agentleFS
matthewwong525matthewwong525/WongStack/.agents/skills/wong-sync/SKILL.md

wong-sync

Skill7 starsChanged 11 days agoMITView on GitHub

Update, sync, or upgrade this repo from the latest WongStack source, or review upstream changes, planned with /plan.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read .claude/.wong-stack.json for the installed version, upstream, and local choices.

    line 11
  2. Distinctive:

    Follow latest source, read the payload inventory, and run the helper once from the source, not the install, so an old install gets the …

    line 13

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/wong-sync

Get the latest WongStack source, run its payload preflight, and invoke /plan only for an update.

Read .claude/.wong-stack.json for the installed version, upstream, and local choices. No record, or a seed with null version and commit, means setup is incomplete: invoke wong-setup from the source checkout. Never sync the source repo with itself.

Follow latest source, read the payload inventory, and run the helper once from the source, not the install, so an old install gets the current classifier:

node "<source path>/.claude/skills/wong-sync/scripts/preflight.mjs" \
  --target "<target root>" \
  --source "<source path>" \
  --record "<record path relative to target>"

It fetches and writes nothing. Follow exactly one route, by the status in its versioned JSON:

  • current — report the source version and commit, selected-unit count, and preflight time; stop. No /plan or /explore, no change, no record edit.
  • update — keep the whole report in context and invoke /plan, never stopping at Plan it?. Start from changes; expand only for a named dependency or impact, never re-compare the full payload.
  • error — report every diagnostic and stop: no partial "current", no broad AI scan, no /plan.

An unknown schema version or status, truncated output, failed command, or invalid JSON is an error; never infer missing fields.

Invoke /plan with this description, filled in, plus any user instructions:

Update this repo to WongStack <version> at <source path>, commit <commit>; it now runs <installed version, or unknown>. The preflight found this complete set of changed payload units: <preflight report>. Start there and expand only for a named dependency or target impact. Keep local adaptations and renamed skills. If CLAUDE.md is a real file, not a link to AGENTS.md, plan its move per <source path>/.claude/skills/wong-sync/references/payload-manifest.md#the-agent-folder. Follow <source path>/.claude/skills/wong-sync/references/payload-manifest.md#planning-an-update for catch-up moves, skipped releases' hand steps, the merge check, and plain wording. Plan the useful updates through the normal workflow. As the last task, after implementation, record the source version in the install record.

Pass prior user decisions as context, an old verdict record's too. Use installed skills by their recorded names, else the source's; resolve source resources in the source checkout while working in the target. Provision a missing part by setup's provisioning runbook from the source checkout.

/plan owns the artifacts and review; its bounded /explore owns investigation and questions. Ask in the ask format. A bare sync stops at the plan's review.html with the next step; a request to implement or ship continues through that verb (just ask). Write no verdict file; prescribe no proposal format.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.