skillboardUpdated every 6 hours
skillboardAutonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
Auto Review Loop (Generic LLM): Autonomous Research Improvement Autonomously iterate: review → implement fixes → re review, until the external reviewer gives a positive assessment or MAX ROUNDS is reached. Context: $ARGUMENTS Constants MAX ROUNDS 4 POSITIVE THRESHOLD: score 6/10, or verdict contains "accept", "sufficient", "ready for submission" REVIEW DOC: in project root (cumulative log) LLM Configuration This skill uses any OpenAI compatible API for external review via the MCP server.…
Full body not shown for this license – view the source on GitHub →Copy a source-pinned command for your client. You run it yourself.
Destination: .claude/skills/auto-review-loop-llm · pinned to the source commit
# Run from your project root
git clone https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git .skillboard-tmp
git -C .skillboard-tmp checkout 692e9fa3fea40bbdf614584d461851f8fb968ac2
mkdir -p ".claude/skills"
cp -r ".skillboard-tmp/skills/42-wanshuiyin-ARIS/skills/auto-review-loop-llm" ".claude/skills/"
rm -rf .skillboard-tmpReview the source before running. This copies files into your project; it is not a one-click install and does not verify runtime safety.
sudo apt update && sudo apt install -y gitnpm install -g @anthropic-ai/claude-code# Run from your project root
git clone https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git .skillboard-tmp
git -C .skillboard-tmp checkout 692e9fa3fea40bbdf614584d461851f8fb968ac2
mkdir -p ".claude/skills"
cp -r ".skillboard-tmp/skills/42-wanshuiyin-ARIS/skills/auto-review-loop-llm" ".claude/skills/"
rm -rf .skillboard-tmpDestination: .claude/skills/auto-review-loop-llm
Scanner static-checks@0.1.0 · commit 692e9fa3fea4. Static checks cannot prove runtime safety – review the source and the exact diff before installing. How checks work.
References credentials, tokens or secret files that a skill should not need.
Evidence: [redacted]· fingerprint ccae6d912a41bfef
Fetches remote content at runtime, which can change after review.
Evidence: curl· fingerprint 427e4b79b1f0fc90