skills/paperclip/SKILL.md
Onboard and manage Paperclip AI for research-paper knowledge and agent orchestration
npx skillsauth add lamm-mit/scienceclaw paperclipInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use Paperclip AI from ScienceClaw to onboard a local Paperclip instance, run health checks, and start the service that provides AI agents with indexed literature and orchestration capabilities.
Paperclip's quickstart command is:
npx paperclipai onboard --yes
python3 {baseDir}/scripts/paperclip.py --action check --format json
python3 {baseDir}/scripts/paperclip.py --action onboard --format json
python3 {baseDir}/scripts/paperclip.py --action onboard --execute --yes --format json
By default this detaches the long-running Paperclip server and returns a PID plus a log file.
python3 {baseDir}/scripts/paperclip.py --action doctor --execute --format json
python3 {baseDir}/scripts/paperclip.py --action run --execute --format json
| Parameter | Description | Default |
|-----------|-------------|---------|
| --action | Operation: check, onboard, doctor, run, or version | check |
| --execute | Actually run the Paperclip command; omitted means dry run | false |
| --detach | Run long-lived onboard/run commands in the background | true for onboard/run |
| --foreground | Keep long-lived commands attached to the current process | false |
| --yes | Pass --yes to paperclipai onboard | true |
| --run-after-onboard | Pass --run to paperclipai onboard | false |
| --repair | Pass --repair to paperclipai doctor | false |
| --bind | Optional bind target for onboarding, such as tailnet | - |
| --work-dir | Directory where the Paperclip CLI runs | current directory |
| --timeout | Command timeout in seconds | 600 |
| --wait-seconds | Seconds to watch a detached command before returning | 5 |
| --format | Output format: summary or json | summary |
The skill returns a JSON object with:
action: requested operationcommand: command ScienceClaw would run or did runexecuted: whether a command was executedreturncode, stdout, and stderr when executedpid and log_file for detached server runschecks for local Node/npm/npx availabilityonboard --yes uses Paperclip's non-interactive quickstart defaults.development
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.
testing
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.
development
Execute arbitrary Python code and return stdout. NumPy, pandas, scipy, matplotlib, and other scientific libraries are available.
content-media
Read a CSV or XLSX file and return columns, shape, dtypes, and first N rows as JSON.