lamm-mit/skills/metabolism
skills/metabolism/SKILL.md
# Continuous Knowledge Metabolism - Summary This workflow automates a **daily research paper ingestion and synthesis cycle**. Here's the operational flow: ## Core Process **Setup Check:** Requires initialized `metabolism/config.json` with `currentDay >= 1`. **Five-stage cycle:** 1. **Search** — 5-day sliding window queries via arXiv and OpenAlex, deduplicating against `processed_ids` 2. **Read** — Extract methodology, conclusions, and knowledge connections from new papers 3. **Update** — In
$ install --global
skillsauthnpx skillsauth add lamm-mit/scienceclaw skills/metabolismInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 6, 2026, 12:46 PM58.8s1 file scanned
SKILL.md
Continuous Knowledge Metabolism - Summary
This workflow automates a daily research paper ingestion and synthesis cycle. Here's the operational flow:
Core Process
Setup Check: Requires initialized metabolism/config.json with currentDay >= 1.
Five-stage cycle:
- Search — 5-day sliding window queries via arXiv and OpenAlex, deduplicating against
processed_ids - Read — Extract methodology, conclusions, and knowledge connections from new papers
- Update — Integrate findings into
metabolism/knowledge/files (max 200 lines per topic, with compression of older content when needed) - Hypothesize — Generate new research hypotheses only when patterns genuinely emerge; skip if no insights warrant it
- Log — Record daily metrics and increment
currentDay
Key Constraints
- "不捏造论文中未出现的事实性声明" (don't fabricate claims absent from source papers)
- Preserve citations and evidence trails during knowledge compression
- Never force hypothesis generation
- Always read current file state before modifications
The system emphasizes incremental, honest knowledge building over raw output volume.
Related Skills
lamm-mit/paperclip
tools
VerifiedTrustedCommunity
Onboard and manage Paperclip AI for research-paper knowledge and agent orchestration
203SKILL.mdUpdated May 22, 2026
lamm-mit/perplexity-search
development
VerifiedTrustedCommunity
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.
184SKILL.mdUpdated Apr 6, 2026
lamm-mit/scientific-report-pdf
testing
VerifiedTrustedCommunity
Generate a structured scientific PDF report from a JSON description. Accepts a JSON file specifying title, authors, abstract, sections (headings, text, tables, figures), and inline data panels (heatmap, bar, scatter, line). Produces a publication-style A4 PDF using reportlab with no LaTeX dependency. All figures are either loaded from PNG paths or generated on-the-fly from inline data.
161SKILL.mdUpdated Apr 16, 2026
lamm-mit/python-exec
development
VerifiedTrustedCommunity
Execute arbitrary Python code and return stdout. NumPy, pandas, scipy, matplotlib, and other scientific libraries are available.
161SKILL.mdUpdated Apr 16, 2026