All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 417,824 of
them, each with its token cost per session, a security scan with the
line that triggered it, and whether it is the original or one of the
copies.
Universal radial-tree exploration engine for Claude Code. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideation, adversarial critique, and design-space exploration. 12 framings × hard-ban-on-incomplete-leaves × stable convergence. See CHANGELOG.md for per-version histor.
Use when a complex task needs dependency-aware interactive branches, subagents, or AI coding threads while keeping the master session context clean through explicit branch briefs, completion reports, wave planning, and user-approved merges. Especially useful with grill-me, Trellis, research, implementation, writing…
Run local commands with API keys stored in EnvLatch instead of copying credentials between .env files or shell profiles. Use when an agent, CLI, script, SDK, test, or build needs a saved credential environment variable on macOS.
Route every Hancom/HWP document edit, analysis, and verification request to the GSGHWPBETA (gsg-hwp-beta-live) MCP. Never fall back to computer-use; report an unavailable or closed MCP connection and stop. Supports already-open HWP inspection and editing, native tables and captions, ratio-preserving images, PPTX/XLSX…
A web-search skill that uses Playwright to search Bing or Google and extract structured results and page elements. Playwright is a tool for controlling a web browser with code.
An image-editing skill for opening a product-image optimisation page and adding sales-oriented elements to 1688 product main images. 1688 is a Chinese online wholesale marketplace.
Search engine for MCP tools and agent skills. Search 790+ MCP server tools and 760+ agent skills in one place, call remote MCP tools, and get full skill instructions via simple HTTP API.
Script-backed, out-of-box auditing workflow for Solidity/EVM repositories based on EVMbench detect/patch/exploit methodology. Use when asked to audit a smart contract repo from a URL or local path, auto-prepare the environment, find high-severity loss-of-funds vulnerabilities, validate exploitability, propose safe…
Reference for the restricted Deno runtime that hosts Secutils.dev responder scripts and API tracker configurator/extractor scripts. Documents what is and is not available inside the sandbox, the context global shape per script kind, the Deno.core utility namespace (encode/decode, binary string helpers, base64 building…
A Chinese-language assistant for improving product titles on 1688, an online Chinese wholesale marketplace. It produces title suggestions using rule-based keyword additions and deeper language-model rewrites.
Create or refresh Morphous website design-system/theme bundles from animal, insect, plant, landscape, mineral, weather, or other nature motifs. Use when Codex is asked to generate Morphous motif images, light/dark design-system boards, reusable image prompts, generated web assets, shadcn/tweakcn theme exports, or the…
An agent for automating infrastructure and software delivery operations. It covers infrastructure-as-code, which describes servers and cloud resources in files, and CI/CD, which automatically tests and deploys code.
A lightweight RSS subscription manager for tracking updates from services such as YouTube, Vimeo, Behance, Twitter/X, and several Chinese platforms. RSS is a format that lets one tool collect new posts from many sites.
A skill for using IDA and the WPeGPT plugin to analyse executable files in PE or ELF formats. It produces a structured report about the program, network indicators, suspicious functions, and possible vulnerabilities.
Orchestrates continuous kernel optimization by chaining profiling, bottleneck diagnosis, tier-based optimization, verification, and benchmarking into an iterative loop. This is the "main program" that drives the other skills. Use when you want to iteratively optimize a kernel until it meets a performance target…
A Chinese-language guide to preparing software projects for reliable work by coding agents. It covers project instructions, documentation, code checks, tests for agent output, prompts, and ways to coordinate multiple agents.
This project follows a set of conventions to ensure code quality and consistency. The following rules should be followed when working on this project, especially when using AI tools like Cursor.
★not rated 101▲
+1 1mo agoA389 tokens
originalMIT
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: