"Use this agent when you need to discover, collect, and validate data from multiple sources to fuel analysis and decision-making. Invoke this agent for identifying data sources, gathering raw datasets, performing quality checks, and preparing data for downstream analysis or modeling.".

"Use this agent when distributed system errors occur and need coordinated handling across multiple components, or when you need to implement comprehensive error recovery strategies with automated failure detection and cascade prevention.".

"Use when building payment systems, financial integrations, or compliance-heavy financial applications that require secure transaction processing, regulatory adherence, and high transaction accuracy.".

"Use when coordinating multiple concurrent agents that need to communicate, share state, synchronize work, and handle distributed failures across a system.".

"Use when building production NLP systems, implementing text processing pipelines, developing language models, or solving domain-specific NLP tasks like named entity recognition, sentiment analysis, or machine translation.".

"Use when designing RL environments, training agents with reward optimization, implementing policy gradient methods, or deploying decision-making systems for robotics, gaming, and autonomous operations.".

"Use when you need to search scientific literature and retrieve structured experimental data from published studies. Invoke this agent when the task requires evidence-grounded answers from full-text research papers, including methods, results, sample sizes, and quality scores.".

"Use when distributing tasks across multiple agents or workers, managing queues, and balancing workloads to maximize throughput while respecting priorities and deadlines.".

Design agent tools and CLI surfaces—schemas, naming, errors, idempotency, and discoverability for LLM callers. Use when defining tools for agents, SDKs, or AI-native CLIs.

Prepare iOS App Store and Google Play submissions—metadata, assets, compliance checks, and release checklist. Use before store upload or review submission.

Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes. Separate from /benchmark, which measures web page performance. Use when: "benchmark models", "compare models", "which model is best for X", "cross-model comparison", "model shootout". (gstack) Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".

Design lightweight CI quality gates—lint, test tiers, security scans, and merge policies. Use when setting up or improving pipelines without tying to one stack only.

Ask the minimum clarifying questions before implementing when scope, constraints, or success criteria are unclear. Use when a request has multiple plausible interpretations, missing acceptance criteria, or ambiguous environment constraints. Triggers: "unclear", "ambiguous", "not sure what you want", "multiple options".

Use when you need to analyze direct and indirect competitors, benchmark against market leaders, or develop strategies to strengthen competitive positioning and market advantage.

Patterns for centralized error capture, user-appropriate messaging, and observability across web and mobile clients.

Chọn đúng biểu đồ, kể chuyện với số liệu, và tránh误导 — dựa trên nguyên tắc từ Kieran Healy (Data Visualization, Princeton 2019) và taxonomy từ AntV chart-visualization-skills. Dùng khi cần quyết định loại chart, trình bày insight cho stakeholder, hoặc kiểm tra xem figure có gây hiểu lầm không. Để vẽ Python thực tế, chuyển sang matplotlib / seaborn / scientific-visualization.