deep-research-prompt-builder
This skill should be used when the user asks to "build a research prompt", "create a deep research query", "enhance my research question", "structure a research prompt", "help me write a research prompt", or needs help transforming research topics into comprehensive prompts for product comparisons, technical documentation, academic literature, market analysis, or any domain requiring structured deep research.
What this skill does
# Deep Research Prompt Builder Expert system for constructing high-quality research prompts through adaptive interviewing and best-practice application. ## Core Workflow ### 1. Categorize Research Topic When user provides a topic, immediately categorize it: - **Product/Service**: Shopping comparisons, reviews, buying guides - **Technical**: Code patterns, architecture, implementation details - **Academic**: Literature reviews, theoretical analysis, scientific research - **Business**: Market analysis, competitive intelligence, trends - **General**: Historical, cultural, educational topics ### 2. Conduct Adaptive Interview Ask questions ONE AT A TIME. Wait for the response before proceeding. **Generate questions that directly probe the specific research topic.** Use the category examples below as inspiration, not scripts. Each question should surface something the user has not yet specified about the actual topic. #### Using AskUserQuestion (Optional Enhancement) If the `AskUserQuestion` tool is available, use it to provide a more structured interview experience with clear options. This enhances usability but is not required - fall back to conversational questions if the tool is unavailable. **When to use AskUserQuestion:** - Category-specific questions where there are clear, distinct options - Priority ordering questions (when requirements might conflict) - Confirmation questions before generating the final prompt - Clarifying ambiguous terminology with specific interpretations **When to use conversational questions:** - Open-ended exploration questions - Questions that need nuanced, free-form responses - Follow-up questions that depend on complex context - When the user's answer suggests they need to explain more #### Clarification Triggers Before proceeding with interview questions, clarify when: - The user uses ambiguous or unusual terminology (use AskUserQuestion with specific interpretation options if available) - Scope is mentioned but intent is unclear (what specifically matters about it?) - The user gives compound answers - confirm priority ordering (use AskUserQuestion with ordered options if available) - Technical terms may have multiple meanings in context #### Opening Question (All Categories) "What specific aspect of [TOPIC] are you most interested in exploring?" #### Category-Specific Question Examples Use these as **inspiration only** - adapt questions to the actual topic at hand: **Product/Service examples:** - Research goal: current best options, specific comparisons, or understanding what makes something good? - Key criteria and their priority order - Preferred output format *Example with AskUserQuestion (if available):* - Question: "What's your primary goal for this product research?" - Options: "Find the best option to buy now", "Compare specific products I'm considering", "Understand evaluation criteria", "General market overview" - Question: "Which criteria matter most for your decision?" - Options: "Price and value", "Features and capabilities", "Reliability and reviews", "Long-term costs" - multiSelect: true **Technical examples:** - Context: learning, implementing, or making architectural decisions? - Critical aspects: performance, best practices, pitfalls, examples? - Depth needed: overview, implementation guide, or deep analysis? *Example with AskUserQuestion (if available):* - Question: "What's your context for researching this technical topic?" - Options: "Learning the fundamentals", "Implementing in a project", "Making architectural decisions", "Troubleshooting issues" - Question: "Which aspects are most critical?" - Options: "Performance characteristics", "Best practices and patterns", "Common pitfalls to avoid", "Practical examples" - multiSelect: true - Question: "What depth of coverage do you need?" - Options: "High-level overview", "Implementation-focused guide", "Deep technical analysis", "Comprehensive reference" **Academic examples:** - Purpose: literature review, hypothesis exploration, or current knowledge state? - Time scope preferences - Evidence standards: peer-reviewed only or broader sources? *Example with AskUserQuestion (if available):* - Question: "What's the purpose of this academic research?" - Options: "Comprehensive literature review", "Exploring a specific hypothesis", "Understanding current state of knowledge", "Identifying research gaps" - Question: "What evidence standards should be applied?" - Options: "Peer-reviewed only", "Include preprints and working papers", "Include reputable non-academic sources", "Broad sources for comprehensive view" **Business examples:** - Focus: market landscape, competitor analysis, or trends? - Most valuable data types - Scope boundaries **General examples:** - What's driving this research? - Perspective: comprehensive, specific angle, or comparative? - Key debates or controversies to address? #### Closing Question (All) "Any specific angle or outcome you haven't mentioned that should shape this research?" ### 3. Build Enhanced Prompt #### Prompt Construction Principles - **Include only what was discussed or directly implied** - Do NOT add "enhancements" the user didn't ask about - If uncertain whether to include something, leave it out - Scope mentions (geographic, temporal, etc.) should reflect user's stated intent, not assumed interests - No speculative expansions beyond what user requested Use this template structure: ``` # Research Objective [Clear statement synthesized from topic and clarifications] # Context and Scope - Purpose: [Why this research matters] - Boundaries: [Time, geography, domain limits] - Focus Areas: [3-5 specific aspects to emphasize] # Research Requirements ## Investigation Depth Primary questions: 1. [Main research question] 2. [Key sub-question 1] 3. [Key sub-question 2] Secondary considerations: - [Related area if relevant] - [Adjacent topic to explore] Explicitly exclude: [What NOT to research] ## Evidence Standards - Source types: [Academic, industry, user-generated, etc.] - Recency: [How current sources must be] - Credibility: [Minimum authority level] - Citations: [How to reference sources] ## Analysis Framework [INSERT CATEGORY-SPECIFIC FRAMEWORK - see below] ## Output Structure ### Required Sections: 1. Executive Summary (3-5 key findings) 2. Detailed Analysis by Subtopic 3. Supporting Evidence with Citations 4. Practical Implications 5. Confidence Levels and Limitations 6. Further Research Needed ### Format Requirements: - Hierarchical headings for navigation - Data visualization descriptions where helpful - Balance depth with readability - Include both synthesis and details # Quality Instructions ## Reasoning Approach - Think step-by-step through each research aspect - Build from foundational understanding to nuances - Explicitly address source contradictions - Validate through multiple independent sources ## Critical Evaluation - Cross-reference all major claims - Distinguish facts from interpretations - Note confidence levels for findings - Acknowledge information gaps [Additional topic-specific instructions from interview] ``` ## Category-Specific Frameworks Insert appropriate framework based on category: ### Product Framework ``` ## Analysis Framework - Feature comparison matrix across top options - Price-performance analysis - Real user experience synthesis - Expert review aggregation - Long-term value assessment - Common issues and solutions ``` ### Technical Framework ``` ## Analysis Framework - Implementation complexity assessment - Performance and scalability analysis - Code examples and patterns - Best practices vs anti-patterns - Tool ecosystem and dependencies - Migration and maintenance considerations ``` ### Academic Framework ``` ## Analysis Framework - Theoretical foundations and evolution - Methodological approaches comparison - Key findings synthesis across studies - Debates and controversies mapping - Research gaps identification
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.