AI & ML

naubergois Bundle

Use when scripting a screencast or tutorial video before recording it, the user says "script a tutorial", "draft the transcript and timeline", "outline a screencast walkthrough", "plan the demo", or "write the storyboard" for showing how to set up or use a tool (e.g. add an MCP server in Claude Code or Claude Desktop). Reads the tool's real README, install command, and config so the transcript is accurate, drafts an ordered storyboard.md (scenes with type, on-screen actions, narration, one-line caption, pacing), presents STORYBOARD READY FOR APPROVAL, and stops for approval. Never fabricates config or commands. Stack-agnostic and dependency-free; the output can feed screencast-tutorial-video, Google Vids, or a human presenter.

naubergois Skill

NotebookLM でスライドデッキを作成する。「NotebookLM スライド」「NotebookLM スライドデッキ」「NotebookLM プレゼン」「NotebookLM デッキ」などで起動。notebooklm-mcp を使用。 Vendored shiiman-google. Use when the user asks notebooklm-slide or shiiman notebooklm-slide.

naubergois Skill

Índice dos skills públicos de NotebookLM/Google trazidos ao repo. Use when the user asks quais skills Google, login NotebookLM, trazer skills, ou shiiman/sanjay/ibai/mcp.

naubergois Skill

NotebookLM でレポート・ブリーフィングを作成する。「NotebookLM レポート」「NotebookLM ブリーフィング」「NotebookLM 学習ガイド」「NotebookLM ブログポスト」などで起動。notebooklm-mcp を使用。 Vendored shiiman-google. Use when the user asks notebooklm-report or shiiman notebooklm-report.

naubergois Skill

NotebookLM でインフォグラフィックを作成する。「NotebookLM インフォグラフィック」「NotebookLM で図解」「NotebookLM 視覚化」「NotebookLM でインフォグラフィック」などで起動。notebooklm-mcp を使用。 Vendored shiiman-google. Use when the user asks notebooklm-infographic or shiiman notebooklm-infographic.

naubergois Skill

NotebookLM でディープリサーチ（Web 調査）を実行する。「NotebookLM リサーチ」「NotebookLM で調査」「NotebookLM ディープリサーチ」「NotebookLM で調べて」などで起動。notebooklm-mcp を使用。 Vendored shiiman-google. Use when the user asks notebooklm-deepresearch or shiiman notebooklm-deepresearch.

valorisa Bundle

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

valorisa Bundle

Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.

valorisa Bundle

Use when user hits rate limits, quota exceeded errors, context exceeds 40%, or exhibits token waste symptoms (long conversations, wrong model, verbose output, MCP bloat, cache invalidation, expensive files, too many requests)

valorisa Bundle

Advanced meta-skill for creating, reviewing, validating, and improving Claude skills following Anthropic's official patterns. Use when the user asks to build a production-ready skill, audit skill quality, generate complete skill packages with tests and validation, review skill architecture, or optimize skill triggering. Handles all 3 categories (document creation, workflow automation, MCP enhancement).

valorisa Bundle

Promptor v3 Council Edition — Prompt Architect with Multi-Perspective Deliberation

valorisa Bundle

Optimize token consumption in Claude Code through cache management, context forking, model selection, and input filtering. Use when user mentions high token costs, context window bloat, slow sessions, cache invalidation, verbose agent output, heavy MCP load, or any context management issues. Covers four critical axes - cache misses, context bloating, wrong model/effort level, and verbose input formats. Triggers on "tokens", "cost", "expensive", "context", "cache", "slow session", "optimize", or symptoms of token waste even without explicit mention.

valorisa Bundle

Skill d'agent qui impose le décodage contraint pour toutes les sorties destinées à être lues par du code (agents, outils, API, BDD). Elle sépare explicitement la phase de raisonnement libre de la phase de sortie structurée conforme à un schéma ou une grammaire.

valorisa Bundle

Organise un débat structuré entre plusieurs LLM sur un plan, un design ou une idée de projet, avec un cadrage silencieux de type "grill me", des rounds de critique croisée, puis un juge final. Utilise cette skill dès qu’un plan, une architecture, un design ou une idée de projet doit être stress-testé par plusieurs modèles avant décision.

valorisa Bundle

Monitors task execution for skill improvement opportunities. Use this skill during ANY multi-step task, agentic workflow, or substantive work session where the agent is using tools and producing deliverables. It captures patterns, user corrections, workflow insights, and methodology worth preserving as reusable skills. Also triggers during post-task feedback discussions and when the user explicitly mentions skill observations, improvements, the observation log, skill taxonomy, or asks the agent to watch for skill opportunities. Also known as "One Skill to Rule Them All" — trigger on this phrase too. IMPORTANT: this skill should be invoked at the start of every task-oriented session — if you are about to use tools to produce deliverables, invoke this skill first. For reliable activation, pair this description with a CLAUDE.md instruction or harness-level session-start hook (see Recommended Activation Setup) — description-level matching alone is not enforceable.

shawnclybor Skill

Run a Ralph Loop — Stop-hook-driven autonomous iteration on a single prompt. Same prompt re-fed each iteration via a Stop hook that blocks session exit. Claude emits an exact completion-promise string to signal done. Use for well-defined tasks with automatic verification that can run autonomously (overnight, walk-away). Triggers — "ralph this", "ralph loop on X", "autonomous loop on X", "let it iterate until done", "run until completion-promise". Monolithic — one task per loop.

shawnclybor Skill

Structured 3-agent quality review using parallel simplifier, adversarial-reviewer, and chaos-engineer agents. Use when evaluating plans, designs, PRDs, architecture decisions, or any proposal before implementation. Three non-overlapping lenses — KISS/YAGNI, evidence/reasoning, robustness/edge cases.

shawnclybor Skill

A framing diagnostic for "why did this happen?" moments during agent and tool work. Use when the user says "why did this fail", "why did the agent do that", "why is this output wrong", "why isn't this working", or otherwise asks for an explanation of agent/tool behavior. Reads like an incident report — frame the question, surface the assumptions doing silent work, walk the reasoning back, name where the chain honestly ends, point at what to test first.

shawnclybor Skill

Governance layer for all web search operations in the life-crm workflow. Enforces the mandatory use of Brave Search (`brave_web_search` via MCP) and blocks the built-in `WebSearch` tool. Use this skill whenever you are about to perform a web search, look something up online, search for documentation, find current information, or any request that involves querying the web — even if the user just says "look up", "search for", "find out", "google", or "what is the latest on." Also use when you instinctively reach for WebSearch or WebFetch — this skill redirects you to the correct tool. If in doubt about whether a web lookup is involved, use this skill — it's cheap to consult and expensive to use the wrong search tool.

ferocknew Bundle

当用户需要"识别图片文字"、"OCR"、"图片转文本"、"提取图片/截图中的文字"、"图片翻译"时使用此 skill。按优先级决策：优先 LLM 直接读图，LLM 无法识别时才调用系统 OCR；macOS 用系统自带 Vision 框架（零安装），Windows 用 tesseract.js。对话中的图片必须先落盘到临时目录再识别。

ferocknew Bundle

当用户需要查询金融行情、黄金/白银现货期货、A股实时行情、K线数据、新浪财经海外期货、财经新闻、同花顺股票新闻公告研报，或需要调用本地 financial_info_api 的 HTTP/MCP 接口时使用此 skill。

ferocknew Bundle

当用户需要"发送 HTTP 请求"、"调用 REST API"、"测试 API 接口"、"获取网页内容"、"发送 POST/GET 请求"、"使用 fetch API"、"处理 JSON API"时，或者在 JavaScript/Node.js 环境中需要发起 HTTP 请求处理 Web API 时使用此 skill。

ferocknew Skill

---

ferocknew Bundle

当用户要求"查看 Happy Agent 会话"、"管理远程 Agent"、"获取会话状态"、"查看会话历史"、"发送消息到 Agent"时，或者需要与 Happy Coder Agent 进行远程交互时使用此 skill。

ferocknew Bundle

麻将游戏 AI Agent 助手。当用户要求"打麻将"、"麻将游戏"、"麻将 AI"、"四川麻将"、"上海麻将"、"扬州麻将"时，或者需要模拟多人麻将游戏对局时使用此 skill。AI 将扮演 2-3 个 agent 与用户对战。

ferocknew Skill

Publish tweets on X/Twitter using agent-browser automation. Requires Chrome 146+ with remote debugging, X.com account already logged in.

dtsong Skill

Interactive wizard to craft effective prompts using Claude Code best practices

jh941213 Bundle

agent-browser CLI를 활용한 E2E 테스트 자동화. 스냅샷 기반 접근성 트리와 ref 시스템으로 안정적인 브라우저 테스트를 수행. 트리거: "E2E", "브라우저 테스트", "agent-browser", "e2e 테스트 작성", "E2E 테스트", "브라우저 자동화" 안티-트리거: "유닛 테스트", "API 테스트", "pytest", "Jest 테스트만", "Playwright 직접 사용"

tricentis Bundle

Automates Tosca Commander via in-process MCP when Commander is open with a workspace — checkout, tasks, test cases, and Data Integrity. Use for Tosca automation, /commander-mcp, tosca-commander, McpServerAddIn, or when Commander MCP tools connect. Does NOT cover headless TCShell, TCAPI, Remote Control, or CI when Commander is closed (use Commander CLI pack).

i-onlabs Bundle

Run a multi-agent code review on a GitHub pull request, with parallel security / performance / architecture / style passes, inline comments, and quality-gate enforcement. Use when asked to "github code review", "review github pr", "run code review on PR", "swarm review", "automated PR review", or "post inline review comments".

i-onlabs Bundle

Dispatch one focused agent per independent problem domain so investigations run concurrently. Use when facing 2+ independent tasks with no shared state — for example "spawn agents in parallel", "parallel debugging", "fan out tasks", "investigate multiple failures at once", or "distribute independent work across agents".

i-onlabs Skill

Multi-model consensus and escalation framework for critical decisions. Activates when facing architectural choices, security decisions, or when intelligent-gate recommends escalation. Integrates with consult-llm MCP for multi-model opinions.

h1d3r Skill

Apply project-aware Go conventions for services, CLIs, packages, APIs, and tests.

h1d3r Skill

Use red-green-refactor when test-first development is requested or materially reduces implementation risk.

h1d3r Skill

Apply project-aware Java conventions for applications, services, libraries, and tests.

h1d3r Skill

Apply project-aware Rust conventions for services, CLIs, libraries, async systems, and validation.