agentleFS
PratiyushPratiyush/llm-wiki/.claude/skills/wiki-all/SKILL.md

wiki-all

Skill383 starsChanged 5 months agoMITView on GitHub

Run the complete llmwiki pipeline from scratch — init, sync, graph, build, lint, and serve. Use when the user says "run everything", "full pipeline", "wiki-all", or wants to rebuild the entire wiki from session history.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run each step in order. Report the result of each before proceeding to the next.

    line 21
  2. Distinctive:

    If new sessions were converted, follow the Ingest Workflow from CLAUDE.md for each new file (create/update entity + concept pages, …

    line 39
  3. Distinctive:

    Ask the user: "Export graph to Obsidian vault?" If yes:

    line 49
  4. Distinctive:

    Ask the user: "Start the local server?" If yes:

    line 77

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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-all

What this skill does

Runs the complete llmwiki pipeline in the correct sequence:

  1. init — scaffold raw/, wiki/, site/ directories
  2. sync — convert .jsonl sessions to markdown
  3. graph — build Graphify AI knowledge graph (communities, god nodes, hyperedges)
  4. build — compile wiki/ markdown into site/ HTML
  5. lint — run 14 quality rules, report issues
  6. serve — start local server at http://127.0.0.1:8765

Steps

Run each step in order. Report the result of each before proceeding to the next.

Step 1: Init

python3 -m llmwiki init

Report what was created or confirmed.

Step 2: Sync

python3 -m llmwiki sync --no-auto-build --no-auto-lint

Report: how many sessions converted, how many unchanged, any errors.

If new sessions were converted, follow the Ingest Workflow from CLAUDE.md for each new file (create/update entity + concept pages, cross-link, update index).

Step 3: Graph

python3 -m llmwiki graph

Report: node count, edge count, community count, top 5 connected nodes.

Ask the user: "Export graph to Obsidian vault?" If yes:

python3 -c "
from llmwiki.graphify_bridge import export_to_obsidian
from pathlib import Path
export_to_obsidian(Path.home() / 'Documents/Obsidian Vault/Temp/Graph')
"

Step 4: Build

python3 -m llmwiki build

Report: HTML file count, total size, export formats written.

Step 5: Lint

python3 -m llmwiki lint

Report: total issues by severity (errors, warnings, info). Highlight any errors that need immediate attention.

Step 6: Serve

Ask the user: "Start the local server?" If yes:

python3 -m llmwiki serve --open

Report the URL: http://127.0.0.1:8765

After completion

Report a summary table:

StepResult
initN dirs, M seed files
syncN converted, M unchanged
graphN nodes, M edges, K communities
buildN HTML files, M MB
lintN issues (E errors, W warnings)
servehttp://127.0.0.1:8765

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.