Skills Catalog

Evidence-first pull request judge that reviews a PR and posts one consolidated GitHub review with inline comments via the gh CLI. Runs the repo's own deterministic checks first, researches current official docs before any claim about external libraries or APIs, then reviews correctness, security, structural quality (code judo, spaghetti growth, file-size limits), and AI slop including useless code comments. Every finding must carry evidence, every comment passes a deterministic noise gate before posting, and the verdict (APPROVE, COMMENT, REQUEST_CHANGES) is weighed by findings. Use when asked to review a PR, judge this PR, review this branch or diff before merge, run the-judge, "revise esse PR", "faca o code review", or "julgue esse PR". Do NOT use for reviewing prose or documents, fixing CI failures, resolving merge conflicts, writing the fix itself, or responding to review comments (use gh-address-comments).

When the user wants to build video-first cold outreach, create personalized video at scale, implement async selling, or use AI demo generation for prospecting. Also use when the user mentions 'video outreach,' 'personalized video,' 'video prospecting,' 'Tavus,' 'Sendspark,' 'HeyGen,' 'video email,' 'async selling,' 'video demo,' or 'made this for you.' This skill covers video-first outreach systems from personalization through conversion optimization. Do NOT use for technical implementation, code review, or software architecture.

Creates Architecture Decision Records (ADRs) to document significant architectural choices and their rationale for future team members. Use when the user says "write an ADR", "document this decision", "record why we chose X", "add an architecture decision record", "create an ADR for", or wants to capture the reasoning behind a technical choice so the team understands it later. Do NOT use when the decision hasn't been made yet (use create-rfc instead), for implementation planning (use technical-design-doc-creator), or for general documentation.

Creates structured Request for Comments (RFC) documents for proposing and deciding on significant changes. Use when the user says "write an RFC", "create a proposal", "I need to propose a change", "draft an RFC", "document a decision", or needs stakeholder alignment before making a major technical or process decision. Do NOT use for TDDs/implementation docs (use technical-design-doc-creator instead), README files, or general documentation.

When the user wants to define their ideal customer profile, position an AI product, build messaging architecture, or validate product-market fit. Also use when the user mentions 'ICP,' 'ideal customer profile,' 'positioning,' 'PMF,' 'product-market fit,' 'messaging,' 'buyer persona,' 'enrichment signals,' 'market positioning,' or 'competitive positioning.' This skill covers market positioning, ICP definition, messaging architecture, and PMF validation for AI-native products. Do NOT use for technical implementation, code review, or software architecture.

When the user is a solo founder building their GTM motion, wants to scale without hiring, or needs to design an AI agent team for go-to-market. Also use when the user mentions 'solo founder,' 'one-person startup,' 'solopreneur,' 'bootstrapped,' 'no team,' 'AI agents as team,' 'scaling without hiring,' 'founder-led sales,' 'lean GTM,' 'one-person company,' or 'no employees.' This skill covers the complete solo founder GTM playbook from stack selection through agent team design, revenue-stage transitions, time allocation, and when to finally hire. Do NOT use for technical implementation, code review, or software architecture.

Opinionated Rails conventions: rich models, concerns, CRUD-everything, state-as-records, minimal dependencies, Minitest with fixtures. Load this skill BEFORE any code-level thinking, not only before editing a file. It is required the moment a task touches Rails code in ANY way: designing or even just discussing a data model, schema, migration, entity, association, field, validation, class, or method name; writing, planning, reviewing, analyzing, testing, debugging, or refactoring; or proposing any model, table, column, route, or code snippet inline in chat. If you are about to name a model or sketch a column you are already in scope, even in an exploratory back-and-forth where no file is written yet. Do not let a "we're just discussing" framing defer it. Do NOT use for non-Rails backends, NestJS, or general architecture (use nestjs-modular-monolith or coding-guidelines).

When the user wants to choose between PLG and sales-led, design a sales motion, optimize time-to-first-value, or build a value-before-purchase experience. Also use when the user mentions 'PLG,' 'product-led growth,' 'sales-led,' 'sales motion,' 'free trial,' 'freemium,' 'self-serve,' 'demo-first,' 'time-to-first-value,' 'TTFV,' or 'agent-led sales.' This skill covers sales motion selection, value delivery design, and go-to-market motion architecture. Do NOT use for technical implementation, code review, or software architecture.

Use when a question, decision, plan, tradeoff, or claim needs a rigorous verdict and one perspective is not enough. Spawns a panel of 3 to 5 subagent jurors that form independent blind opinions, deliberate anonymously under an anti-anchoring and anti-sycophancy protocol, and return one committed verdict with confidence, preserved dissent, and a concrete next action. Domain-agnostic across engineering, architecture, data, product, hiring, strategy, vendor choice, build-vs-buy, and research design. Trigger phrases include "convene a jury", "have agents debate and decide", "get a panel to decide", "multi-agent decision", "stress-test this and decide", "monte um juri", "tribunal de agentes", "painel para decidir". Do NOT use to only critique without deciding (use the-fool for that), to build a plan or write the solution itself, or for simple factual lookups.

Evaluate a repo agent harness (AGENTS.md, rules, skills, skill refs) for broken paths/commands, redundant instructions, and usefulness using a stack-agnostic dual-judge protocol with planted traps. HIGH PRIORITY questionnaires at top: Q1 optional docs, Q2 B/C budget before Track A (certainty/tokens). A always runs after Q2; B/C opt-in. ADRs/RFCs excluded from T2. Mixed apply uses 11-mixed-apply.md (KEEP/CUT). Use when the user says harness eval, harness-eval, harness debug, audit AGENTS.md, audit skills/rules, instruction audit, redundancy of agent instructions, usefulness of skills, Ship/Review/Hold/Slim/Keep-core for harness, or wants Track A/B/C harness evaluation. Do NOT use for harness setup or init, feature spec-driven work (tlc-spec-driven), or applying Ship/Slim trims unless the user explicitly asks after the report.

Detects anemic domain models, validates and refactors them into rich domain models, and enforces tactical DDD patterns (Entities, Value Objects, Aggregates, Domain Services, Domain Events). Use when the user asks to validate, review, or check domain models or DDD code; detect anemia; refactor domain objects; improve encapsulation; or mentions terms like "anemic model", "rich domain", "aggregate", "value object", "domain event", "ubiquitous language", "is this good DDD", "does this follow DDD", or "check my domain". Do NOT use for module or service boundary design, architectural decomposition, strategic DDD context mapping, or code outside the domain layer (DTOs, controllers, infrastructure adapters).

Scores how completely an implementation fulfills a PRD/spec, case by case, and produces a single comparable final grade. Invoke only when explicitly named (e.g. run spec-driven-eval); do not auto-trigger. Use when benchmarking spec-driven implementations, grading acceptance criteria, evaluating whether a feature was 100% implemented, comparing multiple implementations of the same PRD, or auditing implementation and test coverage (unit and e2e) against product requirements. Do NOT use for planning or building features (use tlc-spec-driven), writing PRDs, or general code review unrelated to a spec.

Autonomous senior-operator mode for AI agents that resolve tasks end to end without babysitting and never create new problems. The agent verifies every claim against real evidence (web search dated to the current month and year, the codebase, and available tools, MCPs, and CLIs); it never guesses, never fakes confidence, and never claims something is done without proof. It stays silent and keeps working, interrupting the user only on three stops, namely a destructive or irreversible action, a dead-end with no evidence after exhausting sources, or genuine ambiguity that changes the outcome. Output is short, literal, and human. Use when the user says "not-your-babysitter", "nanny mode", "work autonomously", "stop babysitting", or "no hand-holding", or wants an agent that solves problems on its own, especially hands-on engineering and operational tasks. Do not use when the user explicitly wants a tutorial, a verbose walkthrough, or open-ended brainstorming.

Expert in Confluence operations using Atlassian MCP. Use when the user says "search Confluence", "create a Confluence page", "update a page", "find documentation in Confluence", "list spaces", or "add a comment to a page". Do NOT use for Jira issues, general web search, or local file creation.

Runs a sequenced monolith-to-modular pipeline that sizes and inventories components, finds shared domain duplication, addresses flattening and hierarchy issues, analyzes coupling, then groups components into candidate domain-aligned units, with optional embedded DDD strategic analysis for bounded contexts. Use when asking how to split a monolith, size components before extraction, find duplicated domain logic, clean up module hierarchy, measure coupling between modules, or group components into services. Do NOT use for phased extraction roadmaps or prioritization without the prior analysis steps (use decomposition-planning-roadmap after this pipeline), end-to-end legacy migration strategy writeups (use legacy-migration-planner), pure infrastructure capacity sizing, or when you only need DDD without the structural pipeline (install domain-analysis standalone).

Generative Engine Optimization (GEO) specialist — the technical, on-page publishing work that makes a given page or site discoverable, understandable, trustworthy, quotable, and fresh for AI answer engines (Google AI Overviews, ChatGPT Search, Bing Copilot, Perplexity). Use when asked to 'optimize this page/site for GEO', 'optimize for AI search / answer engines', 'get my page cited by ChatGPT/Perplexity', 'improve AI visibility/citability', 'write an llms.txt', 'add citation-ready structure or schema for AI answers', 'otimizar para busca com IA', or to audit/create/improve a codebase for generative search. Do NOT use for AI-driven SEO content strategy or programmatic pages at scale (use ai-seo), classic keyword/SERP ranking (use seo), accessibility (use web-accessibility), or multi-area site audits (use web-quality-audit).

Guides design and implementation of evolutionary modular-monolith platforms with DDD (strategic + tactical), flat-by-aggregate organization, an Anti-Corruption Layer for vendor independence, a transactional outbox for events, smart resilience (backoff with jitter, circuit breakers, idempotency), and a polished architecture HTML document with elegant SVG diagrams. Use when designing a platform or backend, defining bounded contexts, organizing modules and folders, choosing monolith vs microservices, decoupling from an external service (ERP, storage, AI), making calls resilient, adding real-time push, picking a 2026 TypeScript stack (Nx, NestJS, React), or producing an architecture document or diagram. Also triggers on 'modular monolith', 'bounded contexts', 'flat-by-aggregate', 'ports and adapters', 'architecture diagram'. Do NOT use for simple CRUD, NestJS-only deep implementation (use nestjs-modular-monolith), or pure domain-model review (use tactical-ddd).