agentleFS
nathanadaynathanaday/claude-atlas/skills/wiki-query/SKILL.md

wiki-query

Skill1 starsChanged 37 days agoMITView on GitHub

Answer a question from the wiki, with citations, and say what the wiki does not cover. Reads only. Use for what does the wiki say, explain from my notes, find in the wiki, what do we know about X, which repositories use Y. Keeping the answer is wiki-save; a reading list of the documents on a subject is wiki-checkout.

41 other projects use a version of this, 1 of them edited.

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

  • 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

  • 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

  • +5 more from Ivy-Chen1999

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Call search. A document must hold every tag, or a tag below it.

    line 21
  2. Distinctive:

    When the user wants to browse a tag rather than ask, link the tag's page (its overview topic or repository page): it lists the documents …

    line 28
  3. Distinctive:

    Read the best documents with Read.

    line 30

“Common” is measured: kept by at least 6 in 10 of the 31 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

The wiki holds what the vault knows, each claim cited. This skill turns a question into a search with tags, reads the documents that answer it, and answers with a citation for each claim, keeping the wiki's claims apart from your own reasoning.

Tools: search, context, and Read.

Procedure

  1. Turn the question into a query. Words that name tags in the vocabulary (the tag list in the session-start context, or vault) become tags: "my cs513 self-driving project" → tags: [school/cs513, self-driving, project]. The rest is text. Add types or kinds when the question asks for one ("which policies…" → types: [topic], kinds: [policy]).
  2. Call search. A document must hold every tag, or a tag below it. When the hits are many, read facets.tags and add the tag that splits them; facets.types and facets.status narrow the same way. When there are no hits, drop the least certain tag and search again. Say which tags you used.
  3. For a question about repositories ("which services use MQTT"), call context with the tags, or with repository for one repository. Read the tag pages' ## Context in pages, and the repositories and policies it lists. When the user wants to browse a tag rather than ask, link the tag's page (its overview topic or repository page): it lists the documents under the tag.
  4. Read the best documents with Read. Follow a link one hop when the answer needs it.
  5. Answer. Cite each claim with its document ([[Topic]]), and through the topic its source. Keep the wiki's claims apart from your own reasoning, and mark the reasoning as yours.
  6. Say what the wiki lacks, when it lacks something the question needs. Do not fill the gap from general knowledge without saying so.

Gate

None. The skill writes nothing.

Hand off

wiki-save when the answer is new synthesis the user wants kept. wiki-checkout when the user wants to read the material itself: a reading list and copies to mark up. almagest when the question turns into work in a repository.

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.