All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 419,204 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.
Install, configure, verify, upgrade, or repair AgentCairn persistent cross-agent memory. Use when a user wants shared local-first memory in Claude Code, Codex, Cursor, OpenCode, Antigravity, VS Code, Claude Desktop, or another supported harness; when AgentCairn recall or remember tools are missing; or when its plugin…
Use when the user wants to research on the web, pull data from a page, work across their open Safari tabs, or fill in / click through a site. Safari is one of the most-used domains (evaluatejs + navigate→read are top patterns). Powered by Local MCP, driving the user's real Safari.
A guide for reading a shop's business data from the logged-in Taobao or Tmall management service, 生意参谋 (Shuān yì cān móu). Taobao and Tmall are Chinese online marketplaces.
A drafting and checking assistant for Chinese invention-patent applications filed with CNIPA, China's patent office. It works with LaTeX files for the request form, abstract, claims, description, and drawings.
How to build a working dashboard — the exact dashboard.json contract, how to explore a schema and test SQL before it becomes a panel, which chart answers which question, and how to lay panels out so the important number is where the eye lands. Use for EVERY dashboard request, before writing anything.
Multi-agent web research for any coding agent. Use for anything requiring current information from the internet — news, trends, product/service/company facts, statistics, people, places, events, APIs, library behavior, or 'what is X / how does X work' questions. Also use to search a local knowledge store of previously…
Drift detection for AI-generated codebases: in-loop MCP tools that keep new code consistent with the repo's own patterns, plus a run-once /vibedrift:setup.
★not rated 59
changed 4d agoA
tokens not measured
originalMIT
A toolkit of 13 skills for choosing, checking, presenting, and promoting products in e-commerce. It covers product selection, product-page work, image and video planning, traffic reasoning, and e-commerce data analysis.
★not rated 59▲
+1
changed 21d agoA
tokens not measured
LLM prompt management and evaluation platform. Version prompts, run A/B tests, evaluate with metrics, and deploy with confidence using Agenta's self-hosted solution.
MCP server "nova" as configured in towardsai/agentic-ai-engineering-course. Launched with uv --directory lessons/research_agent_part_2/mcp_server run -m src.server --tran. Needs 2 environment variables to run.
The crow-cli map — where the source lives, how a running agent was spawned, and how to change, upgrade, or repair crow-cli itself. Use when the task touches crow-cli's own code or install ("fix crow-cli", "upgrade crow-cli", "reinstall", "where is the source", "the checkout", "crow-cli init", "project agent", "why is…
Install, upgrade, diagnose, and verify DevSpace Ultra with DuckDNS/DDNS plus Caddy as the preferred ingress and Cloudflare named tunnel as the quota-governed fallback.
Use Ivan Pasichnyk's published experience pack — a 57-day inbound B2B acquisition trajectory that closed (outcome label closedwon, day +57). Counterparty redacted to category tokens. Invoke when the user is running a similar acquisition motion (inbound discovery from a counterparty technical decision-maker, free pilot…
For go-zero work, first read .ai-context/go-zero/00-instructions.md from the project root. Follow its task-specific references to workflows.md, tools.md, and patterns.md inside .ai-context/go-zero/.
Elite frontend design taste for building, reviewing, and polishing web interfaces. Use whenever the user wants to design, redesign, shape, critique, audit, polish, or improve any UI (landing pages, portfolios, dashboards, product UI, components, forms, onboarding, empty states) or asks to make something look better /…
★not rated 59▲
+1
changed todayA
tokens not measured
originalMIT
AI agents can use the official r0x facilitator on Robinhood Chain directly from Claude Code: check balances, prices and transactions, trade any token and manage Uniswap V3 liquidity positions, check yield and bridge quotes, chat with the r0x agent, and pay for capabilities in USDG, one x402 call at a time.
★not rated 58 2mo agoA
tokens not measured
originalMIT
Convert Markdown files to academic paper-style Word (.docx) and PDF documents. Dual format support: Chinese academic paper (paperolcnv2.0 template) and English arXiv-style.
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: