$ loading_
Chat directly with the Discord-backed OpenClaw agent in real time.
This appears to be a prompt/documentation-style skill with no declared secrets, remote endpoints, or local data permissions in the material itself; combined with open source and very high community adoption, the overall risk is low. The README does reference local relay scripts to interact with a Discord-backed agent/session, so any actual network sending or execution capability likely resides in external companion tooling rather than in this skill itself.
The material explicitly states there are no required keys or environment variables. The README only warns not to expose gateway tokens or session secrets, with no direct credential collection or abuse pattern shown.
The skill is described as talking to a 'Discord-backed agent/session,' and the README references openclaw_relay.py for ask/publish/force-send. Although no specific remote host is listed, its intended use clearly involves sending messages to an external session/Discord route, implying routine outbound data flow.
The README shows usage via local python3 relay scripts, indicating companion tooling may start local scripts/processes. However, the system flags this item as prompt-only, and the material does not show the skill itself requesting elevated or unusually dangerous execution privileges.
The material does not declare access to local files, databases, system resources, or Discord archive/history data. It explicitly says not to use this for local Discord archive queries, and no overbroad data access is described.
The source is an open-source GitHub repository with extremely high community adoption (~377k stars), which is a strong risk-reducing signal. While the license is not stated and maintenance status is unknown, there are no high-risk red flags such as closed source, unclear distribution, or suspicious installation payloads.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "discord-clawd" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/openclaw/main/.agents/skills/discord-clawd/SKILL.md 2. Save it as ~/.claude/skills/discord-clawd/SKILL.md 3. Reload skills and tell me it's ready
Connect to the current Discord-backed OpenClaw session and tell me what task the agent is handling, its current progress, and the recommended next step.
A status update summarizing the agent’s current task, progress, and recommended next actions.
In the Discord-backed OpenClaw session, send this instruction: prioritize investigating the latest build failure and reply with a concise list of issues found and suggested fixes.
The agent acknowledges the instruction and returns a list of issues and suggested fixes.
Continue the current OpenClaw session and follow up on the previous discussion: if this must be completed today, give me the minimum viable plan and key risks. This is a live conversation, not an archive search.
A contextual follow-up response with an executable minimum viable plan and risk notes.
Use this when the task is to talk with the Discord-backed agent/session, ask it a question, or post through that route.
For Discord archive/history/search, use $discrawl instead.
Use the OpenClaw relay helper:
cd ~/Projects/agent-scripts
python3 skills/openclaw-relay/scripts/openclaw_relay.py targets
python3 skills/openclaw-relay/scripts/openclaw_relay.py resolve --target maintainers
If the target alias exists, prefer a private ask first:
python3 skills/openclaw-relay/scripts/openclaw_relay.py ask \
--target maintainers \
--message "Reply with exactly OK."
Use publish when the session should decide whether to post. Use force-send only when the user explicitly wants a message posted.
Transcribe audio into text or speaker-separated transcripts with OpenAI APIs.
Automate web page workflows, login checks, tab handling, and recovery steps.
Generate concept, architecture, flow, and whiteboard diagrams in multiple formats.
Helps maintainers triage, clean up, and resolve OpenClaw secret scanning alerts.
Investigate test memory growth, heap leaks, and OOM root causes.
Run, debug, monitor, and summarize OpenClaw release CI workflows.
Connect OpenClaw to Claude Desktop for cross-assistant AI interaction.
Discover OpenClaw ecosystem resources, tools, plugins, and deployment options quickly.
Deploy and scale multi-tenant AI agent teams with strong built-in safety.
Connect Claude.ai/Desktop to self-hosted OpenClaw using OAuth 2.1.
Diagnose OpenClaw node pairing, auth, routing, and connection issues.
Search MCP servers, agent skills, and plugins from terminal or agents.