jobseek
5689MCP server Claude CodeCodexCursor +2
Search jobs and companies on Job Seek (jseek.co). Runs locally from the @jseek/mcp-server npm package.
All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 437,288 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.
MCP server Claude CodeCodexCursor +2
Search jobs and companies on Job Seek (jseek.co). Runs locally from the @jseek/mcp-server npm package.
Plugin Claude Code
Bundles 12 skills · 1,766 tokens together
Advisor-facing systems and workflows. Teaches Claude how advisor platforms work so it can help design, evaluate, or integrate with them. Covers the full advisor workflow from onboarding through reporting.
MCP server Claude CodeCodexCursor +2
One of 2 in claude_desktop_config.json
MCP server "llamaindexdocsserver" as configured in run-llama/llamacloud-mcp. Runs locally from the llamacloud-mcp@latest Python package.
Skill Claude CodeCodex
Create visualizations and interactive tools directly in conversation. Use when the user asks to see how something works, explore 'what happens when' or 'what changes', compare or inspect, or wants a simulation, map, chart, graph, or mockup, or when a visual clearly explains better than text. Use standard tools for…
MCP server Claude CodeCodexCursor +2
Access control for AI agents and MCP servers: allow, hold for approval, or block each tool call. Runs locally from the node9-ai npm package.
Skill Claude CodeCodex ✓ vendor
Creates isolated Linux MicroVMs using Vercel Sandbox SDK. Use when building code execution environments, running untrusted code, spinning up dev servers, testing in isolation, or when the user mentions "sandbox", "microvm", "isolated execution", or "@vercel/sandbox".
dean9703111/ai-agent-skill-for-video-workflow
Skill Claude CodeCodex
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Plugin Claude Code
Bundles 1 skill · 102 tokens together
Agent-native PowerPoint manipulation. One CLI (deck.py) lets agents inspect, edit, create, and verify .pptx files through atomic JSON patches — with self-correcting errors, deterministic geometry repair, and built-in visual verification.
Skill Claude Code
Guide to setting up third-party authentication for a Notion Worker. Covers brokered credentials for external-service API keys / personal access tokens, OAuth, and plaintext environment secrets only when worker code needs the value. Use when the worker needs credentials for a non-Notion API, not for Notion API tokens…
marketcalls/vectorbt-backtesting-skills
Skill Claude Code
VectorBT backtesting expert. Use when user asks to backtest strategies, create entry/exit signals, analyze portfolio performance, optimize parameters, fetch historical data, use VectorBT/vectorbt, compare strategies, position sizing, equity curves, drawdown charts, or trade analysis. Also triggers for openalgo.ta…
kangarooking/system-prompt-skills
Skill Claude CodeCodex
Design guidance for giving an AI a persistent memory system. It covers storing, finding, using, changing, and deleting information such as user preferences and project knowledge.
Skill Claude Code
Fix a broken OpenAPI spec in jentic-public-apis with an OpenAPI Overlay, validate it (spectral lint + idempotency check), and contribute it back via a PR to the community catalog. Falls back to applying the same overlay to the local Jentic registry if the user can't wait for maintainer approval, and closes the loop by…
Skill Codex
A Chinese-language coaching skill for building and managing a personal IP, meaning a recognisable public identity around a person or account.
Skill Claude CodeCodex needs its repo
Go 1.24–1.27 coding guidelines for the dimetron/pi-go AI agent runtime. Use this skill whenever writing, reviewing, or refactoring ANY Go code in pi-go. This covers idiomatic style, error handling, concurrency, project layout, testing (table-driven, fuzz, benchmarks, synctest), new stdlib usage, golangci-lint v2…
Skill Claude CodeCodex
A Chinese-language guide for auditing an Amazon product listing identified by its ASIN, Amazon’s product identifier. It examines listing visibility, conversion, advertising, and Amazon’s COSMO and Rufus systems, then suggests changes.
Skill Claude CodeCodex
Scrape AI papers published by 28 big tech companies and AI labs in a given date window, with institutional attribution (lead vs. participating vs. intern). Use when the user asks "what did big tech publish recently", "what AI research has put out", "run the paper radar", or wants to inventory recent arXiv output by…
Plugin Claude Code
Bundles 3 skills, 3 agents, 1 hook, 1 MCP server · 624 tokens together
Emulate an enterprise SaaS knowledge source over a corpus you supply, then wire a real client to it.
Skill Claude CodeCodex
Read and create Word and PDF documents with checked outputs.
Plugin Claude Code
Claude Code plugins by Pierce Lamb.
composio-community/awesome-agent-clis
Skill Claude CodeCodex
CLI for Gmail, Calendar, Chat, Drive, Docs, Sheets, Slides, Forms, Contacts, Tasks, Keep, and Admin. Use when an agent needs to interact with any Google Workspace service — send emails, manage calendar events, search Drive, read/write spreadsheets, or manage contacts.
Cursor rule Cursor
Yushio (夕潮) base persona — emotion/judgment/reflection/autonomy + work discipline + memory system.
Skill Claude Code
Use when authoring or repairing Kilroy Attractor DOT graphs from requirements, with template-first topology, routing guardrails, and validator-clean output.
MCP server Claude CodeCodexCursor +2
Gemini 3 MCP server with 30+ tools: images, video, research, TTS, code exec & CLI. Runs locally from the @rlabs-inc/gemini-mcp npm package. Needs 2 environment variables to run.
Plugin Claude Code
Bundles 1 skill · 61 tokens together
Docs-grounded grilling, unknown discovery, and shared understanding before implementation.
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: