agentleFS
SkinnnyJaySkinnnyJay/wiki-llm/skills/wiki-upgrade/SKILL.md

wiki-upgrade

Skill0 starsChanged 4 months agoMITView on GitHub

Update the llm-wiki plugin repo (git pull), re-run setup, and sanity-check vault config against the new version.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are 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.

  • 4

    Very specific

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

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

    Update the wiki-llm plugin checkout (this repository), re-run ./setup if present, and verify the user’s llm-wiki/config.json still matches …

    line 9
  2. Distinctive:

    If merge conflicts or non-ff: stop and ask the user to resolve manually.

    line 24
  3. Very specific:

    If ./setup exists and is executable:

    line 28
  4. Very specific:

    Run python3 scripts/llm_wiki.py --help or bin/llm-wiki validate from repo root with --vault /path/to/llm-wiki if the user has a vault …

    line 48
  5. Very specific:

    If templates/llm-wiki/config.json gained new keys, suggest merging defaults into the user vault’s config.json (do not overwrite without …

    line 49

≈ “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

Wiki upgrade — Self-update

Update the wiki-llm plugin checkout (this repository), re-run ./setup if present, and verify the user’s llm-wiki/config.json still matches the template schema expectations. No telemetry.

Pre-flight

  1. Confirm the user is at the plugin repo root (contains bin/llm-wiki, scripts/llm_wiki.py, .claude-plugin/plugin.json). If they only have a vault, tell them to git pull in the plugin clone they use for development.

Steps

Step 1 — Fetch and merge

git status
git pull --ff-only

If merge conflicts or non-ff: stop and ask the user to resolve manually.

Step 2 — Re-run setup script (optional)

If ./setup exists and is executable:

chmod +x ./setup
./setup

This refreshes agent-specific hints (Cursor rules, etc.) per the repo root setup script.

Step 3 — Changelog

Show recent changes:

git log -1 --oneline
# Optional: head CHANGELOG.md

Step 4 — Vault compatibility

  • Run python3 scripts/llm_wiki.py --help or bin/llm-wiki validate from repo root with --vault /path/to/llm-wiki if the user has a vault nearby.
  • If templates/llm-wiki/config.json gained new keys, suggest merging defaults into the user vault’s config.json (do not overwrite without confirmation).

Done looks like

  • Plugin repo is up to date with origin (or user knows why not).
  • ./setup ran without fatal errors, or user skipped with reason recorded.
  • User knows whether to re-run llm-wiki setup / wiki-setup for vault-only changes.

Artifacts

Reads: git history, CHANGELOG.md, optional llm-wiki/config.json. Writes: none except user-edited files from setup.

Related skills

  • wiki-setup — vault reconfiguration after breaking template changes
  • wiki-status — verify tools after upgrade

Smoke check

  • CLI: From the plugin repo root: llm-wiki check and python3 -m compileall scripts (optional syntax check).
  • Prompt: Invoke this skill; confirm upgrade checks git remote and plugin root paths.

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.