Check calendars, find open times, and manage Google Calendar events with confirmation before every change.
by Jay81 installs33 stars
Coding
OpenClaw CLI
Run and troubleshoot OpenClaw CLI workflows with consistent profiles, cautious execution, and explicit verification.
What it does
Operate and troubleshoot OpenClaw from the CLI with consistent default, dev, or named-profile context. Route requests to the appropriate command family, inspect help before risky operations, use JSON output for automation where available, and verify results with status, health, node, or command-specific checks.
When to use it
- Diagnosing OpenClaw health failures
- Managing gateway or node lifecycle issues
- Running commands in isolated profiles
- Automating verified CLI checks with JSON
The skill document
OpenClaw CLI
Run OpenClaw commands safely and efficiently. Choose the right command family, execute with the correct profile context, and verify postconditions.
Execution Workflow
-
Clarify the target state. Ask what should change and what must remain untouched.
-
Select runtime scope first. Use default profile unless isolation is requested. Use:
openclaw --dev ...for isolated dev state under~/.openclaw-dev.openclaw --profile ...for named isolated state under~/.openclaw-.
-
Choose the command family. Use
references/command-map.mdto route the request quickly. -
Expand command details before running risky operations. Run
openclaw --helpfor starred families and confirm flags. -
Prefer machine-readable output when automation is needed. Use
--jsonwhere available, then parse/verify. -
Verify outcomes explicitly. Check with
openclaw status,openclaw health,openclaw nodes status --json, or command-specific follow-up.
Safety Rules
- Require explicit user confirmation before
reset,uninstall, destructive--forceflows, or credential-clearing operations. - Prefer non-destructive diagnostics first:
status,health,doctor,logs. - Keep profile usage consistent across a workflow. Do not mix default and
--dev/--profilecommands accidentally. - For gateway issues, diagnose before restart unless restart is explicitly requested.
Triage Sequence
For generic "OpenClaw not working" issues:
- Run
openclaw status. - Run
openclaw health. - Run
openclaw doctor. - Check
openclaw gateway ...,openclaw node ..., oropenclaw nodes ...based on where failure appears. - Escalate to targeted commands in
references/command-map.md.
Resources
references/command-map.md: Command families, routing guidance, and practical recipes.
Questions people ask
- How does it handle an “OpenClaw not working” report?
- It follows a non-destructive triage sequence: run `openclaw status`, `openclaw health`, and `openclaw doctor`, then inspect gateway or node commands based on where the failure appears.
- How are isolated environments handled?
- It uses `openclaw --dev ...` for state under `~/.openclaw-dev` or `openclaw --profile ...` for named isolated state, and keeps that profile context consistent throughout the workflow.
- What safeguards apply to destructive commands?
- Explicit user confirmation is required before reset, uninstall, destructive `--force` flows, or credential-clearing operations. Diagnostics are preferred before changes, and gateway issues are diagnosed before restart unless a restart was requested.
Related skills
Save, search, organize, and manage Get Notes content and knowledge bases through explicit commands.
755 installs66 stars
Build and operate a testable learning plan with practice, spaced review, transfer checks, and durable local records.
by Iván93 installs3 stars
Learn a topic through level checks, adaptive explanations, retrieval practice, and review across sessions.
270 installs8 stars
Discover and trade Polymarket crypto fast markets using CEX momentum or a custom signal.
262 installs50 stars
Extract email dates, links, and deadlines for review, then create or update tracked Google Calendar events.
236 installs5 stars