arnesto

Set a goal that Cursor will pursue to completion.

Define, compose, and wire Google ADK agents with function tools and multi-agent orchestration. Use when writing agent definitions, adding Python function tools, building pipelines with SequentialAgent/LoopAgent/ParallelAgent, or designing router/delegation patterns. Trigger on: adk agent, LlmAgent, SequentialAgent, LoopAgent, ParallelAgent, AgentTool, function tool, output_key, output_schema, agent routing.

Bootstrap a Google ADK (Agent Development Kit) project from zero to a running local dev UI. Use when setting up a new ADK agent project, configuring Vertex AI credentials, scaffolding the agent folder, or troubleshooting ADK environment issues. Trigger on: adk setup, adk init, google-adk, vertex ai agent, uv run adk, adk web.

Color-code the Obsidian graph view by rewriting `.obsidian/graph.json` colorGroups. Use this skill when the user says "color my graph", "color code obsidian", "colorize the graph", "color the graph by tag", "color by category", "highlight visibility in graph", "make the graph colorful", "distinguish tags in graph", or wants nodes in Obsidian's graph view tinted by tag, folder, or visibility. Generates a `colorGroups` array from the vault's actual tags/categories and merges it into the existing graph.json without clobbering other graph settings. Always backs up first.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Use when asked to "growth loops", "build a growth engine", "design a viral loop", "create a content loop", "move beyond paid acquisition", or "why isn't growth compounding". Helps design self-reinforcing growth systems where output becomes input. The Growth Loops framework (from Brian Balfour / Reforge and Elena Verna) shifts thinking from linear funnels to compounding loops.

Evaluate or integrate Headroom for large repetitive tool outputs, JSON, logs, or retrieved context. Use when the user names Headroom or asks to measure context compression in an application they control. Start with a local library trial; not a default proxy, provider switch, prose-shortening mode, or solution for an ordinary small command result.

Applies hexagonal (ports & adapters) architecture. Use when designing application structure, separating domain from infrastructure, creating testable boundaries, or when user mentions ports, adapters, hexagonal, or clean architecture.

Use when asked to "define our core action", "North Star metric", "accruing benefits", "improve retention mechanics", "hierarchy of engagement", or "Sarah Tavel framework". Helps consumer products identify the actions and benefits that drive long-term retention. The Hierarchy of Engagement framework (created by Sarah Tavel at Benchmark) maps progression from core action to mounting loss.

Use when asked about "marketplace strategy", "chicken and egg problem", "liquidity", "two-sided market", "tipping a marketplace", "GMV growth", or "Sarah Tavel marketplaces". Helps founders and product leaders build defensible marketplace businesses by sequencing supply and demand. The Hierarchy of Marketplaces framework (created by Sarah Tavel / Benchmark) provides a progression from focused launch to market dominance.

Use when asked to "build habit-forming products", "Hooked model", "trigger action reward investment", "create sticky behavior loops", or "design habit loops". Helps design products that form unprompted user habits. The Hooked Model (created by Nir Eyal) explains how products create habits through Trigger, Action, Variable Reward, and Investment.

Use on demand when the user requests Humanizer, asks to rewrite AI-sounding prose in the author's voice, or accepts that recommendation for a public or professional draft. Includes a Spanish/English communication profile. Recommend it in fitting prose tasks; ask before an unrequested broader rewrite.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Fetch a URL and distill its content into the Obsidian wiki. If invoked from inside a project directory, the page lands directly in that project's folder (creating the project in the vault if needed). Otherwise it goes to misc/ and gains project affinity over time. Use this skill when the user says "/ingest-url <url>", "add this URL to the wiki", "ingest this link", "save this page", or pastes a URL and asks to save that link or page to the wiki.

Use when asked to "jobs to be done", "JTBD", "why customers churn", "prep for customer interviews", "hire and fire products", or "find real competitors". Helps discover unmet needs and the context behind purchasing decisions. The Jobs to be Done framework (created by Clayton Christensen and Bob Moesta) explains why customers hire and fire products.

Launches agent teams with structured roles and task decomposition. Use when asked to create a team, spawn teammates, or coordinate multiple agents in parallel.

Guide AI adoption decisions in software development using Lean, Extreme Programming, and pragmatic simplicity. Use when evaluating AI tools, agents, workflows, prompts, automations, or rollout guardrails; deciding whether to automate or keep work manual; detecting tool sprawl, prompt graveyards, or low-value AI assets; or defining team standards for AI usage.

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.

The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources → wiki → schema). Also use when discussing knowledge management strategy, wiki structure decisions, or how to organize distilled knowledge. This is the "theory" skill — other skills handle specific operations (ingesting, querying, linting).