Skip to content

Commit c6c5da3

Browse files
yangruofengclaude
authored andcommitted
Add Auto-claude-code-research-in-sleep to Agent Skills
8 Claude Code skills for autonomous ML research workflows with cross-model collaboration (Claude Code executor + external LLM reviewer). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1 parent a2c6012 commit c6c5da3

File tree

1 file changed

+1
-0
lines changed

1 file changed

+1
-0
lines changed

README.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -80,6 +80,7 @@
8080

8181
- [AgentSys](https://github.com/avifenesh/agentsys) by [avifenesh](https://github.com/avifenesh) - Workflow automation system for Claude with a group of useful plugins, agents, and skills. Automates task-to-production workflows, PR management, code cleanup, performance investigation, drift detection, and multi-agent code review. Includes [agnix](https://github.com/avifenesh/agnix) for linting agent configurations. Built on thousands of lines of code with thousands of tests. Uses deterministic detection (regex, AST) with LLM judgment for efficiency. Used on many production systems.
8282
- [AI Agent, AI Spy](https://youtu.be/0ANECpNdt-4) by [Whittaker & Tiwari](https://signalfoundation.org/) - Members from the Signal Foundation with some really great tips and tricks on how to turn your operating system into an instrument of total surveillance, and why some companies are doing this really awesome thing. [warning: YouTube link].
83+
- [Auto-claude-code-research-in-sleep](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep) by [wanshuiyin](https://github.com/wanshuiyin) - 8 skills for autonomous ML research: Claude Code executes (reads papers, writes code, runs GPU experiments) while an external LLM reviews via Codex MCP (scores, finds weaknesses, suggests fixes). The auto-review-loop skill iterates review→fix→re-review overnight — a real run improved a paper from 5/10 to 7.5/10 across 4 rounds with 20+ GPU experiments, zero human intervention.
8384
- [Book Factory](https://github.com/robertguss/claude-skills) by [Robert Guss](https://github.com/robertguss) - A comprehensive pipeline of Skills that replicates traditional publishing infrastructure for nonfiction book creation using specialized Claude skills.
8485
- [cc-devops-skills](https://github.com/akin-ozer/cc-devops-skills) by [akin-ozer](https://github.com/akin-ozer) - Immensely detailed set of skills for DevOps Engineers (or anyone who has to deploy code, really). Works with validations, generators, shell scripts and CLI tools to create high quality IaC code for about any platform you've ever struggled painfully to work with. Worth downloading even just as a source of documentation.
8586
- [Claude Code Agents](https://github.com/undeadlist/claude-code-agents) by [Paul - UndeadList](https://github.com/undeadlist) - Comprehensive E2E development workflow with helpful Claude Code subagent prompts for solo devs. Run multiple auditors in parallel, automate fix cycles with micro-checkpoint protocols, and do browser-based QA. Includes strict protocols to prevent AI going rogue.

0 commit comments

Comments
 (0)