deep-dive — Claude Code command: research a topic with sources
deep-dive — a slash command that investigates a topic from several angles and writes a structured report into artifacts/research/ inside your project.
MIT ★ 1,988 updated 2026-04-01
/plugin marketplace add glittercowboy/taches-cc-resources
/plugin install taches-cc-resources@taches-cc-resourcesWhat deep-dive does
Give it a topic, or drop the argument and it picks up whatever you are working on. Before any research begins, the command asks two to four questions through AskUserQuestion: what you need to understand, how deep, which angle matters. A second prompt then offers three paths: start, ask more, or add context yourself.
The report follows one layout every time: summary, key questions, overview, mechanics, history, patterns, limitations and edge cases, current state, takeaways, open questions. A claude_context block at the end lists when to use the thing and when to avoid it, plus libraries, patterns, conflicts and alternatives. The result lands in artifacts/research/ as YYYY-MM-DD-[topic]-deep-dive.md and the command prints that path back.
The file goes into the working directory you ran it from. Because of the intake gate, this is not a one-line lookup tool: nothing gets researched until you answer.
What it helps with
- understand how an unfamiliar tool actually works before adopting it
- trace why a technology exists and what it replaced
- list failure modes and edge cases up front
- keep a dated research file with sources inside the repo
- feed a decision with structured notes before
/plan/project
Example prompts for the agent
/deep-diveKubernetes networking: I need the mechanics and the usual mistakes- Run
/deep-divewith no argument and investigate what we are working on right now /deep-diveCompare Postgres and SQLite for a small CLI tool
How to install deep-dive
1Plugin marketplace
/plugin marketplace add glittercowboy/taches-cc-resources/plugin install taches-cc-resources@taches-cc-resources2Manually: put the files in place
.claude/commands/deep-dive.mdCall it with /deep-dive. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/deep-dive.mdCall it with /prompts:deep-dive. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/deep-dive.prompt.mdManually: put the files in place
.gemini/commands/deep-dive.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about deep-dive
How do I install deep-dive in Claude Code?
Add the marketplace: /plugin marketplace add glittercowboy/taches-cc-resources, then install the plugin: /plugin install taches-cc-resources@taches-cc-resources. The command file itself is .claude/commands/deep-dive.md.
What does deep-dive do?
It runs an investigation on the topic you name and puts the result in a single file: mechanics, history, patterns, limitations, takeaways. At the end it points to a next step, either applying the knowledge or running /plan/project.
Where does the report get saved?
Under artifacts/research/ in the current working directory. The filename combines the date, a slug of the topic and deep-dive.md, for example 2025-01-15-kubernetes-networking-deep-dive.md.
Source text
deep-dive.md · MIT
--- description: Comprehensive investigation of a topic - thorough analysis with sources argument-hint: [topic or leave blank for current context] --- <objective> Conduct a deep-dive investigation into $ARGUMENTS (or the current topic if no arguments provided). Go beyond surface-level understanding. Synthesize multiple sources into comprehensive knowledge. </objective> <intake_gate> <context_analysis> First, analyze $ARGUMENTS to extract what's already provided: - The topic to investigate - Specific questions to answer - Depth required - How this knowledge will be used Only ask about genuine gaps - don't re-ask what's already stated. </context_analysis> <initial_questions> Use AskUserQuestion to ask 2-4 questions based on actual gaps: **If questions unclear:** - "What do you need to understand?" with options: How it works, When to use it, Why it exists, Limitations/gotchas, All of the above, Other **If depth unclear:** - "How deep should I go?" with options: Overview (key points only), Solid understanding (main concepts), Comprehensive (thorough coverage), Other **If focus unclear:** - "Any specific angles?" with options: Practical application, Theoretical understanding, Comparison to alternatives, Historical context, Other **If application unclear:** - "How will this be used?" with options: Inform implementation, Make architecture decision, Evaluate feasibility, General knowledge, Other Skip questions where $ARGUMENTS already provides the answer. </initial_questions> <decision_gate> After receiving answers, use AskUserQuestion: Question: "Ready to start the deep dive, or would you like me to ask more questions?" Options: 1. **Start research** - I have enough context 2. **Ask more questions** - There are details to clarify 3. **Let me add context** - I want to provide additional information If "Ask more questions" → generate 2-3 contextual follow-ups, then present decision gate again If "Let me add context" → receive input, then present decision gate again If "Start research" → proceed to research </decision_gate> </intake_gate> <process> After intake complete: 1. Define the scope and key questions to answer 2. Gather information from multiple angles: - How it works (mechanics) - Why it exists (history, motivation) - How it's used (patterns, best practices) - Where it fails (limitations, edge cases) - What's next (trends, evolution) 3. Synthesize into coherent understanding 4. Identify remaining unknowns </process> <output_format> ## Deep Dive: [Topic] ### Strategic Summary [2-3 sentences: what this is, key insight, main implication for our work] ### Key Questions - [Question this research answers] - [Question this research answers] ### Overview [2-3 paragraph synthesis of what this is and why it matters] ### How It Works [Detailed explanation of mechanics, architecture, or process] ### History & Context [Why it exists, what problem it solved, how it evolved] ### Patterns & Best Practices - [Pattern/practice 1]: [when and why] - [Pattern/practice 2]: [when and why] - [Pattern/practice 3]: [when and why] ### Limitations & Edge Cases - [Limitation]: [workaround or mitigation] - [Edge case]: [how to handle] ### Current State & Trends [Where things are heading, recent developments, community direction] ### Key Takeaways 1. [Most important insight] 2. [Second most important insight] 3. [Third most important insight] ### Remaining Unknowns - [ ] [Question that still needs answering] - [ ] [Question that still needs answering] ### Implementation Context <claude_context> <application> - when_to_use: [situations where this applies] - when_not_to_use: [situations to avoid this] - prerequisites: [what must be true to use this] </application> <technical> - libraries: [relevant packages/tools] - patterns: [code patterns to follow] - gotchas: [common mistakes, edge cases] </technical> <integration> - works_with: [complementary technologies] - conflicts_with: [incompatible approaches] - alternatives: [other options to consider] </integration> </claude_context> **Next Action:** Apply this knowledge to implementation, research specific aspect deeper, or run /plan/project ### Sources - [Source name]: [URL] - [date accessed] - [Source name]: [URL] - [date accessed] </output_format> <artifact_output> Save the research to a file: 1. Create directory structure if it doesn't exist: - `[current-working-directory]/artifacts/research/` 2. Generate filename from topic: - Get current date in YYYY-MM-DD format - Slugify the topic (lowercase, hyphens for spaces) - Format: `YYYY-MM-DD-[topic]-deep-dive.md` - Example: `2025-01-15-kubernetes-networking-deep-dive.md` 3. Write the complete research to the file 4. Report to user: "Saved to `artifacts/research/[filename]`" </artifact_output> <success_criteria> - Answers the key questions thoroughly - Goes beyond surface-level (not just "what" but "why" and "when") - Identifies limitations honestly - Synthesizes into actionable understanding - Implementation context is specific enough for Claude to apply - Clear about what's still unknown - Output saved to artifacts/research/ directory </success_criteria>
© Lex Christopherson · MIT · glittercowboy/taches-cc-resources