paperclip
Onboard and manage Paperclip AI for research-paper knowledge and agent orchestration
Skill by lamm-mit
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/lamm-mit-paperclip
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: research, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/paperclip
What's inside
- Skill name
paperclip- Description
- Onboard and manage Paperclip AI for research-paper knowledge and agent orchestration
- License
- Apache-2.0
- Instructions
- 79 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (2)
- SKILL.md
- paperclip.py · scripts/
SKILL.md (first lines)
# Paperclip
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:
```bash
npx paperclipai onboard --yes
```
## Usage
### Check local prerequisites
```bash
python3 {baseDir}/scripts/paperclip.py --action check --format json
```
### Show the onboarding command without running it
```bash
python3 {baseDir}/scripts/paperclip.py --action onboard --format json
```
### Run non-interactive onboarding
```bash
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.
### Run Paperclip health checks
```bash
python3 {baseDir}/scripts/paperclip.py --action doctor --execute --format json
```
### Start Paperclip
```bash
python3 {baseDir}/scripts/paperclip.py --action run --execute --format json
```
## Parameters
| 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` |
## Output
The skill returns a JSON object with:
- `action`: requested operation
- `command`: command ScienceClaw would run or did run
- `executed`: whether a command was executed
- `returncode`, `stdout`, and `stderr` when executed
- `pid` and `log_file` for detached server runs
- `checks` for local Node/npm/npx availability
## Notes
- Requires Node.js, npm, and npx. Paperclip currently documents Node.js 20+ as the expected runtime.
- `onboard --yes` uses Paperclip's non-interactive quickstart defaults.
- Rerunning onboarding should preserve an existing Paperclip configuration; use Paperclip's own configuration commands for later edits.From lamm-mit/scienceclaw, Apache-2.0.
More from lamm-mit/scienceclaw
- 0.516score
drugbank-database
lamm-mit
Access and analyze comprehensive drug information from the DrugBank database including drug properties, interactions, targets, pathways, chemical structures…
SkillCFreshness: C★ 250Claude Code +9 - 0.516score
geometry-generator
lamm-mit
Generate parametric bioinspired ribbed membrane STL geometry via LLM-guided design.
SkillCFreshness: C★ 250Claude Code +9 - 0.516score
disease-research
lamm-mit
Generate comprehensive disease research reports using 100+ ToolUniverse tools.
SkillCFreshness: C★ 250Claude Code +9 - 0.516score
drug-research
lamm-mit
Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections.
SkillCFreshness: C★ 250Claude Code +9 - 0.516score
fem-analysis
lamm-mit
Modal analysis of a membrane STL using Kirchhoff plate FEM (scipy eigensolver).
SkillCFreshness: C★ 250Claude Code +9 - 0.516score
generate-image
lamm-mit
Generate or edit images using AI models (FLUX, Gemini).
SkillCFreshness: C★ 250Claude Code +9 - 0.516score
ase
lamm-mit
Atomic Simulation Environment (ASE) for computational materials science.
SkillCFreshness: C★ 250Claude Code +9 - 0.516score
askcos
lamm-mit
Retrosynthetic template relevance prediction using a locally deployed ASKCOS TorchServe service.
SkillCFreshness: C★ 250Claude Code +9 - 0.516score
pylabrobot
lamm-mit
Vendor-agnostic lab automation framework.
SkillCFreshness: C★ 250Claude Code +9 - 0.516score
biorxiv-database
lamm-mit
Efficient database search tool for bioRxiv preprint server.
SkillCFreshness: C★ 250Claude Code +9 - 0.516score
esm
lamm-mit
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C…
SkillCFreshness: C★ 250Claude Code +9 - 0.516score
jax-modal-analysis
lamm-mit
3D tetrahedral FEM modal analysis of a membrane STL.
SkillCFreshness: C★ 250Claude Code +9
Signals
- Stars
- 250
- Forks
- 47
- Open issues
- 1
- Last commit (this folder)
- May 21, 2026 (5 months ago)
- Last release
- Jun 23, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/lamm-mit/scienceclaw
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from lamm-mit
- 0.516score
biorxiv-database
lamm-mit
Efficient database search tool for bioRxiv preprint server.
SkillCFreshness: C★ 250Claude Code +9 - 0.516score
disease-research
lamm-mit
Generate comprehensive disease research reports using 100+ ToolUniverse tools.
SkillCFreshness: C★ 250Claude Code +9 - 0.516score
askcos
lamm-mit
Retrosynthetic template relevance prediction using a locally deployed ASKCOS TorchServe service.
SkillCFreshness: C★ 250Claude Code +9 - 0.516score
ase
lamm-mit
Atomic Simulation Environment (ASE) for computational materials science.
SkillCFreshness: C★ 250Claude Code +9 - 0.516score
pylabrobot
lamm-mit
Vendor-agnostic lab automation framework.
SkillCFreshness: C★ 250Claude Code +9 - 0.516score
drug-research
lamm-mit
Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections.
SkillCFreshness: C★ 250Claude Code +9
Cite this page
paperclip skill. Agent Mart. https://agentmart.dev/skills/lamm-mit-paperclip (last updated 2026-10-24)