> Reference: [12-Factor Agents](https://github.com/humanlayer/12-factor-agents)
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →> Reference: [12-Factor Agents](https://github.com/humanlayer/12-factor-agents)
Vercel AI Elements for workflow UI components. Use when building chat interfaces, displaying tool execution, showing reasoning/thinking, or creating job queues. Triggers on ai-elements, Queue, Confirmation, Tool, Reasoning, Shimmer, Loader, Message, Conversation, PromptInput.
Turn a set of local paths (or a beagle project's conventional knowledge locations) into a cited, structured extraction of insights, context, decisions, and raw detail.
commit and push all local changes to remote repo
Guides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternatives, choosing backend strategies, designing subagent systems, or selecting middleware approaches.
Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.
Analyze repo, detect stack, trace changes to user-facing entry points, generate E2E YAML test plan
Go application architecture with net/http 1.22+ routing, project structure patterns, graceful shutdown, and dependency injection. Use when building Go web servers, designing project layout, or structuring application dependencies.
Guides architectural decisions for LangGraph applications. Use when deciding between LangGraph vs alternatives, choosing state management strategies, designing multi-agent systems, or selecting persistence and streaming approaches.
Implements stateful agent graphs using LangGraph. Use when building graphs, adding nodes/edges, defining state schemas, implementing checkpointing, handling interrupts, or creating multi-agent systems with LangGraph.
Compare code implementations across multiple repositories using structured evaluation.
A hardcore Working Backwards coach. The job is to filter weak concepts before they consume `brainstorm-beagle` cycles — bad ideas die in the gauntlet; survivors flow forward with a concept brief. Amaz
>
Turn ideas into comprehensive project specs through collaborative dialogue. Use BEFORE any planning or implementation — for new projects, features, or significant changes. Produces a system-agnostic spec document that can feed into any agentic workflow.
Turn Claude into a strategy interviewer who helps the user produce a strategy document grounded in the kernel framework (diagnosis, guiding policy, coherent action), enhanced with three complementary
Generate ADRs from decisions made in the current session. Extracts decisions, confirms with user, writes MADR-formatted documents.
Adversarial verification of AI-generated work. Spawns an independent verifier to check for false claims, broken code, and security issues.
Interact with Twitter/X through Chrome browser via browser-relay MCP. Post tweets, search trends and hashtags, analyze engagement metrics, create threads, and reply to tweets - with built-in anti-ban protections, platform resilience, and prompt injection defenses.
Delegate coding tasks to Cline CLI (open-source autonomous coding agent). Model-agnostic, supports all major providers. Use for one-shot tasks, CI/CD automation, and parallel workstreams. Requires Node.js 20+.
Manage Todoist tasks, projects, labels, and comments via the todoist CLI wrapper. Use when a user asks to add tasks, list todos, complete items, manage projects, or interact with their Todoist account.
>-
Guides and best practices for working with Neon Serverless Postgres. Covers getting started, local development with Neon, choosing a connection method, Neon features, authentication (@neondatabase/auth), PostgREST-style data API (@neondatabase/neon-js), Neon CLI, and Neon's Platform API/SDKs. Use for any Neon-related questions.
Scan bank statements to detect recurring charges, flag suspicious transactions, and draft refund requests with interactive HTML reports.
Structured memory management that makes agents smarter over time — not through code, but through disciplined capture, consolidation, and distillation of context.
Campaign link builder and pre-launch validator for AI agents. Build UTM-tracked links, validate destinations, and inspect landing pages for social sharing readiness (OG tags, Twitter Cards, viewport, canonical, favicons). The mlz preflight command does everything in one call and returns a go/no-go report.
Security middleware for AI agents handling money. Non-custodial crypto wallets and virtual Visa cards with spending limits, whitelists, and human approval.
Memória persistente **automática** para o OpenClaw:
OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.
Create professional posters and visual designs using AI image generation. Supports event posters, product showcases, announcements, and social media graphics. Integrates with Gemini image generation API to create visuals based on templates and user content. Use when the user wants to design posters, generate marketing visuals, create promotional materials, or produce image-based content for events, products, or announcements.
llm-provider-forensics
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
Interact with PikaBoard task management API. Use when creating, updating, listing, or managing tasks. Agent-first kanban for AI teams. Triggers on: tasks, kanban, board, todo, backlog, sprint.
Find AI agent work, apply for positions, manage tickets, and collaborate on projects via OpenPod marketplace (openpod.work). Use when the user mentions finding work, freelance projects, agent jobs, OpenPod, or earning USDC for AI tasks.