AI & ML

jorinyang Skill

Hermes 任务执行慢的系统性能诊断——排查文件搜索、网络搜索、LLM 推理三大瓶颈，按优先级输出根因和修复方案。触发：执行慢/很慢/太久了/卡住了/性能/performance/优化/诊断。

jorinyang Bundle

Diagnose and repair Windows components (services, Store, AppX packages, registry) from a WSL session by bridging to Windows PowerShell. Use when a user reports a Windows-side problem but the agent's shell is WSL.

itamarzand88 Skill

<!-- source: mcp-builder — https://raw.githubusercontent.com/anthropics/skills/main/skills/mcp-builder/SKILL.md -->

itamarzand88 Skill

<!-- source: chdb-datastore — https://raw.githubusercontent.com/chdb-io/chdb/main/agent/skills/chdb-datastore/SKILL.md -->

itamarzand88 Skill

<!-- source: wshobson-rag-implementation — https://raw.githubusercontent.com/wshobson/agents/main/plugins/llm-application-dev/skills/rag-implementation/SKILL.md -->

itamarzand88 Skill

<!-- source: milo-solana-portfolio — https://raw.githubusercontent.com/and-milo/agent-to-agent-portfolio-manager/main/skill.md -->

deankelly751 Skill

Step-by-step procedure to design a GraphQL schema from a domain model. Covers type design, queries, mutations, error handling, pagination (connections pattern), subscriptions, and field-level auth. Includes a schema design checklist. Use when designing a new GraphQL API or extending an existing schema.

deankelly751 Skill

AI agent architecture patterns covering tool use, planning, memory, and multi-agent coordination. Decision framework for agent design choices. Use when designing AI agent systems, choosing agent architectures, or reviewing agent implementations.

deankelly751 Skill

Prompt engineering patterns covering system prompts, few-shot examples, chain-of-thought, structured output, and prompt testing. Use when writing prompts for AI systems, designing agent instructions, or optimizing LLM interactions.

arjunprabhulal Skill

Replaces network location with verified identity as the basis for access, removing implicit trust inside the perimeter via microsegmentation and continuous verification. Use this whenever the user assumes "inside the VPC" means trusted, wants access controls that follow identity rather than IP address, is planning a migration off perimeter-based security, or is limiting lateral movement after a compromised workload. For firewalls and segmentation use `network-security`; for the role model behind access decisions use `iam-access-management`.

harsh817 Bundle

Write precise coding-agent instructions for implementing one feature. Use when converting a plan into actionable agent guidance with scope boundaries, project comparisons, tests, stop conditions, documentation updates, and expected outcomes.

harsh817 Skill

Define or audit how AI agents plan, ask questions, limit scope, preserve user work, verify changes, and report deviations. Use when setting agent instructions, reviewing autonomous work, or creating guardrails for coding assistants.

jorcan Bundle

Agent SDK Patterns — TypeScript

jorcan Bundle

Code Review Agent

jorcan Bundle

Implementer Subagent Prompt Template

mhassan0000 Bundle

How to Build a Website AI Agent in 13 Min (Free N8N Template)

mhassan0000 Bundle

Upwork AI Agent (Flowchart + Proposal + Application Generator)

steph-dove Skill

Use when the user is tired of approving the same routine dev work ("stop asking me yes", "allow the normal dev tools", "grant permissions"). Detects the repo's stack and writes a curated allow-list into the agent's own local permission file so the basics stop prompting — reading, editing and creating files, plus tests, lint, build, git, the package manager and the run command — while keeping secret files denied.

steph-dove Skill

Use when the user is tired of approving the same routine dev work ("stop asking me yes", "allow the normal dev tools", "grant permissions"). Detects the repo's stack and writes a curated allow-list into the agent's own local permission file so the basics stop prompting — reading, editing and creating files, plus tests, lint, build, git, the package manager and the run command — while keeping secret files denied.

steph-dove Skill

Use when the user is tired of approving the same routine dev work ("stop asking me yes", "allow the normal dev tools", "grant permissions"). Detects the repo's stack and writes a curated allow-list into the agent's own local permission file so the basics stop prompting — reading, editing and creating files, plus tests, lint, build, git, the package manager and the run command — while keeping secret files denied.

steph-dove Skill

Use when the user is tired of approving the same routine dev work ("stop asking me yes", "allow the normal dev tools", "grant permissions"). Detects the repo's stack and writes a curated allow-list into the agent's own local permission file so the basics stop prompting — reading, editing and creating files, plus tests, lint, build, git, the package manager and the run command — while keeping secret files denied.

steph-dove Skill

Use when the user is tired of approving the same routine dev work ("stop asking me yes", "allow the normal dev tools", "grant permissions"). Detects the repo's stack and writes a curated allow-list into the agent's own local permission file so the basics stop prompting — reading, editing and creating files, plus tests, lint, build, git, the package manager and the run command — while keeping secret files denied.

steph-dove Skill

Use when the user is tired of approving the same routine dev work ("stop asking me yes", "allow the normal dev tools", "grant permissions"). Detects the repo's stack and writes a curated allow-list into the agent's own local permission file so the basics stop prompting — reading, editing and creating files, plus tests, lint, build, git, the package manager and the run command — while keeping secret files denied.

steph-dove Skill

Use when the user is tired of approving the same routine dev work ("stop asking me yes", "allow the normal dev tools", "grant permissions"). Detects the repo's stack and writes a curated allow-list into the agent's own local permission file so the basics stop prompting — reading, editing and creating files, plus tests, lint, build, git, the package manager and the run command — while keeping secret files denied.

tomjiu Skill

Use when doing AI-native web search or finding similar pages via Exa API (EXA_API_KEY). Prefer for research/code-oriented retrieval; use Tavily Hikari or Keenable for general agent search MCP.

tomjiu Skill

Install and use the Keenable CLI for fast web search and page fetching from the terminal. Use when you need to search the web, fetch a page as clean markdown, or configure Keenable as the search provider (MCP) for AI clients like Claude Code or Cursor.

tomjiu Skill

Use when choosing MCP servers, skills packs, tools, or GitHub orgs — look up local catalog and pre-cloned mirrors first; fall back to listed upstream repos only after local miss. Also use to answer "where is X installed locally".

tomjiu Skill

Use when a needed skill or MCP is not in local selected/packs mirrors — search listed upstream repos and awesome lists, download into sources/, review for malice and prompt injection before promoting to selected or enabling MCP.

tomjiu Skill

Use when the agent needs web search, extract, crawl, map, or research via Tavily Hikari pool (tvly-hikari CLI or tavily_hikari MCP). Prefer this over inventing search APIs.

orcaqubits Skill

Implement the UCP Cart capability (`dev.ucp.shopping.cart`) — a lightweight CRUD surface for collecting line items before purchase intent exists, and its conversion into a Checkout session. Use when building pre-checkout item collection, shareable carts, or cart-recovery flows over REST, MCP, or Embedded bindings.

orcaqubits Skill

Scaffold a new AP2 project — install the SDK, set up agent roles, configure credentials, and create a basic multi-agent payment system. Use when starting a new AP2 agentic payments project from scratch.

orcaqubits Skill

Run the full agentic commerce readiness audit against a live site — six probe modules (Reachable, Discoverable, Comprehensible, Transactable, Payable, Trustworthy), weighted scoring, and a report that maps every gap to the marketplace skill that closes it. Use when a user asks "is my store agent-ready", "audit my site for agentic commerce", or "what do I need for ACP/UCP/agents to buy from us".

orcaqubits Skill

Set up a WebMCP project — enable Chrome flags, install MCP-B polyfill, scaffold tool registration, and configure development environment. Use when starting a new WebMCP-enabled website from scratch.

orcaqubits Skill

Implement AP2 MCP servers — payment tools exposed via Model Context Protocol for agent access to payment capabilities. Use when building MCP-based payment tool integrations for AP2.

orcaqubits Skill

Implement ACP checkout as an MCP server, exposing checkout operations as MCP tools. Use when building an MCP-based commerce server for AI agents that use tool-calling to complete purchases.

orcaqubits Skill

Apply AP2 cross-cutting development patterns — multi-agent payment architecture, UCP integration, x402 crypto payments, testing with mock providers, and production deployment. Use when architecting agentic payment systems or solving cross-cutting payment concerns.