All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 411,659 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.
A Chinese-language sales assistant that turns a business situation into a structured request and sales content. It can create materials such as emails, proposals, and analysis reports.
Extend Pydantic AI agents with batteries-included capabilities from pydantic-ai-harness, currently Code Mode for collapsing many tool calls into one sandboxed Python execution.
★not rated 135▲
+2 todayA
tokens not measured
originalMIT
A source-code reading method for understanding a large open-source repository and turning it into documentation, a course, or a book. Every technical claim is tied to exact lines in the repository.
An academic-diagram skill for creating research-paper figures as TikZ/LaTeX code or draw.io XML. TikZ is code that embeds precisely into LaTeX papers, while draw.io XML creates diagrams editable in the draw.io app.
A Chinese-language workflow for reading and assessing one arXiv AI or robotics paper. arXiv is an online repository for research papers that are often shared before formal peer review.
Surgical PDF access for AI agents: keyword, semantic & hybrid search; structured extraction of text, tables, images & TOC; OCR; and CJK/vertical-script support — with SQLite caching. Runs locally from the pdf-mcp Python package. Needs 2 environment variables to run.
★not rated 136▲
+2 todayASocket: warn
tokens not measured
originalMIT
A Chinese-language assistant for social and romantic conversations. It interprets messages or screenshots and suggests replies, invitations, or next steps across services such as WeChat, Tinder, and Bumble.
A tool for turning reference images and story details into detailed prompts for making short videos. It can describe characters, clothing, scenes, relationships, stories, and video length.
Papers With Code CLI (pwc) for searching and reading AI/ML papers, discovering recent and trending research, finding related work and paper lineage, browsing tasks, methods, conferences, organizations, frameworks, and benchmark leaderboards, and submitting authenticated paper edits through the public Papers With Code…
Help users create high-quality skills by discovering and incorporating proven methodologies from domain experts. Use this skill BEFORE skill-creator when users want to create a new skill - it enhances skill-creator by first identifying expert frameworks and best practices to incorporate. Triggers on requests like…
Audit a browser fingerprint for internal contradictions with the liarjs CLI - canvas, WebGL, WebGL2, WebGPU, audio, 220 fonts, WebRTC and timezone probes, scored against the TLS/HTTP/ASN view of the same request. Use when asked to run a browser fingerprint test, see what a fingerprint looks like, check canvas or WebGL…
Look up version-matched Hankweave documentation, configuration, CLI commands, and captured evidence. Attach the optional source pack to inspect runtime code and exact source lines.
Use when the user wants cross-disciplinary research ideas generated as concise research cards with Title, Abstract, Design, Distinctiveness, and Significance rather than one-shot prompting.
A read-only review skill for OpenSpec changes, Git diffs, frontend, BFF, backend, LangGraph, tools, MCP, and security boundaries. BFF means a backend service tailored for a frontend.
Overview of gh-infra and command workflow (import, validate, plan, apply). Use when managing GitHub repository settings, labels, actions settings, rulesets, secrets, variables, or files declaratively via YAML manifests.
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: