dvy1987/agent-loom / .agents/skills/agent-loom-sync
agent-loom-sync
VerifiedSync library skills from an agent-loom upstream repo into this project's .agents/skills while preserving project-local and forked skills. Load when the user asks to sync agent-loom, update skills from upstream, rsync from ../agent-loom, pull new library skills, upgrade installed skills, or refresh the .agents folder without losing custom project skills. Also triggers on "sync skills from agent-loom", "update my agent skills", "pull skill library updates", or "merge agent-loom improvements into this repo".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.3 KB |
| references/examples.md | markdown | 1.9 KB |
| references/sync-policy.md | markdown | 1.5 KB |
| scripts/sync_agent_loom.py | script | 9.5 KB |
| templates/agent-loom-sync.json | config | 131 B |
references/sync-policy.md
View on GitHub# Sync Policy — Protection Rules
## Automatic protection (never overwrite on sync)
1. **Local-only** — skill directory exists in project but not in upstream `.agents/skills/`.
2. **project-local origin** — `metadata.origin: project-local` in SKILL.md. `universal-skill-creator` writes it; `agent-loom-sync --apply` stamps it on local-only skills missing it.
3. **forked_skills** — key listed in `.agents/agent-loom-sync.json` with optional reason string.
4. **protected_skills** — explicit list in config (manual pins).
## Safe to update (rsync from upstream)
- Skill exists in both repos
- Not protected by any rule above
- Directory hash differs from upstream
## Add (new upstream skills)
- Present in upstream, absent locally → full directory rsync in.
## Unchanged
- Hash match — skip rsync.
## Resolving forks
When user wants upstream version of a forked skill:
1. Remove from `forked_skills` and `origin: project-local` if set
2. Back up local copy: `mv .agents/skills/<name> .agents/skills/.backup-<name>-<date>/`
3. Re-run sync with `--apply`
When user wants to keep fork permanently:
- Add to `forked_skills`, or rely on auto-stamp if the skill is local-only (not in upstream)
## What is NOT synced by default
| Path | Reason |
|------|--------|
| Project root `AGENTS.md` | Generated by project-setup for this repo |
| `docs/` in project | Project artifacts |
| Whole `.agents/` delete | Would remove local skills |
Optional with user consent: `.agents/ROUTING.md` if unchanged locally.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |