feat: add deep-research skill with 4-phase methodology#344
Conversation
Spec: design for two features inspired by DeerFlow analysis Plan: 9-task implementation plan across 5 chunks, two PRs Co-Authored-By: Claude Opus 4.6 <[email protected]>
Teaches the agent systematic research using web_search and web_fetch: - Phase 1: Broad exploration (3-5 searches) - Phase 2: Deep dive (targeted + full content fetch) - Phase 3: Diversity validation (6 information types) - Phase 4: Synthesis check Inspired by DeerFlow's research methodology, adapted for ZeptoClaw with memory integration and temporal awareness. Closes #338
Skills loader only recognizes `requires` and `os` under metadata.zeptoclaw. The `tags` field was silently ignored. Co-Authored-By: Claude Opus 4.6 <[email protected]>
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (3)
✨ Finishing Touches🧪 Generate unit tests (beta)
📝 Coding Plan
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
## Summary - Adds `deep-research` bundled skill (`skills/deep-research/SKILL.md`) that teaches the agent systematic multi-phase web research - 4-phase methodology: Broad Exploration, Deep Dive, Diversity & Validation, Synthesis Check - Includes temporal awareness, memory integration, and anti-patterns guidance - Zero binary cost — pure markdown skill file Closes qhkm#338 ## Test plan - [ ] `zeptoclaw skills list` shows `deep-research` in output - [ ] Skill content loads correctly when agent is asked to research a topic - [ ] No impact on binary size or compilation 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 4.6 <[email protected]>
1 participant
Summary
deep-researchbundled skill (skills/deep-research/SKILL.md) that teaches the agent systematic multi-phase web researchCloses #338
Test plan
zeptoclaw skills listshowsdeep-researchin output🤖 Generated with Claude Code