.claude/skills/audit-sync/SKILL.md
--- name: audit-sync description: Cross-project audit and sync. Backs up, bootstraps, promotes, syncs, and verifies all downstream projects. disable-model-invocation: true allowed-tools: Bash, Read argument-hint: [--dry-run] [--project <name>] --- # Audit Sync ## Objective Bring all downstream projects up to date with the upstream agent-kit. Runs a 5-phase workflow: Backup, Bootstrap, Promote, Sync, Verify. ## Usage ```bash # From upstream agent-kit directory ./scripts/audit-sync.sh --dry-r
npx skillsauth add lucidlabs-hq/agent-kit .claude/skills/audit-syncInstall 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.
Bring all downstream projects up to date with the upstream agent-kit. Runs a 5-phase workflow: Backup, Bootstrap, Promote, Sync, Verify.
# From upstream agent-kit directory
./scripts/audit-sync.sh --dry-run # Preview
./scripts/audit-sync.sh # Full audit
./scripts/audit-sync.sh --project neola # Single project
| Phase | Action | |-------|--------| | 1. Backup | rsync + git bundle of every project to ~/.lucidlabs-backups/ | | 2. Bootstrap | Fix broken projects (missing sync scripts, .upstream-sync.json) | | 3. Promote | Process promote queues from all projects (creates PRs) | | 4. Sync | Run sync-upstream.sh --all in each project | | 5. Verify | Check .upstream-sync.json, zone markers, scripts, promote queues |
| Flag | Effect | |------|--------| | --dry-run | Preview without changes | | --project NAME | Process single project | | --backup-dir PATH | Custom backup location | | --skip-promote | Skip promote phase | | --skip-bootstrap | Skip bootstrap phase | | --skip-backup | Skip backup (dangerous) | | --yes | Auto-confirm all prompts |
development
Deploy invoice-accounting-assistant to HQ server. Runs tests first (TDD), then builds and deploys. Use when ready to push changes to staging/production.
testing
Visual UI verification with agent-browser. Use after implementing UI components to take screenshots, verify interactions, and self-check your work. FASTER than E2E tests.
documentation
Update README with current project status and features. Use after completing features.
tools
--- name: time-report description: Cross-project time report. Aggregates all session data from ~/.claude-time/sessions/. Use to see how much time was spent across all projects. disable-model-invocation: true allowed-tools: Bash, Read argument-hint: [all | this-week | this-month | last-month | {project-name}] --- # Time Report: Cross-Project Session Overview ## Objective Read ALL session files from `~/.claude-time/sessions/*.json` and produce an aggregated time report. Supports filtering by pe