Research

Produce externally credible evidence that Prompt-Driven Development (PDD) delivers measurable advantages beyond standalone agentic CLIs (for example, Claude Code or Codex used in direct patch mode).

Azure resource troubleshooting patterns including KQL templates, metric thresholds, health checks, and remediation playbooks. Use when diagnosing unhealthy Azure resources or building diagnostic workflows.

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.

Force honest confidence assessment before claiming conclusions. Triggers on 'root cause identified', 'problem identified', 'complete clarity'. Express confidence as percentage, explain what's stopping 100%, validate assumptions before presenting.

Research competitor YouTube channels, niches, and trending topics for your content strategy. Use this skill whenever the user says "research channels", "analyze competitors", "find trending topics", "niche analysis", "competitive research", "what are other creators doing", "scrape YouTube channels", or wants to understand the competitive landscape for a specific tool or topic area.

Scientific delegation framework for orchestrators — provide observations and success criteria while preserving agent autonomy. Use when assigning work to sub-agents, before invoking the Task tool, or when preparing delegation prompts for specialist agents.

Using `__free()` with a cleanup function that cannot handle all values the variable may hold causes crashes or undefined behavior. If an allocator returns `ERR_PTR` on failure but the cleanup wrapper only checks `if (_T)`, the `ERR_PTR` value is truthy and the cleanup function receives a bogus pointer, causing a kernel crash.

**Prompt:**

This phase establishes the baseline understanding of the database schema. You will analyze exported schema files to identify the structure, data types, and potential issues that will inform later optimization phases.

Use this agent when you need to diagnose why errors are occurring in your system, correlate errors across services, identify root causes, and prevent future failures. Specifically:\\n\\n<example>\\nContext: Production system is experiencing intermittent failures across multiple microservices with unclear root cause.\\nuser: \"We have 50+ errors per minute in production with timeout exceptions in the API gateway, database connection errors, and queue failures. The incidents started after a dep...

Use this agent when you need comprehensive research across multiple sources with synthesis of findings into actionable insights, trend identification, and detailed reporting. Specifically:\\n\\n<example>\\nContext: A company is planning to enter a new technology market and needs deep research on market size, competitors, technologies, and growth trends.\\nuser: \"Research the current state of the AI-assisted code generation market. We need to understand market size, key competitors, technolog...

**Status**: Accepted **Date**: 2024-12-27

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. Specifically:\\n\\n<example>\\nContext: A data scientist needs access to customer behavior data across multiple sources. The data scientist asked you to find and compile raw customer interaction logs, transaction ...

Synthesize discovery findings into a consolidated analysis document with proposed tickets

Use when ideating solution concepts tied to top opportunities.

Quick reference for using the `scientific_report.sty` style package.

Define explicit procedure when a task fails irrecoverably. How to undo artifact changes? How to restore artifact plane to consistent state after failure?

Goal: produce an actionable referee report (`output/REVIEW.md`) that is traceable to the submitted paper’s claims and evidence (no free-floating advice, no invented comparisons).

COG (Claude-Obsidian-Git) is a self-evolving second brain pattern that combines: - **Claude Code** for AI-powered organization - **Obsidian** for knowledge storage and linking - **Git** for version control and automation triggers

An Obsidian vault is a codebase of markdown files. Claude Code navigates file structures and makes surgical edits natively.

Agent for link validation, broken link detection, URL enrichment, and res...

Show current task plan status and phase summary

> Comprehensive research findings on AI and creativity, covering new papers, techniques, limitations, best practices, and tools. ---

> Research conducted: 2026-01-29 ---