.claude/skills/scheduled-run/SKILL.md
Wrapper for scheduled playbooks - handles git sync before and after execution
npx skillsauth add abilityai/cornelius scheduled-runInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Wrapper that runs any playbook with git sync. Use this for all scheduled executions to ensure:
Ensures scheduled playbooks on Trinity stay in sync with the GitHub repository.
$ARGUMENTS = The playbook name to run (e.g., auto-discovery, analyze-kb)
cd /Users/eugene/Dropbox/Agents/Cornelius && git pull --rebase
If conflicts, abort and log error.
Invoke the specified playbook using the Skill tool:
Skill: $ARGUMENTS
Wait for completion.
cd /Users/eugene/Dropbox/Agents/Cornelius && git status --porcelain
If no changes, skip to completion.
cd /Users/eugene/Dropbox/Agents/Cornelius && git add -A && git commit -m "$(cat <<'EOF'
Scheduled: $ARGUMENTS $(date '+%Y-%m-%d %H:%M')
Automated execution via /scheduled-run
Co-Authored-By: Claude <[email protected]>
EOF
)"
cd /Users/eugene/Dropbox/Agents/Cornelius && git push
| Error | Recovery | |-------|----------| | Pull fails (conflicts) | Abort, log error, do not run playbook | | Playbook fails | Still attempt commit/push of partial changes | | Push fails | Log error, changes remain local |
Schedule format:
Daily 5am → /scheduled-run refresh-index
Sunday 8pm → /scheduled-run auto-discovery
Sunday 10pm → /scheduled-run analyze-kb
1st & 15th → /scheduled-run integrate-recent-notes
development
Rebuild the Cornelius voice agent system prompt from knowledge base sources
data-ai
Update dashboard.yaml with current knowledge base metrics from analysis report
documentation
Update Knowledge Graph Changelog
testing
Comprehensive testing playbook for Local Brain Search memory improvements (Phases 1, 3, 4)