agentleFS
Sign inStart free
SkinnnyJaySkinnnyJay/wiki-llm/skills/wiki-query/SKILL.md

wiki-query

Skill0 starsChanged 4 months agoMITView on GitHub

Answers questions using llm-wiki/wiki pages with citations. Use when the user asks about vault content or synthesized knowledge.

41 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use wiki-capture, wiki-update and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • jehrhardtSkill

    wiki-capture

    Quickly capture raw thoughts, links, images, or notes to today's Obsidian daily note from anywhere in Pi. Use when the user wants to jot something down for later wiki processing.

    Also in 6 projects that use this

  • bozhouDevSkill

    wiki-update

    Use when revising existing wiki pages because knowledge has changed, a new piece of information updates or contradicts existing content, or the user wants to directly edit wiki content with LLM assistance.

    Also in 9 projects that use this

  • bozhouDevSkill

    wiki-init

    Use when bootstrapping a new personal wiki for any knowledge domain — research, codebase documentation, reading notes, competitive analysis, or any long-term knowledge accumulation project.

    Also in 7 projects that use this

  • justvinhhereSkill

    wiki-review

    Use when the user runs /review, says "show pending changes", "what's uncommitted", or wants an audit of uncommitted wiki edits before they land in history. Narrates uncommitted changes, flags structural issues scoped to those changes, and commits them with a conventional subject. Fully automatic.

    Also in 8 projects that use this

  • Ivy-Chen1999Skill

    claude-history-ingest

    Ingest Claude Code conversation history into the Obsidian wiki. Use this skill when the user wants to mine their past Claude conversations for knowledge, import their ~/.claude folder, extract insights from previous coding sessions, or says things like "process my Claude history", "add my conversations to the wiki", "what have I discussed with Claude before". Also triggers when the user mentions their .claude folder, Claude projects, session data, past conversation logs, local-agent-mode sessions, or audit logs.

    Also in 3 projects that use this

  • Ivy-Chen1999Skill

    graph-colorize

    Color-code the Obsidian graph view by rewriting `.obsidian/graph.json` colorGroups. Use this skill when the user says "color my graph", "color code obsidian", "colorize the graph", "color the graph by tag", "color by category", "highlight visibility in graph", "make the graph colorful", "distinguish tags in graph", or wants nodes in Obsidian's graph view tinted by tag, folder, or visibility. Generates a `colorGroups` array from the vault's actual tags/categories and merges it into the existing graph.json without clobbering other graph settings. Always backs up first.

    Also in 3 projects that use this

  • +3 more from Ivy-Chen1999

The file

We split this skill into the rules it gives an agent

12 rules. 0 are common, 4 are distinctive, and 8 are very specific to this project.

  • 0

    Common

    Most of the 33 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 8

    Very specific

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

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

    Read wiki/index.md to orient.

    line 16
  2. Very specific:

    Check config.json for mcp.search_backend (fts5 / grep / chromadb / hybrid) and knowledge_graph.enabled to decide which tools to use.

    line 17
  3. Very specific:

    If the question is vague, narrow it or list candidate pages from wiki/index.md.

    line 25
  4. Distinctive:

    If the answer is not in the wiki, say so and offer wiki-research or wiki-fetch instead of inventing sources.

    line 26
  5. Very specific:

    If memory.enabled is true, optionally run llm-wiki memory recall "<terms>" for past session notes under raw/memory/ before giving up.

    line 27
  6. Very specific:

    Search shortcut: When the vault is large or the question targets specific terms, use the CLI search for BM25-ranked results (see reference …

    line 28
  7. Very specific:

    If knowledge_graph.enabled is true, run llm-wiki kg query "<entity>" for structured relationships — see reference § "CLI quick reference".

    line 32
  8. Distinctive:

    Prefer quoting short spans.

    line 37
  9. Distinctive:

    When the knowledge graph provides structured facts, cite both the KG triple and the source wiki page.

    line 38
  10. Very specific:

    If the answer should live in the vault, offer to save as a new wiki/ page (linked from the index) or under outputs/ as a draft to verify …

    line 42
  11. Distinctive:

    If nothing relevant exists in the wiki, you state the gap and suggest wiki-research / wiki-fetch / wiki-ingest as next steps.

    line 47
  12. Very specific:

    If you created or updated a page, wiki/index.md and wiki/log.md are updated when appropriate.

    line 48

“Common” is measured: kept by at least 6 in 10 of the 33 edited versions of this file we could read. “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 query — Reader

Answer questions from curated wiki pages with inline citations to wiki/ paths. Use when the user wants facts, summaries, or navigation help inside the vault (not when they need new research from the web).

Pre-flight

  1. Confirm llm-wiki/config.json exists (vault root). If missing, offer wiki-setup.
  2. Read wiki/index.md to orient; open the most relevant wiki/**/*.md files for the question.
  3. Check config.json for mcp.search_backend (fts5 / grep / chromadb / hybrid) and knowledge_graph.enabled to decide which tools to use. hybrid needs Chroma installed; if unsure, read wiki_status / skills/references/mcp-and-kg.md for fallbacks.

Search backend API, KG CLI, and Python examples: skills/references/mcp-and-kg.md

Steps

Step 1 — Scope the question

  • If the question is vague, narrow it or list candidate pages from wiki/index.md.
  • If the answer is not in the wiki, say so and offer wiki-research or wiki-fetch instead of inventing sources.
  • If memory.enabled is true, optionally run llm-wiki memory recall "<terms>" for past session notes under raw/memory/ before giving up.
  • Search shortcut: When the vault is large or the question targets specific terms, use the CLI search for BM25-ranked results (see reference § "Search"). Prefer CLI locally; fall back to MCP wiki_search only when shell access is unavailable.

Step 1b — Query the knowledge graph (when enabled)

If knowledge_graph.enabled is true, run llm-wiki kg query "<entity>" for structured relationships — see reference § "CLI quick reference".

Step 2 — Answer with citations

  • Cite paths inline, e.g. `wiki/topics/foo.md` or [[Topic]] when listing sources.
  • Prefer quoting short spans; for long passages, point to the file and section.
  • When the knowledge graph provides structured facts, cite both the KG triple and the source wiki page.

Step 3 — Optional persistence

  • If the answer should live in the vault, offer to save as a new wiki/ page (linked from the index) or under outputs/ as a draft to verify before promoting to wiki.

Done looks like

  • The user’s question is answered using only (or primarily) wiki/ content, with at least one citation per non-obvious claim.
  • If nothing relevant exists in the wiki, you state the gap and suggest wiki-research / wiki-fetch / wiki-ingest as next steps.
  • If you created or updated a page, wiki/index.md and wiki/log.md are updated when appropriate.

Artifacts

ReadsWrites
wiki/index.md, wiki/**/*.mdOptional new wiki/**/*.md or outputs/**/*.md

Downstream: wiki-maintainer if many pages change; wiki-lint for a health pass.

Related skills

  • wiki-research — add new sources and merge into wiki when the vault lacks an answer.
  • wiki-fetch — quick single-URL ingest into raw/ without full research orchestration.
  • wiki-ingest / wiki-maintainer — merge curated content after new material lands in raw/.
  • wiki-lint — audit wiki coherence after bulk edits.
  • wiki-session-memory — recall per-chat notes in raw/memory/ when enabled.

Smoke check

  • CLI: llm-wiki validate from the vault root.
  • Prompt: Invoke this skill with a sample question; confirm answers cite paths under wiki/.

Optional: skills/references/context-persona.md; vault display name: persona.name in llm-wiki/config.json (default Gennie).

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.

Check your setup, free