deeper-research
Comprehensive 6-phase research funnel — 8-10 parallel survey agents sweep wide, a synthesizer compiles evidence, deep-dive and adversarial agents run in parallel to elaborate and challenge findings, a final synthesizer reconciles everything, and an integrator maps verified findings to a concrete codebase plan with full traceability
npx skills add majiayu000/claude-skill-registry --skill deeper-research-ahrav-gossip-rs --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Deeper Research A six-phase evidence-gathering funnel for problems where the cost of a wrong design exceeds the cost of thorough research. Doubles the agent count of `/deep-research` (21-23 agents vs 7), approaches the problem from 8-10 independent lenses, and adds adversarial review to challenge conclusions before they reach the implementation plan. The funnel narrows progressively: a wide initial survey generates raw findings, synthesis distills them, parallel deep-dives and adversarial challenges stress- test the synthesis from both directions, a final synthesis reconciles all streams, and an integrator grounds everything in the codebase with full traceability from finding IDs to implementation steps. ## When to Use - **Highest-stakes design decisions**: foundational architecture, core data structures, protocols that are impossible to change later - **Novel or unfamiliar territory at scale**: combining multiple research domains where cross-pollination matters - **When `/deep-research` isn't enough**: you need adversarial challenge of findings, deeper dives into gaps, and full traceability - **Safety-critical + performance-critical intersection**: where you need both theoretica
- When to Use
- When NOT to Use
- Invocation
- Architecture
- Finding ID Scheme (Traceability)
- Output Budgets Per Phase
- Evidence Strength Scale
- Orchestrator: Problem Decomposition (Inline)
- Steps
- Phase 1 — Wide Survey (8-10 Parallel Agents)
- 10 Research Lenses
- Common Preamble (included in every Phase 1 agent's prompt)
- Agent Focus Areas
- Collecting Phase 1 Results
What does the deeper-research skill do?
Comprehensive 6-phase research funnel — 8-10 parallel survey agents sweep wide, a synthesizer compiles evidence, deep-dive and adversarial agents run in parallel to elaborate and challenge findings, a final synthesizer reconciles everything, and an integrator maps verified findings to a concrete codebase plan with full traceability
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill deeper-research-ahrav-gossip-rs --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.