deep-research
Deep research before design — 3-5 parallel research agents survey papers, production systems, failure modes, and prior art, then a synthesizer compiles evidence, and an integrator maps findings to a concrete codebase plan with citations
npx skills add majiayu000/claude-skill-registry --skill deep-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.
# Deep Research A three-phase evidence-gathering workflow for problems where getting the design wrong is expensive: safety-critical code, performance-critical paths, distributed systems protocols, unsafe Rust, concurrency primitives, and novel algorithms. Research agents independently survey the landscape (papers, production systems, post-mortems, specifications), a synthesizer cross-references and ranks the evidence, and an integrator maps findings to a concrete implementation plan grounded in the codebase. ## When to Use - **Safety-critical**: unsafe blocks, memory management, lock-free data structures - **Performance-critical**: hot-path algorithms, cache-aware layouts, SIMD strategies - **Distributed systems**: consensus, replication, failure detection, ordering - **Novel or unfamiliar territory**: algorithms you haven't implemented before - **High-stakes design decisions**: choices that are expensive to reverse - **Concurrency**: lock strategies, atomic ordering, async runtime interactions ## When NOT to Use - Straightforward CRUD features or wiring code - Problems with a single obvious solution - Tasks where you already have deep domain expertise and just need to code - Use `
- When to Use
- When NOT to Use
- Invocation
- Phase 1 — Research (3-5 Parallel Agents)
- Research Agent Specialties
- Collecting Results
- Phase 2 — Synthesize (Single Agent)
- Synthesizer Prompt
- Phase 3 — Integrate (Single Agent)
- Integrator Prompt
- Final Output Format
- Configuration
- Tips
What does the deep-research skill do?
Deep research before design — 3-5 parallel research agents survey papers, production systems, failure modes, and prior art, then a synthesizer compiles evidence, and an integrator maps findings to a concrete codebase plan with citations
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill deep-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.