Confidence calibration contra labeled set y stratified sampling por document_type; accuracy desglosada, nunca agregada.

Seleccion de built-in tools con estrategia Grep then Read then Edit, failure modes y sin Read masivo upfront.

Investigacion adaptativa: mapeo barato, budget de exploracion acotado y re-plan disciplinado solo al invalidar la hipotesis.

System integration patterns — point-to-point, ESB, iPaaS, event mesh, API contract management, data mapping. Use when the user asks to 'design integrations', 'map system connections', 'define API contracts', 'plan event-driven integration', or mentions ESB, iPaaS, MuleSoft, API gateway, event mesh, data mapping. [EXPLICIT]

Pre-processing layer that analyzes raw user input — detecting surface errors, performing root-cause analysis (5 Whys), impact tracing (7 So-Whats), and intent gap analysis — then reformulates into a precise, actionable prompt.

Infrastructure and platform architecture — compute, network, storage, HA/DR, IAM, cloud landing zones, and cost optimization. Use when the user asks to 'design cloud infrastructure', 'plan network topology', 'define HA/DR strategy', 'set up cloud landing zones', 'optimize cloud costs', or mentions VPC, Kubernetes, serverless, multi-AZ, IAM, reserved instances, or chaos testing. [EXPLICIT]

Deploy and operate on Hostinger: shared and VPS hosting, Git/SFTP/PM2 deployment, MySQL/MariaDB, auto-renewing SSL, DNS and email via hPanel. [EXPLICIT] One of the three target platforms (Firebase + Vercel + Hostinger). Trigger: 'hostinger', 'shared hosting', 'hpanel', 'vps deploy', 'pm2', 'mariadb'.

Design current Claude Code hooks with nested matcher-entry schema, five handler types, matcher/if boundaries, permissions-aware policy, portable scripts, MCP timing checks, and deterministic validation.

This skill should be used when the user asks to create a skill from scratch, optimize an existing skill, run skill evals, or benchmark skill performance — routing to the skill-creator plugin under toolkit governance.

This skill should be used when the user asks to review a PR or diff for code quality, comments, tests, error handling, type design, or simplification — routing to pr-review-toolkit's specialized agents under toolkit governance.

This skill should be used when the user asks to scaffold a Claude Code plugin, design plugin structure, develop a command/agent/hook/MCP/skill, validate a plugin, or review a skill — routing to the plugin-dev plugin under toolkit governance.

This skill should be used when the user asks to commit, push and open a PR, or clean gone git branches — routing to the commit-commands plugin under toolkit governance.

This skill should be used when the user asks to audit, improve, or update CLAUDE.md files with session learnings — routing to the claude-md-management plugin under toolkit governance.

This skill should be used when the user asks to scaffold or verify a Claude Agent SDK app in Python or TypeScript — routing to the agent-sdk-dev plugin under toolkit governance.

This skill should be used when the user asks to automate Claude Code headlessly, run claude -p in CI or scripts, parse json or stream-json output, use --bare, configure non-interactive permissions, compare CLI vs TypeScript or Python Agent SDK usage, wire MCP or hooks for automation, resume sessions programmatically, or harden reproducible Claude Code automation.

This skill should be used when the user asks to operate Claude Code /goal, write a goal completion condition, compare /goal with /loop, Stop hooks, or auto mode, diagnose a stuck goal loop, set stop conditions, resume or clear an active goal, or define safe continuation gates for autonomous Claude Code sessions.

Generative AI architecture — RAG patterns, LLM orchestration, multi-model tiering, agent workflow design, vector database architecture, knowledge connectors, and GenAI quality assurance. This skill should be used when the user asks to 'design RAG architecture', 'architect LLM system', 'select vector database', 'design AI agents', 'implement knowledge retrieval', 'plan GenAI quality', or mentions RAG, embeddings, vector search, LLM orchestration, agent framework, context-aware generation, hallucination reduction, or multi-model routing. [EXPLICIT]

Functional specifications. MVP modules, 8+ use cases, business rules, acceptance criteria. Data models (relational/NoSQL). [EXPLICIT]

Build on Firebase: Auth, Cloud Functions, Firestore security rules and query optimization, Hosting, Storage, scheduled jobs, emulator suite, and cost control. [EXPLICIT] One of the three target platforms (Firebase + Vercel + Hostinger). Trigger: 'firebase', 'firestore', 'cloud functions', 'firebase auth', 'firebase hosting', 'security rules'.

Cloud financial operations assessment and strategy using FinOps Foundation framework. Use when the user asks to 'assess cloud costs', 'optimize cloud spending', 'FinOps assessment', 'cloud cost analysis', 'rightsizing', 'reservation strategy', 'showback/chargeback model', 'cloud unit economics', 'cost allocation', or mentions 'cloud financial management', 'cost optimization', 'FinOps maturity'. [EXPLICIT]