AI & ML

masanao-ohba Skill

Invoke when deciding which agent handles a task. Provides routing decisions based on task type, scale classification, and agent capabilities, outputting a sequenced routing plan with parallel opportunities.

masanao-ohba Skill

Invoke when coordinating multi-agent execution via TeamCreate. Provides workflow templates (team setup, task dependencies, retry loops, failure handling), progress tracking via TaskList, and coordination patterns.

wix Bundle

Build and release a Wix Headless site from a single prompt, on shipped, verified @wix/sdk code — this entry takes a cold environment (prerequisites, Wix sign-in) to the point where the wix-headless-fast skill runs the build. Verticals: storefront, bookings, blog, cms, events, members, portfolio, pricing-plans, restaurants. Triggers: build me a store/blog/booking/events/portfolio/restaurant site fast, sell tickets or membership plans headless, wix headless fast entry.

tenequm Bundle

Run coding agents (codex, claude, Antigravity/agy) headlessly through the acpx ACP CLI. Use before launching or prompting an acpx subagent, and when an acpx command fails, a session is not found, or a prompt seems lost.

tenequm Bundle

Launch and drive coding agents (codex, claude, agy) through the Herdr CLI. Use before starting or prompting a subagent via herdr agent or pane commands, and when a herdr command fails or an agent seems stuck or silently lost a prompt.

masanao-ohba Skill

Invoke when quality-reviewer identifies refactoring opportunities in CakePHP code. Produces prioritized refactoring recommendations covering fat controller reduction, model extraction, query optimization, and CakePHP best practice alignment.

corygabrielsen Skill

Strip overspecified instructions from an artifact. Trust the model's intuition — prescribe intent, not format.

swarmclawai-andrej-karpathy-skills Skill

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

alanlee0323 Bundle

Expert system for Ultralytics YOLO workflows (including YOLO26). Use when the user asks about training, validation, inference, dataset setup, model export, tracking, or performance tuning in Ultralytics.

alanlee0323 Skill

Expert system for generating Agent Skills compatible with any LLM agent (Copilot, Gemini, Codex, Claude, etc.). Enforces folder structure, YAML standards, and best practices.

corygabrielsen Bundle

Observe→decide→act loop. Halts on target, stall, cap, or human/agent delegation.

alanlee0323 Skill

Acts as a QA Auditor and Red Team for new Agent Skills. Verifies structure, safety guardrails, and compliance with global-rules.

tenequm Bundle

Build, harden, and debug production MCP servers with the TypeScript SDK. Use when writing or reviewing an MCP server - transports, tool schemas, errors, OAuth, token bloat, SDK migrations, MCP Apps, Registry. Assumes a server already exists.

tenequm Bundle

Opinionated best practices for building Agent Skills - SKILL.md structure, frontmatter, description writing, progressive disclosure, testing, distribution. Use when creating or reviewing a skill, or debugging why one will not trigger.

tenequm Bundle

Durable project knowledge as Git-native OKF bundles (docs/knowledge/, one concept per file, with provenance and trust tiers). Use to record a decision, finding, or rule that must outlive the session. Not session state or agent instructions.

alanlee0323 Skill

在數據收集（collecting-market-data, scanning-macro-news）與分析鏈之間的強制驗證閘門。執行三層數據品質檢核：多源交叉對標、統計異常偵測、LLM 邏輯與真實性審查。遵循「Garbage In, Garbage Out」原則——所有下游分析的品質上限取決於此技能。

alanlee0323 Bundle

Creates and maintains agent onboarding files (AGENTS.md, CLAUDE.md, GEMINI.md, copilot-instructions) for a repository — what belongs in them, what must stay out, and how to verify every documented command actually works. Use when the user says init, 初始化專案, onboarding, 建立 AGENTS.md, or when starting agent work in an undocumented repo.

alanlee0323 Skill

Creates new agent skills from a user-specified knowledge folder. Use when the user asks to convert notes, docs, templates, or domain references into reusable SKILL.md packages.

respira-press Skill

Use when the user says 'get started with my site', 'connect to my wordpress site', 'what can you do on my site', or 'onboard'. Verifies connectivity, discovers the site architecture, maps the available MCP tools, and produces a site briefing.

ruvnet-agentdb Skill

Initialize an AgentDB Cognitive Container (.rvf file) in the current project. Sets up storage, embedder config, and the agentdb MCP server. Use when the user is starting a new project that needs vector memory, or asks to "set up agentdb" / "init agentdb".

ruvnet-agentdb Skill

Store a memory in AgentDB — an episode (task + outcome + critique), a pattern, or a skill. Use when the user says "remember this", "save this for later", "add to memory", or when the agent has just succeeded/failed at a task and the lesson is worth keeping.

aisa-team-openclaw-starter-kit Bundle

Replace 100+ API keys with one. Instant access to LLMs, Twitter, YouTube, LinkedIn, Finance, Tavily & Scholar data. Enterprise stability for your local agent.

aisa-team-openclaw-starter-kit Bundle

OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.

respira-press Skill

Use when the user says 'make my store visible to chatgpt', 'set up product feeds', or 'make my store agent-ready', or asks about Google Merchant Center, a store llms.txt, or cart links for AI agents. Sets up product feeds in six formats and registers the catalog with the major platforms.

motlin Skill

Work with markdown-based task lists in .llm/todo.md files. Use when managing tasks, working with todo lists, extracting incomplete tasks, marking tasks complete, or implementing tasks from a task list.

motlin Skill

Guidelines for working with LLM context stored in the .llm/ directory.

aisa-team Bundle

Generate images and videos with AIsa. Four image models (Google Gemini 3 Pro Image, Alibaba Wan 2.7 image + image-pro, ByteDance Seedream) and four Wan video variants (wan2.6/2.7 × t2v/i2v). One API key; the client routes each model to the correct endpoint automatically.

aisa-team Bundle

Professional US stock analysis with financial data, news, social sentiment, and multi-model AI. Comprehensive reports at $0.02-0.10 per analysis. Use when: the user needs market data, stock analysis, watchlists, or portfolio workflows.

aspiers Skill

Deletes files and directories through a wrapper that avoids the usual per- command permission prompt. Use whenever files or directories need removing — clearing build artifacts or temporary files, or dropping obsolete files and directories during a refactor.

aspiers Bundle

Use the Xero MCP server — obtain/refresh OAuth2 bearer tokens, troubleshoot authentication, and pick up other operational notes for working with Xero MCP tools. Use when Xero MCP tools fail with authentication errors, when the bearer token has expired (tokens last ~30 min), before starting any Xero workflow, or for general guidance on Xero MCP usage.

motlin Skill

Convert a planning discussion into self-contained tasks in .llm/todo.md.

motlin Skill

Import a plan markdown file into .llm/todo.md as self-contained implementation tasks.

motlin Skill

Find TODO comments in the codebase and add them to .llm/todo.md as tasks.

motlin Skill

Work through all incomplete tasks in .llm/todo.md with one subagent and commit per task, continuing past blocked tasks.

motlin Skill

Recover blocked [!] tasks from archived task lists back into .llm/todo.md. Use when the user asks to unblock, recover, retry, or resurrect blocked tasks, or wants to know what blocked work is waiting in the archives.

motlin Skill

Formatting and privacy rules for SKILL.md, agent, and command files. Load before creating, editing, or reviewing one, and pair with the skill that does the work: skill-creator:skill-creator, skill-extractor:skill-extractor, or claude-md-management:revise-claude-md / claude-md-management:claude-md-improver.