Top Agent Skills

Analisa alterações staged/unstaged e cria commits convencionais semânticos com contexto sobre POR QUÊ, não apenas O QUÊ. Detecta automaticamente tipo e escopo do commit a partir do diff. Suporta argumentos opcionais de tipo/escopo. Uso - /commit-smart, /commit-smart fix, /commit-smart refactor api

Listar, alternar e configurar projetos do Railway. Use quando o usuário quiser listar todos os projetos, alternar entre projetos, renomear um projeto, ativar/desativar deploys de PR, tornar um projeto público/privado ou modificar configurações do projeto.

Criar pull requests seguindo as convenções do Sentry. Use ao abrir PRs, escrever descrições de PR ou preparar mudanças para revisão. Segue as diretrizes de revisão de código do Sentry.

I'm ready to help you review code changes on your branch for bugs, security vulnerabilities, and code quality issues.

Template do pack (backend/09-rust-axum.md). Orienta o agente em APIs, servicos e arquitetura backend alinhado a esse contexto.

Uso do SDK JavaScript para aplicações cliente PocketBase. Use ao chamar PocketBase a partir do frontend ou Node.js, autenticar usuários, subscrever a eventos em tempo real, fazer upload de arquivos, ou trabalhar com o SDK PocketBase JS/TS. Cobre operações CRUD, fluxos de autenticação, authStore, SSE em tempo real, manipulação de arquivos, operações em lote e sintaxe de query.

Procure e implante serviços do marketplace de templates do Railway. Use quando o usuário quiser adicionar um serviço de um template, encontrar templates para um caso de uso específico, ou implantar ferramentas como Ghost, Strapi, n8n, Minio, Uptime Kuma, etc. Para bancos de dados (Postgres, Redis, MySQL, MongoDB), prefira a skill railway-database.

Itere em uma PR até que o CI passe. Use quando precisar corrigir falhas de CI, endereçar feedback de revisão, ou continuamente enviar correções até que todas as verificações fiquem verdes. Automatiza o ciclo de feedback-correção-push-aguardar.

INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.

Template do pack (dominio/15-filas-jobs.md). Orienta o agente em regras de negocio e requisitos de produto alinhado a esse contexto.

Template do pack (fullstack/01-t3-stack.md). Orienta o agente em stacks fullstack e arquitetura ponta a ponta alinhado a esse contexto.

Especialista em CrewAI - o principal framework multi-agente baseado em papéis utilizado por 60% das empresas da Fortune 500. Abrange design de agentes com papéis e objetivos, definição de tarefas, orquestração de crew, tipos de processo (sequencial, hierárquico, paralelo), sistemas de memória e flows para workflows complexos. Essencial para construir equipes colaborativas de agentes IA. Use quando: crewai, equipe multi-agente, papéis de agentes, crew de agentes, agentes baseados em papéis.

Gerenciar deployments do Railway - visualizar logs, reimplementar, reiniciar ou remover deployments. Use para ciclo de vida de deployment (remover, parar, reimplementar, reiniciar), visibilidade de deployment (listar, status, histórico) e troubleshooting (logs, erros, falhas, travamentos). NÃO é para deletar serviços - use a skill railway-environment com isDeleted para isso.

Otimize conteúdo para ser citado por mecanismos de busca com IA — ChatGPT, Perplexity, Google AI Overviews, Claude, Gemini, Copilot. Use quando quiser que seu conteúdo apareça em respostas geradas por IA, não apenas ranqueado em links azuis. Gatilhos: 'otimizar para busca IA', 'ser citado pelo ChatGPT', 'AI Overviews', 'citações Perplexity', 'AI SEO', 'busca generativa', 'visibilidade em LLM', 'GEO' (otimização para motores generativos). NÃO para SEO tradicional (use seo-audit). NÃO para criação de conteúdo (use content-production).

Template do pack (backend/04-go-chi-gorm.md). Orienta o agente em APIs, servicos e arquitetura backend alinhado a esse contexto.

Compact the current conversation into a handoff document so a fresh agent can pick up the work with zero prior context. Use when the user wants to end a session and continue later, is running low on context, says "write a handoff", "hand this off", "summarize for the next session", "compact this", or wants to transfer work to another agent or teammate.

Restructure any response for an ADHD brain — TL;DR first, ELI16 clarity, short punchy steps, one clear next action, zero walls of text. Use this skill whenever the user says "elihadhd", "adhd mode", "tldr", "eli16", "eli5", "too long", "overwhelmed", "shorter", "just tell me what to do", "break this down", "snap it", "gauntlet", or shows signs of overwhelm (e.g. "wait what", "I'm lost", "too much"). Also use it when the user asks for the simple version, the quick version, or the punchy version of anything — explanations, plans, debugging help, docs, decisions. When in doubt about whether a response is too heavy, use this skill.

Scan a codebase, live app, or site and find the features that obviously should exist but don't — missing exports, bulk actions, search/filter, undo, history, notifications, dead-end workflows, data collected but never surfaced, backend endpoints with no UI, and half-built features that stopped partway. Produces an evidence-backed, ranked punch list (top 10 max) with a portable gap_packet JSON. Use whenever the user asks "what features are missing", "what's this app lacking", "find gaps", "run gap-scan", "feature audit", or wants proposal ammo from a prospect's app. Also use it to recheck an existing gap_packet — "what's left to do", "recheck the gaps", "what got built since" — re-verifying findings against current code and marking stale ones superseded. Flags ABSENCE only — broken code goes to code-audit, confusing flows to ux-audit, weak persuasion to conversion-audit, underexploited assets to a WWBD-style analysis. If something exists but is bad, it's not a gap — hand it off.

Approach an app, tool, codebase, website, or product as a genuine first-time user with zero insider context — try it out using only the information provided, get confused where a real newcomer would, and surface the "obvious" questions that people who built or use the thing daily can no longer see. Use this whenever the user wants a first-time-user test, a fresh perspective, a naive walkthrough, a cold read of their README/onboarding/docs/UI, or says things like "pretend you've never seen this", "would a new user get this?", "test my app like a beginner", "what would confuse someone new?", or "give me fresh eyes on this". Also use it when someone wants to find gaps in onboarding, docs, or first-run experience — even if they don't say "fresh eyes" explicitly.

Write the context brief a first-time tester gets before testing an app, tool, codebase, or product — it explains WHAT the thing is and why it exists, while deliberately withholding HOW anything works. The companion to the fresh-eyes skill; the brief it produces is the "starting information" handed to a fresh-eyes tester. Use this whenever the user is preparing a fresh-eyes or first-time-user test and needs the setup material, or says things like "describe my app without giving anything away", "write the context card for the tester", "explain what it is but not how to use it", "set up the newcomer test", "what would the tester be told going in?", or wants a spoiler-free description of their product. Also use it when someone asks for the briefing/intro that a new tester, new hire, or evaluator should receive before first contact with the thing being tested.

Audit a landing page or marketing site through one lens: what is the ONE thing this page wants the visitor to do, and does every element on the page move them toward it? Reconstructs who lands on the page and why, spawns visitor-persona agents to react to it cold, maps the belief chain a visitor must climb before acting, inventories CTAs and everything competing with them, then delivers a prioritized cut/move/add/rewrite plan. Use whenever the user asks "what do we want people to do on this page", "is this page converting", "critique this landing page", "why would someone book/buy/sign up here", "audit the funnel on X page", or wants strategic critique of page content and structure (not visual polish). Works from frontend code in a repo, a live URL via browser tools, or pasted copy/screenshots. Judges persuasion and intent-alignment; for flow usability and friction use ux-audit, for visual and aesthetic quality use the impeccable critique/audit skills.

Decompose an unknown quantity into 3-5 estimable factors and produce a defensible order-of-magnitude answer without needing precise data. Load when the user needs to size something without data — market size, resource requirements, effort estimates, user numbers, costs — or when a decision is blocked by "we don't know the numbers". Also triggers on "ballpark this", "rough estimate", "how big is this market", "how long would this take", "how many users", or when deep-thinking diagnoses a sizing/estimation frame. The goal is not precision — it is a defensible answer that enables a decision to be made. Based on Enrico Fermi's estimation method.

Orchestrate persistent agent memory across coding sessions, repos, and tools. Load when the user asks to remember, recall context, save project memory, create a handoff, manage global memory, update memory, compact memory, audit memory, forget memory, continue from prior sessions, or before commit/push/git operations that checkpoint project state.

Append structured execution traces across operational, cognitive, and contextual surfaces with minimal overhead. Load when inspecting agent runs, logging tool calls and observations, enabling post-run debugging, or pairing with structured-planning step IDs. Also triggers on "trace this run", "log execution", "agent observability", "run log", or when fault-localize needs evidence. Default-on during multi-step plans. Traces live at .agent-loom/traces/ — git-ignored by default.

Score LLM and agent outputs using LLM-as-judge techniques — direct scoring against rubrics or pairwise comparison between two outputs. Includes built-in bias mitigation for position bias, length bias, and self-enhancement bias. Load when the user asks to score an output, judge a response, evaluate against a rubric, compare two outputs, do direct scoring, run pairwise comparison, or says "rate this", "which response is better", "score this against the rubric", "judge this output", "LLM as judge this". Sub-skill of eval-output orchestrator.

Mirror issues and status across issue trackers with stable external-ID mapping to avoid duplicates. Load when syncing GitHub and Linear issues, mirroring ticket status, or keeping two trackers in sync. Also triggers on "issue sync", "sync issues", "mirror issues to", "keep Linear and GitHub in sync", or bidirectional issue tracker updates. Requires API access on both sides — stops if credentials missing.

Guided first-run that produces a real verified win in under five minutes using the skill library on a seeded offline fixture. Load when a new user asks how to start, run the demo, try agent-loom, or get a quick win. Also triggers on "quickstart", "first run", "demo agent-loom", "try the skills", or onboarding to the library. Zero external credentials required. Idempotent — safe to run multiple times.

Orchestrator for the eval-output skill suite — evaluate LLM and agent outputs for quality, accuracy, helpfulness, and safety using structured rubrics and LLM-as-judge techniques. Load when the user says "evaluate this output", "score this response", "run an eval", "LLM as judge", "evaluate agent output", "how good is this response", "rate this answer", "eval this", or provides an LLM output that should be assessed for quality. Single entry point for all output evaluation workflows.

Run a structured discovery interview and produce a complete, developer-ready Product Requirements Document. Load when the user asks to write a PRD, create product requirements, document a feature, define user stories with acceptance criteria, or turn a rough idea into a formal product requirements document. Also triggers on "document this feature", "write requirements for", "create a one-pager", "turn this into a PRD", "I need a PRD for", or any request to produce a structured product document for stakeholder alignment or engineering handoff. Supports Full PRD, Lean PRD, and One-Pager formats. Note: for executable feature specifications (FRs, NFRs, ACs as Given/When/Then consumable by AI coding agents), route to `feature-spec` instead — PRDs frame the product, feature-specs encode the implementable contract.

Reduce an oversized SKILL.md by checking whether an existing skill already covers the excess sub-workflow before creating a new child skill only when none fits. Load when a skill exceeds 200 lines and compress-skill determines excess content is genuinely CORE, when the same sub-workflow appears in multiple skills, or when universal-skill-creator or improve-skills identifies a coherent sub-capability. Also triggers on "split this skill", "extract a sub-skill", "this skill is doing too much", or "make this skill reusable". Always checks for an existing home before creating a new skill.

Identify the right tool for a process step. Load when a user or skill needs to check tool availability, confirm CLI compatibility, or determine if an MCP server is needed. Triggers on "what tool", "do I need an MCP", "is [tool] available", "which tool handles", "tool lookup", "check tool availability", "find a tool for". Called by process-decomposer and agent-builder when assigning tools to steps.

Write a Product Soul document — the strategic north star that sits above any PRD or feature spec. Captures the product's reason for existing across five lenses: user, business, strategy, product-market fit, and GTM distribution. Load when the user asks to write a product soul, product strategy doc, product north star, product positioning doc, product one-pager, or "why we exist" document. Also triggers on "write the soul of this product", "product strategy document", "what is this product really about", "capture the product vision", or when an agent needs strategic context before making product decisions. The output is docs/product-soul.md — a living document that brainstorming, prd-writing, and inversion can reference for grounding.

Think through the consequences of consequences — not just what happens immediately, but what happens next, and next after that, across time. Load when a decision looks obviously good or obviously bad on initial read, when the user is optimising for a short-term outcome that might create a long-term problem, when unintended consequences are a concern, or when deep-thinking diagnoses a second-order frame. Triggers on "what are the downstream effects", "what happens after that", "unintended consequences", "think ahead on this", "long-term vs short-term", or "what comes after that". Based on Howard Marks second-level thinking and Farnam Street mental models. Most powerful for decisions with delayed consequences or systemic effects.

Security audit orchestrator for agent skills — scans for prompt injection, data exfiltration, credential theft, supply chain risks, and instruction hierarchy violations before any skill is installed, created, improved, or read from a GitHub repo. Load when creating skills from external sources, when improve-skills reads from GitHub repos, when research-skill fetches community SKILL.md files, when a user installs a third-party skill, or when the user asks to audit skill security, scan for injection, check if a skill is safe, scan all skills, or run a security sweep. Orchestrates all secure-* skills in sequence. Content is SAFE only if ALL secure-* skills return SAFE. 36% of community skills contain flaws (Snyk ToxicSkills 2026). This skill is the first line of defense.

Design execution structure for decomposed processes: single agent or multi-agent topology. Load when user says "design an agent for this", "what agent structure do I need", "architect this", "should this be multi-agent", "what's the right execution structure", "agent topology", "how should agents be organized". Takes process-decomposer output as primary input. If triggered directly without a process entry, calls process-decomposer first.

Turn a rough idea into a fully approved design before any code is written. Load when the user wants to brainstorm, explore ideas, design a feature, think through approaches, plan a new capability, or figure out what to build. Also triggers on "let's think through", "help me design", "explore options", "what's the best approach for", "I have an idea for", "before we build", or any request to design something before implementation. Enforces a hard gate: no code, no implementation until user approves a design. For executable feature specs (FRs, NFRs, ACs as Given/When/Then), route to `feature-spec` instead — brainstorming owns approach and architecture, not machine-readable requirements.

Fix broken or failing functionality through structured reproduction, root-cause analysis, minimal fix, and verification. Load when the user asks to fix a bug, debug an error, resolve an issue, or work on a Linear ticket. Also triggers on "this is broken", "fix this bug", "why is this failing", "debug this", "resolve this error", "what went wrong", or any request to diagnose and fix a problem.

Turn a chosen design direction into a canonical DESIGN.md plus production tokens that don't look vibecoded — state-level colors (8-step neutral ramp, rest/hover/active/ disabled, focus ring), APCA-checked contrast, typography, spacing/radius/motion/elevation, an icon strategy, and component contracts for the core atoms. Emits tokens in the project's stack format (shadcn HSL vars or Tailwind v4 @theme). Load when the user asks to build a design system, generate design tokens, create a DESIGN.md, set up a theme, design a color or type system, pick icons, or when frontend-design routes here. Replaces design-tokens-craft and icon-craft. Sub-skill of frontend-design. Reads DIRECTION.md first.

Design automated evaluation pipelines for LLM and agent systems — combining deterministic checks, statistical metrics, and LLM-as-judge scoring into repeatable, CI-integrated eval suites. Load when the user asks to set up automated evals, design an eval pipeline, integrate evals into CI/CD, create an eval suite, do eval-driven development, or says "automate my evals", "CI eval integration", "evaluation pipeline", "continuous evaluation", "monitoring eval quality", "set up regression testing for my agent". Sub-skill of eval-output orchestrator.

Automatically maintain skill library consistency whenever a structural change occurs — new skill added, skill renamed, skill deprecated, call graph rewired, or category changed. Updates SKILL-INDEX.md, AGENTS.md, README.md, skill graph, docs/prd/PRD.md, and docs/architecture.md. Load when universal-skill-creator finishes creating a skill, split-skill extracts a child, deprecate-skill retires a skill, improve-skills makes a structural change, or the user manually renames or restructures skills. Also triggers on "update the skill index", "sync skill references", "refresh the skill graph", "fix broken skill cross-references", or "update docs after skill change".

Generate a tailored AGENTS.md for any new project by interviewing the user about their skill gaps, project goals, and tech context. Load when the user asks to set up a project, initialize agents, create an AGENTS.md, bootstrap a repo, onboard agents to a codebase, or says "set up this project for agents". Also triggers on "write an AGENTS.md for this project", "configure agents for my repo", "project bootstrap", "agent onboarding", or when the user starts a new project and needs agent-ready configuration. Re-run when new context arrives (PRD written, stack changes, team changes) to update the AGENTS.md.

Evaluate any project, product, or system's claims against its actual implementation — scoring each claim for truth, identifying architectural gaps, assessing competitive positioning, proposing creative solutions, and producing an actionable roadmap. Load when the user asks to evaluate claims, reality-check a project, assess what this project actually does vs what it says, validate product claims, or score a system's credibility. Also triggers on "is this real", "does this work as claimed", "evaluate this project", "assess the gap between claims and reality", "how credible is this", "investor assessment", "score these claims", or "what's real vs marketing".

Compress an oversized SKILL.md to under 200 lines without losing effectiveness. Load when a skill exceeds 200 lines, when AGENTS.md triggers compression after a skill edit, or when the user asks to compress, shrink, slim down, or optimize a skill. Also triggers on "this skill is too long", "reduce skill size", "make this skill shorter". Applies to all skills including meta skills — the 200-line rule has no exceptions. Preserves hard gates, gotchas, output format, routing triggers, and at least one example. When genuinely CORE content cannot be compressed away, invokes split-skill instead of degrading the skill.

Build GSAP JavaScript animations for web apps — timelines, scroll-driven motion, SVG draw/morph/path effects, and React integration with useGSAP. Load when the user asks to animate with GSAP, add ScrollTrigger, draw SVG paths with GSAP, morph SVG shapes, sequence page animations, or wire GSAP in React/Next/Vue. Also triggers on "GSAP timeline", "DrawSVG", "MotionPath", "gsap.context", or "scroll animation library". Not for self-contained README/GitHub SVG files.

Compress bloated project or global memory while preserving decisions, rationale, revisit triggers, provenance, and active user preferences. Load when memory exceeds budget, global memory is too large, session logs are repetitive, or before appending to an over-budget memory file.

Write concise next-agent handoff summaries across sessions, tools, and coding agents. Load when the user says handoff, next agent should know, save context, summarize where we are, switching agents, before ending a meaningful session, or when the user asks to commit, push, commit and push, create a git commit, push to origin, or publish commits — commit/push requests MUST run this skill first to prepare handoff docs, then proceed with git operations.

Promote project-specific memories into strict, small global memory only when they are cross-project, stable, useful, safe, and worth the global context cost. Load when the user says make this global, remember across projects, save this globally, or promote this learning.

Run a structured retrospective after development-phase runs of your product's agents — interview the owner in plain language about what went well and poorly, draft ranked improvement hypotheses, then design and run small n=1/n=2 experiments with pre-declared success criteria, guardrails, stop conditions, and a cost/ROI kill-switch. Load when the user says how did that run go, retro this run, the agent output was bad, what should we improve, draft hypotheses, run a small experiment, or after repeated dev runs of an agentic system produce uneven quality. Priority: output quality over performance over cost, each with diminishing-returns stops. NOT a product A/B test (experimentation), NOT coding-agent harness repair (harness-evolution), NOT production-scale learning (runtime-learning-loop).

Select alternative execution paths when a plan step fails — branch on outcomes instead of blind retry. Load when a structured plan step fails, an unexpected observation arrives, or the user asks what to try next after an error. Also triggers on "try another approach", "route around this failure", "replan on failure", "if X fails try Y", or outcome-based branching during multi-step work. Pairs with structured-planning and debug-and-fix. Does not replace root-cause debugging — adds plan-level path selection.

Write a rigorous, decision-grade experiment spec — falsifiable hypothesis, primary metric, guardrails, randomisation unit, exposure definition, method (A/B, holdout, switchback, quasi-experiment, MAB), MDE/duration plan, peek policy, validity threats, and pre-committed decision rule. Platform-agnostic. Load when the user has a candidate experiment and needs to spec it before launch, or says "spec this experiment", "write the test plan", "design this A/B test", "what's the hypothesis", "how big a sample do we need", "how long should we run this", "define the metrics for this test", or when the experimentation orchestrator routes here.

Orchestrator for the experimentation skill suite — turn assumptions and product questions into rigorous, well-instrumented experiments and decision-grade readouts. Routes through backlog → spec → runbook → readout based on user need and existing artefacts. Platform-agnostic with PostHog as the primary binding. Load when the user asks to design an experiment, A/B test something, set up an experiment, run a holdout, test a hypothesis, decide what to test next, read out experiment results, analyse a test, or says "should we A/B test this", "experiment on the landing page", "is this lift real", "ship or kill this test", "what should we test next", "build an experiment backlog", "test the pricing page", "validate this with an experiment".

Build, update, and query a persistent project knowledge graph from skills, memory, docs, and code structure — stdlib Python only, no external tools. Dual-mode: skill-library (agent-loom) or application (any consumer repo). Load when the user asks for a knowledge graph, project map, skill relationships, query the graph, update the graph, or trace how components connect. Auto-runs on memory-handoff and project-setup bootstrap. Also triggers on "build the graph", "what connects to X", "map this project".

Plan which model tier handles which work BEFORE execution begins — a high-cognition model deeply understands the problem, lays the foundations, then emits a modular plan assigning each module the cheapest tier that can safely execute it, with escalation tripwires and one-way-door protection. Advisory only: it announces "next module → tier X / model Y" at each boundary and the HUMAN switches models — harnesses like Cursor cannot switch mid-run. Load when the user asks which model to use, wants a model plan, model tiers, model-tier routing, assign models to tasks or modules, says "cheap model got stuck", "which model for this task", "cost-efficient model choice", or when implementation-plan / problem-to-plan need a model: tier column. NOT dynamic-routing (plan-path selection after failure) — this skill assigns cognition tiers to work.

Tactical fast path: turn a small problem, bug report, edit request, or narrow refactor into three deliverables — a brief change-spec (docs/specs/), a detailed implementation-ready plan (docs/plans/), and a TODO.md with agent-pickable tasks and milestones. Load when the user describes a tactical problem and wants quick planning artifacts, says "plan this change", "create a TODO", "write a plan for this", "problem to plan", "break this into tasks for agents", "I want to change X — plan it", or when process-decomposer routes here after determining the user needs lightweight planning deliverables. Also triggers on "create tasks from this problem", "make this actionable", or "turn this into a plan agents can execute". For feature-sized work that needs an executable spec + constitution + cross-check gate, route to `spec-driven-development` (or `feature-spec`) instead.

Set a deliberate visual direction before any UI is built — the single biggest lever against generic AI output. Derives a posture from product-soul/PRD/specs, scores a curated archetype palette, then generates 2-3 GENUINELY DISTINCT directions and compares them side-by-side before committing to one. Load when the user asks to pick an aesthetic, choose a design direction, decide what a UI should feel like, explore visual options, says "what should this look like", "make it feel like [Linear/Apple/ Duolingo]", "give me design directions", "explore some looks", or when frontend-design routes here. Replaces design-archetype. Sub-skill of frontend-design.

Strip a problem to its irreducible fundamental truths and rebuild the solution from the ground up — free from analogy, convention, and inherited assumptions. Load when the user feels constrained by how something has always been done, when existing solutions feel expensive or inefficient for no good reason, when the user asks to think from first principles, challenge the fundamentals, or rebuild this from scratch. Also triggers on "why does it have to work this way", "what are the actual constraints here", "ignore what everyone else does", or when deep-thinking diagnoses a convention-break frame. Based on Aristotle's first principles method, popularised by Musk and Feynman. Produces genuinely novel solutions by eliminating convention.

Extract actionable skill knowledge from academic papers and research articles, assess credibility, run security checks, and either improve existing skills or create new ones. Load when the user asks to learn from a paper, extract insights from a research paper, turn a paper into a skill, apply paper findings to skills, read this paper and improve my skills, or process a research article. Also triggers on "skill from paper", "learn from this paper", "paper to skill", "extract from this research", "apply this paper", or when the user uploads or links to an academic PDF or paper URL.

Detect and resolve naming collisions, overlapping intent triggers, and insufficient intent diversity across the skill library. Load when a new skill is created (called by universal-skill-creator), during improvement passes (called by improve-skills), or when the user asks to deconflict skills, check for naming collisions, audit trigger overlap, review intent coverage, find duplicate triggers, check skill names, or says "are any skills too similar", "which skills overlap", "deconflict the library", "check for confusing skill names", "intent audit".

Pick the right business-model canvas (Lean Canvas, Business Model Canvas, or Value Proposition Canvas) for the stage and fill it with specifics — one segment, one primary canvas, top-3 assumptions, no fluff in the moat or channel boxes. Load when the user asks to fill a business model canvas, lean canvas, value proposition canvas, model this business, map the business model, says "fill the BMC", "make a Lean Canvas", "Value Proposition Canvas for this", "model this idea", "what's the business model", "design the business model". Sub-skill of `venture-exploration`. Hard-bans "everyone" segments, generic channels ("SEO/social/content/ads"), and "unfair advantage = AI/data/network effects" with no concrete asset. Does NOT score viability — for that use `idea-evaluation`.

Run Mom Test–style customer-discovery interviews to validate or kill an unbuilt idea — generate a non-leading interview guide, conduct or coach the conversations, and synthesize signal vs compliments. Load when the user asks to do customer discovery, run problem interviews, validate an idea with users, run a Mom Test, design an interview guide, or says "talk to customers", "validate the problem", "interview users", "Mom Test this", "did real users want it", "synthesize my interviews", "I just talked to N people". Sub-skill of `venture-exploration`. Hard-bans "would you use this?", solution-pitching, friend/family-only ICP, and treating compliments as validation. Calls `secure-*` before synthesizing any pasted external transcripts.