CoPaw API Chat

v0.1.0

Communicate with a CoPaw instance through its HTTP API. Use when: (1) you need to inspect available CoPaw agents or chats, (2) create a chat or session and s...

0· 144·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for erview/copaw-api-chat.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "CoPaw API Chat" (erview/copaw-api-chat) from ClawHub.
Skill page: https://clawhub.ai/erview/copaw-api-chat
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install copaw-api-chat

ClawHub CLI

Package manager switcher

npx clawhub@latest install copaw-api-chat
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match the actual content: the SKILL.md and references describe API endpoints, chat/session flow, and admin surfaces. No unrelated binaries, credentials, or installs are requested.
Instruction Scope
Instructions stay on-topic (create chat → send message → read SSE). The references document admin-level endpoints and explicitly warn they are high-risk; that is appropriate caution rather than scope creep. The skill does not instruct reading local files or unrelated environment variables.
Install Mechanism
No install spec and no code files—instruction-only—so nothing is written to disk or downloaded during install.
Credentials
The skill declares no required env vars or credentials. It mentions possible Basic Auth or Bearer tokens in context (real API concerns) but does not request unrelated secrets or excessive environment access.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent presence or modify other skills or system settings.
Assessment
This is an instruction-only skill for talking to a CoPaw HTTP API and appears coherent. Before using it: ensure you point requests at a trusted/local CoPaw instance (avoid exposing internal endpoints to the public internet); only provide Basic Auth or Bearer tokens when you trust the target server; avoid automating admin endpoints (/api/workspace, /api/mcp, /api/cron) unless you need admin tasks; and review any credentials you supply to other tools or scripts that call these endpoints. Because the skill is just documentation and examples, it won't install code, but the HTTP requests it recommends could be used to read or modify data on the target server — proceed with the usual caution when granting API access.

Like a lobster shell, security has layers — review code before you run it.

latestvk970hd7axz283zjzdj85z9dykh83dzv0
144downloads
0stars
1versions
Updated 1mo ago
v0.1.0
MIT-0

CoPaw API Chat

Use this skill to work with CoPaw over HTTP API, not through the web UI.

When to use

  • You need to talk to a local CoPaw instance programmatically.
  • You need the correct sequence: create chat/session → send message → read SSE.
  • You need to understand agent scoping, auth layers, or related API groups before building automation.

Workflow

  1. Read references/overview-auth-scoping.md first.
  2. If the task is about chatting with CoPaw, then read references/chats-console-sse.md.
  3. If the task touches agent/model/skill/tool management, read references/agents-models-skills-tools.md.
  4. If the task touches workspace, MCP, or cron, read references/workspace-mcp-cron.md.
  5. If you need ready-to-run examples, read references/practical-recipes.md.

Minimal practical path

  1. Confirm agent id (default unless proven otherwise).
  2. Create a chat with POST /api/chats.
  3. Reuse the returned session_id/user_id/channel context.
  4. Send the message with POST /api/agents/{agentId}/console/chat.
  5. Read the response as SSE.

Important rules

  • Do not assume stateless request/response. CoPaw is chat/session-centric.
  • Distinguish confirmed API behavior from interpretation.
  • Prefer agent-scoped routes (/api/agents/{agentId}/...) or set X-Agent-Id explicitly.
  • In the current deployment, auth may be provided by nginx Basic Auth even if internal CoPaw auth is off.
  • Treat /api/workspace and some /api/agents/*/files/* surfaces as dangerous/admin-level APIs.

References

  • references/overview-auth-scoping.md — API surface, auth, scoping, priorities
  • references/chats-console-sse.md — chat lifecycle, session context, SSE mechanics
  • references/agents-models-skills-tools.md — management surfaces around agents/models/skills/tools
  • references/workspace-mcp-cron.md — workspace, MCP, cron boundaries and risks
  • references/practical-recipes.md — short request examples and file structure examples

Output expectations

When using this skill, answer with:

  • the minimal correct endpoint sequence,
  • the required payload shape,
  • auth/scoping caveats,
  • and only the API groups relevant to the task.

Comments

Loading comments...