deep-dive
Featured2-stage pipeline: trace (causal investigation) -> deep-interview (requirements crystallization) with 3-point injection
Install
Quality Score: 99/100
Skill Content
Details
- Author
- Yeachan-Heo
- Repository
- Yeachan-Heo/oh-my-claudecode
- Created
- 8 months ago
- Last Updated
- today
- Language
- TypeScript
- License
- MIT
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
deep-dive
Rigorous multi-agent deep-dive analysis for complex investigative tasks — auditing codebases, evaluating strategies or systems, validating designs, doing open-ended research. Deploys 4–6 specialist agents in parallel across distinct lanes, then synthesis, then adversarial red-team review, then optional patching — producing structured markdown research files plus a plain-English executive briefing with honest 1–10 confidence ratings. ALWAYS invoke when the user says any of "deep dive", "thorough audit", "rigorous analysis", "comprehensive review", "audit this codebase", "analyze the strategy", "evaluate this design", "review this thoroughly", or "research deep dive". Also invoke proactively for any open-ended investigative task involving a codebase, strategy, system design, or research question that warrants 30+ minutes of structured analysis — even when the user doesn't use these exact phrases.
deep-dive
Deep technical investigation for complex systems, unfamiliar codebases, architecture, data flows, and dependencies - when the system works but is not understood. Use when the user asks for a deep dive, investigate deeply, map the system, understand how it works, break down complexity, or produce an evidence-backed technical brief. If something is failing right now use the troubleshooting reference in morpheus; for a past incident timeline and contributing factors use premortem-postmortem.
deep-dive
Use when told "do a deep dive", "go figure this out", or "don't reinvent the wheel" - researches a question across every relevant source and returns a decision. Also fires on "see what everyone else is doing", "use all the skills you have", "what's the best way to X", "should we build this or buy it", "is this possible", "what is everyone doing about X", "research this properly", and any consequential question handed over for a researched answer rather than a quick one. Routes one question across the relevant source classes (primary docs and source code, open-source repos, commercial vendors, practitioner community, academic work, prediction markets, and the operator's own prior work), verifies decision-critical claims against the PING failure modes, and returns a decision-first brief, with an explicit build-vs-adopt call when the question is a sourcing decision. Starts at the cheapest route that can settle the question and escalates only against a named gap.