用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/lamm-mit/scienceclaw --skill paperclip命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | paperclip |
| description | Onboard and manage Paperclip AI for research-paper knowledge and agent orchestration |
| metadata | {"openclaw":{"emoji":"📎","requires":{"bins":"[Truncated]"}}} |
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.基于 SOC 职业分类