wiki-query
Skill1 starsChanged 7 months agoMITView on GitHub
Use when the user runs /query <question>, says "what do we know about X", "summarize our view on Y", "compare A vs B in the wiki", "search the wiki for Z", "which pages link to [[W]]", "when did we first mention Q", or asks any question answerable from wiki content. Classifies the question as lookup or synthesis; runs four internal searches (content / frontmatter / graph / git-history); answers with citations. Synthesis answers auto-file as query pages with a query(<slug>) commit; lookups answer in chat only.
We split this skill into the rules it gives an agent
3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 31 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
If the raw question text contains "don't file" or "just answer" (case-insensitive, substring match), force skip regardless of …
- Very specific: line 47
If the wiki has no relevant content, output Wiki has no material on this.
- Very specific: line 51
If query.dedupe_against_queries is true: git grep -l -i "<question-keywords>" -- 'wiki/queries//*.md'.
“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.
Files
wiki-query
Answers questions against the current wiki and its git history. Never fetches the web.
Refuse conditions
- No
.llm-wiki.yamlin CWD or ancestors. .llm-wiki.yaml:schema_version != 1.- Synthesis filing would require a dirty working tree to merge — caller must
/reviewfirst.
Workflow
1. Classify
| Kind | Signal | Filing |
| Lookup | Asks for pointers / list / counts. "which pages link to X", "list pages tagged Y", "when did Z first appear". | Skip. |
| Synthesis | Asks for comparison, summary, explanation, cross-page connection. Answer is new prose. | File. |
Ambiguous → synthesis (filing is cheap, reversible via git revert).
If the raw question text contains "don't file" or "just answer" (case-insensitive, substring match), force skip regardless of classification.
2. Candidate discovery (parallel)
- Content.
git grep -n -i "<keywords>" -- 'wiki/**/*.md'. Keywords: question tokens minus stopwords. - Frontmatter. Parse YAML of all wiki pages; filter by
type,tags,statuswhere the question names them. - Graph. For every proper-noun in the question,
git grep -l "\[\[<slug>\]\]" -- 'wiki/**/*.md'. - Historical (only if the question contains
when,first,last,recently,over time).git log -S "<phrase>" --oneline -- 'wiki/**/*.md'.
3. Rank and read
Rank union: exact-title-match > frontmatter-tag-match > backlink-count > content-frequency. Read top query.top_k_candidates pages in full. If fewer candidates, read all.
4. Synthesize
Inline citations:
(see [[page-slug]])for general support.(see [[page-slug]] ¶ "phrase")for passage-level.(introduced in <sha>, ingest(<slug>))for temporal claims.
If the wiki has no relevant content, output Wiki has no material on this. Try /ingest <source>. and stop — no file written.
5. Dedupe against existing query pages
If query.dedupe_against_queries is true: git grep -l -i "<question-keywords>" -- 'wiki/queries/**/*.md'. If an existing query page answers the same question (same question: frontmatter or >80% keyword overlap with its answer_summary:), output Already answered at [[queries/<slug>]] and stop.
6. File, if synthesis
- Slug: question text → stopword strip → general slug rule (
skills/wiki-ingest/reference.md). - Copy
templates/query.md, fill frontmatter:title,question,asked: <today>,answer_summary,cites_pages,sources(union of cited pages'sources). - Append entry to
index.mdunder## Queries.
7. Commit
git add wiki/queries/<slug>.md index.md
git commit -m "query(<slug>): file synthesized answer"Output
- Lookup: the answer list.
- Synthesis: the answer body +
Filed as [[queries/<slug>]] in commit <short-sha>. - Skip (dedupe or explicit): pointer line only.
Other versions38 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 38
- AgriciDaniel/claude-obsidian★ 16ksame name
- rohitg00/pro-workflow★ 2.9ksame name
- kfchou/wiki-skills★ 183same name
- bozhouDev/bozhou-skills★ 78same name
- vanillaflava/llm-wiki-skills★ 65same name
- cookyman74/llmwiki-harness★ 34same name
- Ivy-Chen1999/llm-wiki-kit★ 21same name
- CarbeneAI/Forge★ 9same name
- CodePhobiia/claude-roblox-game-studio★ 9same name
- crabin/llm-wiki★ 8same name
28 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use wiki-capture, wiki-update and 10 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.
jehrhardtSkillwiki-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 5 projects that use this
bozhouDevSkillwiki-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 8 projects that use this
nathanadaySkillalmagest
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
nathanadaySkillalmagest-onboard
Make a new Almagest vault: ask its name, its folder, and how freely to tag, then link its first repositories. Use for set up almagest, new vault, start a vault here, onboard, make this folder a vault. Linking a repository to a vault that exists is repo-link.
Also in 3 projects that use this
Ivy-Chen1999Skillwiki-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 3 projects that use this
- +7 more from nathanaday
In this repository6 other files it gives its agents.
- stubs/CLAUDE.mdCLAUDE.md
- wiki-bootstrapSkill
- wiki-historySkill
- wiki-ingestSkill
- wiki-lintSkill
- wiki-reviewSkill
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
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.

