcasts, iTunes, podcast search, or audio downloads.
Comprehensive Cline SDK skill for building AI agents. Covers the direct Agent runtime, ClineCore sessions, custom tools, plugins, events, LLM providers, scheduling, multi-agent teams, and production deployment. Use for any task involving @cline/sdk or its sub-packages.
Conducts comprehensive web research on any topic using search APIs and web scraping. Use when the user asks for research, information gathering, competitive analysis, or needs current data from the web.
A general-purpose guide for examining JavaScript code to identify website encryption, request signatures, and anti-bot checks, then documenting the findings in Python.
Scan React codebase for useEffect anti-patterns (derived state, event logic in effects, effect chains, prop-driven resets, missing cleanup, parent notifications, etc.) and propose idiomatic fixes. Based on React's "You Might Not Need an Effect" guide. Use when asked to audit, review, or clean up useEffect usage.
Scrape GitHub Trending page (github.com/trending) for the most-starred repositories. Supports filtering by programming language and time period. Use when the user wants trending GitHub repos, popular open-source projects, or mentions GitHub Trending.
Use when creating Product Hunt launch carousel images for developer tools, AI tools, open-source projects, GitHub launches, or technical products. Research comparable launches, inspect the project, extract verified proof points, then generate 4-5 launch-ready images with consistent branding, product surfaces, readable…
Weekday + Saturday search for remote OSINT Analyst jobs in the USA and Canada with deduplication, Notion tracking, Vercel dashboard update, and Gmail digest.
★not rated 10 yesterdayA42 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: