OpenClaw is an open-source local AI agent that connects to any LLM. Add a Spine tool config and OpenClaw will delegate research-heavy tasks to Spine automatically.Documentation Index
Fetch the complete documentation index at: https://docs.getspine.ai/llms.txt
Use this file to discover all available pages before exploring further.
Install
Install OpenClaw if you don’t have it:SKILL.md for Spine into OpenClaw’s user skills directory:
Download skill file
spine.openclaw.md — drop into ~/.openclaw/skills/spine/OpenClaw uses
skills/, not tools/. The file must be named exactly
SKILL.md inside a per-skill directory (~/.openclaw/skills/spine/SKILL.md).
OpenClaw also accepts skills under ~/.openclaw/workspace/skills/<name>/SKILL.md
if you want a workspace-scoped install.Set your API key
AddSPINE_API_KEY to your environment or to OpenClaw’s .env file:
What it does
The skill teaches the OpenClaw agent:- When to delegate — multi-source research, competitive landscapes, reports, slide decks, spreadsheets, web apps
- The two-step pattern —
POST /v1/run→ pollGET /v1/run/{run_id}every 15–30s (runs average 10–20 min, up to 2 hr) - How to pick a template —
deep_research,report,slides,memo,excel,app,landing_page, orauto - How to present results —
final_outputtext + artifact download links
Headless invocation
For unattended use (CI, scheduled runs, scripts):--localruns the embedded agent (no gateway required; needs a model-provider key such asOPENAI_API_KEYorANTHROPIC_API_KEYin the shell).--agent main(or--session-id …, or--to <E.164>) is required — otherwiseopenclaw agentexits withPass --to <E.164>, --session-id, or --agent to choose a session.- OpenClaw loads skills lazily. If your prompt doesn’t clearly match the skill’s description, the agent may solve the task with its default tools instead. For deterministic routing, mention the capability by name (“using your Spine skill”) or prompt the agent to check its available skills first.
Example
For long-running production workflows, register a webhook instead of polling — see Webhooks. Polling loops inside the agent can exhaust turn budgets on runs longer than 5–10 minutes.
Templates
Pass the template that best fits the output:| Template | Output |
|---|---|
auto | Agent picks |
deep_research | Research memo |
report | Report (.docx) |
slides | Slide deck (.pptx) |
memo | Memo (.docx) |
excel | Spreadsheet (.xlsx) |
app | Web app (.html) |
landing_page | Landing page (.html) |