agentleFS
kfchoukfchou/wiki-skills/skills/wiki-query/SKILL.md

wiki-query

Skill189 starsChanged 4 months agoMITView on GitHub

Use when asking a question against a personal wiki built with wiki-init and wiki-ingest. Do not answer from general knowledge — always read the wiki pages first.

41 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use wiki-capture, wiki-setup 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

  • Ivy-Chen1999Skill

    wiki-setup

    Initialize a new Obsidian wiki vault with the correct structure, special files, and configuration. Use this skill when the user wants to set up a new wiki from scratch, initialize the vault structure, create the .env file, or says things like "set up my wiki", "initialize obsidian", "create a new vault", "get started with the wiki". Also use when the user needs to reconfigure their existing vault or fix a broken setup.

    Also in 5 projects that use this

  • Ivy-Chen1999Skill

    wiki-research

    Autonomously research a topic via multi-round web search, synthesize findings, and file structured results into the Obsidian wiki. Use this skill when the user says "/wiki-research [topic]", "research X", "find everything about Y", "do a deep dive on Z", "autonomous research on X", or wants comprehensive, web-sourced knowledge on a topic filed directly into their wiki.

    Also in 4 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

  • nathanadaySkill

    almagest

    Orient in the Almagest vault, say what waits for the user, do the work a request asks in a linked repository, and route any other request to the skill that owns it. Use for /almagest, what is going on, status, what waits for me, where do I work on X, work on X, fix this, implement, build, note this, remember to, publish my journal, what is in my journals, and any request when the right skill is not clear. Keeping part of this conversation is wiki-save; files to learn from are wiki-ingest.

    Also in 3 projects that use this

  • +5 more from Ivy-Chen1999

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 33 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask a question. Read the wiki.

    line 8
  2. Very specific:

    Read the identified pages in full.

    line 27
  3. Distinctive:

    Write a response that:

    line 31
  4. Very specific:

    Write the page with full frontmatter: title, category: Analyses (or the wiki's equivalent), summary (one-line), tags: [query, analysis], …

    line 51

“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

Ask a question. Read the wiki. Synthesize with citations. Offer to file the answer back.

Pre-condition

Find SCHEMA.md (search from cwd upward, or ~/wikis/). If not found, tell the user to run wiki-init first. Read it to get wiki root path and cross-reference convention.

Link style. Read link_style: from SCHEMA.md. If the field is missing or <wiki-root>/config/link-style.md does not exist, default to obsidian ([[slug]]). Otherwise, read <wiki-root>/config/link-style.md for the emit and parse rules. Follow cross-references in pages using the ## Parse rule. When you write the answer back as a wiki page (step 4), emit citations and cross-references using the ## Emit rule.

Process

1. Read wiki/index.md first

Regenerate the index so it reflects the current pages — python bin/generate-index.py — then scan the full index to identify which pages are likely relevant. Do NOT answer from general knowledge — the wiki is the source of truth here, even if you think you know the answer.

2. Read relevant pages

Read the identified pages in full. Follow one level of cross-reference links (matched via the ## Parse rule from config/link-style.md) if they point to pages that seem relevant to the question.

3. Synthesize the answer

Write a response that:

  • Is grounded in the wiki pages you read
  • Cites inline using a cross-reference (in the wiki's link_style) for every claim sourced from a specific page
  • Notes agreements and disagreements between pages
  • Flags gaps: "The wiki has no page on X" or "<page slug> doesn't cover Y yet"
  • Suggests follow-up sources to ingest or questions to investigate

Format for the question type:

  • Factual → prose with citations
  • Comparison → table
  • How-it-works → numbered steps
  • What-do-we-know-about-X → structured summary with open questions

4. Always offer to save

After answering, say:

"Worth saving as wiki/pages/<suggested-slug>.md?"

If yes:

  • Write the page with full frontmatter: title, category: Analyses (or the wiki's equivalent), summary (one-line), tags: [query, analysis], sources: [all cited slugs], created: <today>, updated: <today>
  • Regenerate the index — python bin/generate-index.py — do not hand-edit index.md
  • Record the operation (per SCHEMA's Operation Log & Commit Convention):
    • Git wiki: suggest a commit (default docs: for a saved query, plus the trailer); commit on confirmation.
      docs: add analysis — <question summary>
      
      Wiki-Op: query
    • Non-git wiki: append to wiki/log.md:
      ## [<today>] query | <question summary>
      Filed as: <slug reference to the new slug, in the wiki's link_style>

If no:

  • Git wiki: nothing changed, so there is nothing to commit — the query is not logged.
  • Non-git wiki: append to wiki/log.md:
    ## [<today>] query | <question summary>
    Not filed.

Common Mistakes

  • Answering from memory — Always read the wiki pages. The wiki may contradict what you think you know, and that contradiction is valuable signal.
  • Skipping the save offer — Good query answers compound the wiki's value. Always offer.
  • No citations — Every factual claim should trace back to a slug reference (in the wiki's link_style).

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.