AI & ML

gitbutlerapp Bundle

Use for prompts like "get context for branch", "catch up on this branch", "recover branch context", or "what prior agent work happened here". Skim prior agent work from `but agentlog` captures for a GitButler branch, review / pull request / merge request, or change. Prefer this over generic git branch/diff inspection when the user asks for context, history, prior work, or branch catch-up.

humanlayer Bundle

interview the user to design an agentic control loop (sensor, controller, actuator under disturbances) tailored to their codebase, then build it as locally-runnable components plus a scheduled coding-agent workflow

humanlayer Bundle

build a repo-local skill and install a matching iterated coding-agent GitHub Actions workflow, prompt, memory file, and reference templates

michalparkola Skill

Summarize the current conversation session and append results to the weekly agent-log. Use when user says "log this", "session log", "summarize this session", or asks to write results to the agent-log.

mrtooher Bundle

Enforces staged execution discipline on large tasks: a written stage plan, delegation to named fable agents where the runtime supports it, a failable verification check at each stage, and a skeptical self-review before delivery. Trigger when the user explicitly asks ("do this thoroughly", "be systematic", "deep work mode") OR when the task objectively spans multiple files, multiple sources, or multiple sessions. Do NOT trigger on ordinary multi-step requests that a direct attempt handles fine. For a run pinned to a specific model, use fable-fable, fable-opus, fable-sonnet, or fable-haiku instead. Always-on guardrails (verify-before-flag, warning batching, sed safety) live in the companion execution-guardrails skill.

mrtooher Skill

Run fable-mode execution discipline on Claude Opus — one rung below Fable 5.1 on the escalation ladder. Routes the task to the @fable-orchestrator agent (Opus, Write-less), which stages the work, delegates artifact production to @fable-worker-sonnet / @fable-worker-haiku, and cold-checks deliverables with @fable-verifier. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling on Opus ("fable on opus", "stage this on opus", "deep work mode, opus"). Escalate to fable-fable when the orchestrator reports the task exceeds Opus's ceiling. Do NOT use for ordinary single-pass tasks — and prefer fable-sonnet or fable-haiku when the task doesn't need peak reasoning.

mrtooher Skill

Run fable-mode execution discipline on Claude Fable 5.1 — the top of the escalation ladder and the strongest staged run available. Routes the task to the @fable-orchestrator agent with its model overridden to Fable (`model: "fable"`), which stages the work, delegates artifact production to @fable-worker-sonnet / @fable-worker-haiku, and cold-checks deliverables with @fable-verifier. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling on the strongest model ("fable on fable", "stage this on fable", "deep work mode, fable", "run this on 5.1"), or when a fable-opus run reports the task exceeds Opus's ceiling. Benchmarked 2026-09-02: zero correctness delta on Fable 5.1 at ~1.1× tokens, ~2× wall — a provenance runner, not an accuracy runner. Do NOT use for ordinary single-pass tasks — prefer fable-opus, fable-sonnet, or fable-haiku when the task doesn't need peak reasoning. Fable is plan-included; bulk work still routes down-tier.

mrtooher Skill

Run fable-mode execution discipline on Claude Haiku. Routes the task to the @fable-worker-haiku agent, whose definition carries the staged loop with tightened verification (no bare "unverified" allowed) and an escalate-don't-improvise rule. Trigger when the user explicitly asks for thorough/systematic handling run cheaply or fast ("fable on haiku", "deep work mode but cheap", "stage this on haiku"). For bulk mechanical work. Do NOT use for tasks needing synthesis — benchmark note: at n=1 the skill's effect on Haiku swung both directions (+25 / −17); route quality-critical work to fable-sonnet instead.

mrtooher Skill

Automatic final verification pass on completed deliverables. Runs automatically at the end of every fable-mode run (fable-mode, fable-fable, fable-opus, fable-sonnet, fable-haiku) — those skills invoke it before delivery. Also triggers when the user says "double check this", "double-check", or wants the finished work re-checked without doing it themselves. Uses a panel of model-tier checker agents (Haiku for mechanical checks, Sonnet for logic/requirements, Opus to adjudicate disagreements) to verify the finished output — not to redo the task. Any FAIL gets fixed and re-checked before delivery. Do NOT trigger on work still in progress, and never trigger on its own output (no recursion).

mrtooher Skill

Run fable-mode execution discipline on Claude Sonnet. Routes the task to the @fable-worker-sonnet agent, whose definition carries the staged loop with step-3 verification enforced hardest (Sonnet's known gap), optionally followed by a cold @fable-verifier pass. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling on Sonnet ("fable on sonnet", "stage this on sonnet", "deep work mode, sonnet"). The balanced default between Haiku (cheap/fast) and Opus/Fable (peak reasoning). Do NOT use for ordinary single-pass tasks.

mrtooher Skill

Always-on operational guardrails, model-independent. Apply on EVERY task and EVERY model (Fable, Opus, Sonnet, Haiku, and any future tier) whether or not fable-mode's staged loop is running. Three rules: (1) verify-before-flag — never raise a warning about a problem that hasn't been confirmed present by a direct check; (2) warning batching — accumulate minor concerns and surface them together at a threshold instead of interrupting piecemeal; (3) find-and-replace safety — word-boundary anchoring on sed/substring edits plus a corruption grep afterward. Trigger whenever a response would flag a problem, raise a warning, or edit files with search-and-replace. These are behavioral contracts with the user, not capability aids — they do not depend on model strength.

shino369 Bundle

Expert knowledge in creating and configuring Claude Code components (subagents, skills, slash commands, hooks, MCP integrations). Use when the user asks to create, modify, or extend .claude/ directory components. Follows official best practices and documentation standards.

tigerfintech Bundle

Tiger Brokers OpenAPI Python SDK — complete skills for AI coding tools. Covers SDK setup, market data queries, stock/futures/options trading, real-time push subscriptions, CLI command-line tool, and MCP server integration. Use when building trading applications, querying market data, placing orders, using the tigeropen CLI, or integrating Tiger Brokers API with AI editors. 老虎证券 OpenAPI Python SDK 完整技能集。涵盖 SDK 配置、行情查询、股票/期货/期权交易、实时推送订阅、CLI 命令行工具、MCP Server 集成。适用于构建交易应用、查询行情数据、下单交易、使用 tigeropen CLI、或将老虎 API 集成到 AI 编辑器。 用户提到以下关键词时自动使用 / Auto-activate on these keywords: 行情、报价、价格、K线、快照、买卖盘、深度、买入、卖出、下单、撤单、改单、交易、持仓、资金、账户、订单、委托、期权、期权链、到期日、期货、推送、订阅、选股、筛选、tigeropen、tiger API、quote、price、K-line、order、buy、sell、trade、position、asset、account、option、future、push、scanner

0juano Bundle

Search Argentine legal databases (SAIJ, JUBA, CSJN, JUSCABA) for jurisprudence, legislation, case summaries, and doctrine using the `ley` CLI. Use when the user asks about Argentine law, court decisions, legal precedents, fallos, jurisprudencia, legislación, or mentions SAIJ, JUBA, CSJN, JUSCABA. Supports parallel search across databases, JSON/table/text output, and filtering by jurisdiction. Built from reverse-engineered MCP servers (hernan-cc) — direct HTTP calls, no MCP layer needed.

0juano Bundle

Build, update, and operate TRMNL e-ink private plugins end to end — webhook data updates and merge variables, Liquid markup with Framework 3.1, the per-plugin MCP server (stateless JSON-RPC), an offline preview/screenshot harness, and battery-aware refresh cadence. Use when working with TRMNL devices (OG or TRMNL X), trmnl.com private plugins, webhook payloads, e-ink dashboard markup, the TRMNL MCP API, or debugging clipped, empty, or stale TRMNL renders.

ai-native-camp Bundle

Day 2 보충 자료 - MCP 딥다이브. Claude Code에 외부 도구를 연결하는 MCP를 체계적으로 배운다. "MCP 배우기", "MCP 보충", "MCP 강의", "MCP 학습" 요청에 사용.

arcjet Bundle

Add Arcjet security protection to HTTP routes, AI agent tool calls, MCP servers, background jobs, and queue workers. Covers rate limiting, bot detection, email validation, prompt injection, sensitive information blocking (including Rampart NER), content moderation, capture/flush, remote Guard policies, typed inputs, and abuse prevention. Works in JavaScript/TypeScript, Python, and Go. HTTP frameworks share this skill. JS Guard adapters (Vercel AI SDK, Eve, Mastra, LangChain, LangGraph, OpenAI Agents, Genkit, Google ADK, Strands, TanStack AI, Claude Agent SDK, Claude Managed Agents) are per-adapter reference files loaded from Step 3 — do not keep the whole JS Guard reference in context. Official Python LangChain, CrewAI, OpenAI Agents, Claude Agent SDK, Claude Managed Agents, and Strands Agents have dedicated integrate-arcjet-guard skills. Use when the user wants security, rate limiting, bot protection, or abuse prevention – "protect my API," "rate limit tool calls," "block bots," "secure my endpoint," or "pre

arcjet Skill

Integrate Arcjet Guard into official CrewAI — register process-wide PRE_TOOL_CALL with register_arcjet_hooks, or wrap a standalone BaseTool you call yourself with guard_tool. Use when asked to add Arcjet to CrewAI, LiteAgent, crew-injected tools, rate limit those tools, screen inbound messages before kickoff, or block prompt injection / PII. Official crewai only; not an npm CrewAI port and not LangChain Crew wrappers.

arcjet Skill

Integrate Arcjet Guard into Python LangChain — wrap a BaseTool you call with guard_tool, put ArcjetMiddleware + ToolPolicy on create_agent, or observe a chain with ArcjetCaptureHandler. Use when asked to add Arcjet to LangChain, create_agent, langchain-core tools, rate limit those tools, screen inbound messages, or block prompt injection / PII. This is Python LangChain, not LangChain JS createAgent and not LangGraph JS.

arcjet Skill

Integrate Arcjet Guard into Python OpenAI Agents — wrap FunctionTool / function_tool with guard_tool and read a caller-owned session or conversation id via openai_agents_context. Use when asked to add Arcjet to openai-agents, Runner.run, rate limit those tools, screen inbound messages, or block prompt injection / PII. This is Python openai-agents, not the JS @openai/agents adapter.

arcjet Skill

Integrate Arcjet Guard into Python Strands Agents — wrap authored @tool with guard_tool, and put guard_hooks on Agent(hooks=) for unwrapped / MCP tools via BeforeToolCallEvent.cancel_tool. Use when asked to add Arcjet to strands / strands-agents, rate limit those tools, screen inbound messages, or block prompt injection / PII. This is Python strands, not JS @strands-agents/sdk.

arcjet Skill

Integrate Arcjet Guard into the Python Claude Agent SDK — wrap authored @tool with guard_tool, and use guard_hooks for UserPromptSubmit inbound plus PreToolUse on unwrapped built-ins / MCP. Use when asked to add Arcjet to claude-agent-sdk, rate limit those tools, screen inbound prompts, or block prompt injection / PII. This is Python claude-agent-sdk, not the JS adapter and not Claude Managed Agents hosted sessions.

arcjet Skill

Integrate Arcjet Guard into Python Claude Managed Agents — screen user.message with guard_events before sessions.events.send, and gate custom tools on agent.custom_tool_use with guard_custom_tool. Use when asked to add Arcjet to hosted Claude Managed Agents, anthropic beta sessions, rate limit custom tools, or block prompt injection on hosted sessions. Not Claude Agent SDK local query() / PreToolUse.

giulioco Bundle

Craft highly effective prompts for Nano Banana Pro (Gemini image generation). Use when generating images with Nano Banana Pro for any purpose including photorealistic portraits, product photography, creative experiments, e-commerce mockups, social media content, editorial layouts, 3D renders, era-specific aesthetics (Y2K, 2000s, 1990s), miniature/diorama effects, or any advanced image generation task. Provides proven prompt patterns, technical specifications, JSON structuring, identity preservation techniques, and style-specific templates.

httprunner Bundle

Multimodal UI understanding and single-step planning via OpenAI-compatible Responses APIs. Use when you need AIQuery/AIAssert and plan-next to extract UI element coordinates, validate UI assertions, summarize screenshots, or decide the next UI action from an image. External agents handle execution via adb/hdc and multi-step loops. Defaults to Doubao models but can be pointed at other multimodal providers via base URL, API key, and model name.

imagekit-developer Skill

Routing guide for ImageKit's two MCP servers (imagekit_api and imagekit_devtools) — maps each capability to the correct server and tool, and covers the routing rules (e.g. never upload local files via execute). Use before calling any ImageKit MCP tool. Covers file management, folder ops, cache purge, metadata, docs search, transformation building, and upload routing.

memtensor Bundle

Find the most relevant external agent skills for the current task, then submit grounded feedback about which skills were actually used and useful in the same session. Whenever you start a task, use this skill first.

millionco Skill

Use when editing .tsx/.jsx/.css/.html, React components, pages, routes, forms, styles, or layouts. Also when asked to test, verify, validate, QA, find bugs, check for issues, or fix expect-cli failures.

millionco Skill

Systematic evidence-based debugging using runtime logs. Generates hypotheses, instruments code with NDJSON logs, guides reproduction, analyzes log evidence, and iterates until root cause is proven with cited log lines. Use when the user reports a bug, unexpected behavior, or asks to debug an issue.

millionco Skill

Write and improve agent skills (SKILL.md files). Use when creating new skills, refactoring existing ones, debugging why an agent ignores instructions, or improving compliance. Covers prompt structure, TDD for skills, description optimization, and rationalization bulletproofing.

novuhq Bundle

Author step content for Novu workflows defined in the Dashboard or generated/edited via the Novu MCP. Use when filling in step controls (subject, body, editorType, headers, body, conditions) for email, in-app, sms, push, chat, delay, digest, throttle, or HTTP Request steps.

tavily-ai Skill

Set up, authenticate, update, troubleshoot, or choose between Tavily CLI web commands. Use when the user asks about the Tavily CLI, installing Tavily skills, first-time setup, authentication, keyless limits, CLI updates, or which Tavily command to use. For an ordinary web task, use the specific search, extract, map, crawl, research, or dynamic-search skill instead.

tavily-ai Skill

Search the web with LLM-optimized results via the Tavily CLI. Use this skill when the user wants to search the web, find articles, look up information, get recent news, discover sources, or says "search for", "find me", "look up", "what's the latest on", "find articles about", or needs current information from the internet. Returns relevant results with content snippets, relevance scores, and metadata — optimized for LLM consumption. Supports domain filtering, time ranges, and multiple search depths.

tavily-ai Skill

Extract clean markdown or text content from specific URLs via the Tavily CLI. Use this skill when the user has one or more URLs and wants their content, says "extract", "grab the content from", "pull the text from", "get the page at", "read this webpage", or needs clean text from web pages. Handles JavaScript-rendered pages, returns LLM-optimized markdown, and supports query-focused chunking for targeted extraction. Can process up to 20 URLs in a single call.

tavily-ai Skill

Programmatic Tavily search with context isolation. Use when web search or extraction will return large results that need filtering, deduplication, or multi-step triage before they enter the model context. Use tavily-search for ordinary lookups and tavily-research for end-to-end cited synthesis.

zenmux Skill

Guide users through configuring ZenMux Base URL, API endpoint, API Key, and model settings for tools or SDKs. Use when the user wants to set up, configure, or connect ZenMux in Cursor, Claude Code, Cline, Cherry Studio, Open-WebUI, Dify, Obsidian, Sider, Copilot, Codex, Gemini CLI, opencode, or custom SDK code. Trigger on "configure", "setup", "set up", "base url", "endpoint", "api key", "how do I set up ZenMux", "help me fill in API settings", "接入", "配置", "设置", "base url 填什么", "怎么填", "怎么接入", "API 地址", "接口地址". Treat the user as a first-time user and guide step by step. Do not use for usage queries or docs lookups; use zenmux-usage or zenmux-context instead.