Skip to content
SkillModel-led6,617 tokens in use

wiki-query

Answers questions from a compiled Obsidian wiki with cited pages, multi-hop link paths, graph-structure queries and a challenge mode, without changing any page.

3,792 stars on the repository MIT LicenseAr9av/obsidian-wiki · skills/wiki-query
pip install obsidian-wiki
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing wiki-query costs

88tokens idle
6,617tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetectedwrites filesdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter8/15
  • Structure25/25
  • Examples15/15
  • Output15/15
  • Size13/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 55
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 312

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity28
  • Momentum40

wiki-query is the read-only retrieval skill of the obsidian-wiki set. It answers from pre-synthesized pages, starting with a cheap graph query and the index, and only opens page sections or whole pages when it must.

It supports factual, relationship, path, synthesis, gap and challenge questions, annotates stale, disputed and archived citations, and ends every answer with a retrieval report of what it saw, read and dropped.

What You Get

  • An answer with wikilink citations and a list of pages consulted
  • A gaps line that says what the wiki does not cover
  • A retrieval line with candidates seen, read and dropped
  • Typed-edge paths between two concepts with hop counts and weak-link flags
  • Trust annotations on stale, disputed, verified and archived pages
  • A challenge answer that leads with the vault’s own counter-evidence

Common Use Cases

  • Asking what your notes say about a topic with cited pages
  • Finding how two concepts connect when no page links them directly
  • Checking your own past decisions before committing to a new plan

What Makes It Unique

It is built to spend as little reading as possible, using a graph index, frontmatter greps and section reads before full pages, and it reports what it left unread. Structural questions get exact computed answers, event-time frontmatter keeps superseded pages from passing as current, and challenge mode argues against the user using earlier decisions and failures in the vault. Requests to save or change anything are routed to other skills.

Under The Hood

The skill is instructions for the agent. It reads pages and runs the obsidian-wiki command line tool for graph queries, path analysis and one log entry per query, which is its only write. When a QMD collection is configured it queries it through an MCP tool or the qmd command. It does not fetch web pages or call remote APIs, and it tells the agent never to edit pages, the index, the hot file or the manifest, even when a change looks helpful.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers