skills/pka-backup/SKILL.md
Automated backup skill for PKA + Obsidian + Claude memory. Snapshots pka.db (via SQLite .backup so WAL is handled safely), the Obsidian vault, Claude memory files, agent profiles, and the help-content Excel into a single timestamped zip in Zoho WorkDrive. Daily/weekly/monthly retention rotation built in. USE WHEN Danny says "backup", "run backup", "snapshot pka", or to recover from a snapshot.
npx skillsauth add asets-gobizit/claude-skills pka-backupInstall 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.
THIS SKILL HAS FUNCTIONAL CODE. See pka_backup.py.
Use this skill when:
BACKUP_ROOT mtime)Use the restore mode when:
A single timestamped zip — written to TWO destinations for 3-2-1 backup-rule compliance:
C:\Users\dansk\Zoho WorkDrive (Go Biz IT)\00 Claude.ai\Backups\PKA\pka-backup-YYYY-MM-DD_HHMMSS.zipC:\Users\dansk\Dropbox\PKA-Backups\pka-backup-YYYY-MM-DD_HHMMSS.zip (different cloud provider — true offsite redundancy)Each zip contains:
| Inside the zip | Source |
|----------------|--------|
| pka.db | @team-ai.biz/data/pka.db (via SQLite .backup — WAL-safe) |
| obsidian/... | Entire Obsidian@Claude/ tree (excluding .git, .obsidian/workspace*, etc.) |
| memory/... | ~/.claude/projects/c--Users-dansk-Claude/memory/ (Claude auto-memory) |
| agents-global/... | ~/.claude/agents/*.md |
| agents-project/... | @team-ai.biz/.claude/agents/*.md |
| help-content.xlsx | @team-ai.biz/data/help-content.xlsx (Danny's help editorial source) |
| manifest.json | Source paths, byte counts, UTC timestamp |
Older snapshots are deleted on the next cleanup pass. Total typical footprint: ~17 snapshots.
# Take a snapshot now (default: also runs retention cleanup)
python C:/Users/dansk/.claude/skills/pka-backup/pka_backup.py
# Dry-run — show what would happen, no writes
python C:/Users/dansk/.claude/skills/pka-backup/pka_backup.py --dry-run
# Only run retention cleanup, no new snapshot
python C:/Users/dansk/.claude/skills/pka-backup/pka_backup.py --cleanup
# Skip retention after snapshot
python C:/Users/dansk/.claude/skills/pka-backup/pka_backup.py --no-cleanup
# Restore a snapshot to <BACKUP_ROOT>/restore/ (does NOT overwrite source — manual review required)
python C:/Users/dansk/.claude/skills/pka-backup/pka_backup.py --restore "C:/Users/dansk/Zoho WorkDrive (Go Biz IT)/00 Claude.ai/Backups/PKA/pka-backup-2026-04-25_103045.zip"
Run install_schedule.ps1 once (as admin) to register a Windows Task Scheduler job that runs daily at 03:00. Uninstall via the same script with -Uninstall.
The restore command extracts to <BACKUP_ROOT>/restore/. It does NOT automatically overwrite source paths. Reason: restore is rare and high-stakes; manual review prevents accidents. Workflow:
pka_backup.py --restore <zip> — extracts to Backups/PKA/restore/sqlite3, zipfile, shutil, pathlib, argparse, json, datetime, hashlib)pip install neededSnapshot target: C:\...\Backups\PKA\pka-backup-2026-04-25_103045.zip
zipping Obsidian vault...
zipping memory files...
Snapshot created: C:\...\Backups\PKA\pka-backup-2026-04-25_103045.zip (42.7 MB)
Retention: kept 8, deleted 0
Done.
tool_pka_backup_skill.mdArchitecture/Claude Setup/PKA Backup Skill.mdtesting
Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology, packaged as the stress-test skill. MANDATORY TRIGGERS: 'stress-test this', 'stress test this', 'pressure-test this', 'pressure test this', 'war room this', 'council this', 'run the council', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a stress-test question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.
content-media
Weekly scan of Obsidian vault for empty/low-content notes. Moves them to zToBeDeleted/ for user review. Use when the user says "tidy obsidian", "clean obsidian", "obsidian cleanup", or on scheduled weekly run.
development
Design-first website builder. Accepts a Claude Design export (HTML or screenshot) as a visual blueprint, collects business inputs, calls Claude API to generate a design-matched index.html, and publishes to GitHub Pages. Falls back to vibe-based generation if no design is provided. Use when the user says "make-website-design", "design website", "build from design", or provides a Claude Design export for website generation.
tools
Expert system for creating Skills for the Antigravity agent environment. Generates complete `.agent/skills/` directories with SKILL.md files, helper scripts, examples, and resources following strict structural and writing standards. Use this skill whenever the user asks to build, generate, or scaffold a skill for Antigravity, mentions `.agent/skills/`, asks for a SKILL.md template, or wants to create agent capabilities using the Antigravity skill format. Also trigger when the user says things like 'build me a skill for X' or 'create an Antigravity skill' or references the Antigravity agent system.