Total Skills
2
Author Profile: renatodarrigo
Skills published by renatodarrigo with real stars/downloads and source-aware metadata.
Total Stars
2
Total Downloads
0
Skills Performance
Comparison chart based on real stars and downloads signals from source data.
claw-drive-start
1
Stars
1
Downloads
0
claw-drive-status
1
Stars
1
Downloads
0
Published Skills
claw-drive-start
Spawn a driven Claude Code session (Session B) in the given directory and start the Monitor flow against the returned watch_command. Usage — /claw-drive-start <cwd> [--brief <file>] [--policy <file>] [--verbose]. The cwd must exist and be a real project root. If --brief is omitted, the user will be asked for the scenario brief inline. If --policy is omitted, the conservative starter shipped with claw-drive is used. By default Session B receives a system-prompt wrapper teaching a two-token vocabulary — emit [NEEDS-INPUT] when the human is needed, [DONE] when the task is complete, nothing otherwise — and Monitor surfaces turn_completed only when one of those two trailing tokens is present. Pass --verbose to bypass both the wrapper injection and the sentinel filter (raw stream including every turn_completed and tool_output_provided).
Repository SourceNeeds Review
claw-drive-status
Fetch a snapshot of one or all driven claw-drive sessions and characterize what's happening. Usage — /claw-drive-status [<session-id>]. Calls `claw-drive status [--json]` under the hood, parses the result, and surfaces what's noteworthy (sessions waiting on input, pending tool decisions, recent failures) — does NOT dump raw JSON to the user. Use this when the user asks "what's going on?" or you need a cold-start snapshot of in-flight driven sessions.
Repository SourceNeeds Review