query
Skill2 starsChanged 7 months agoMITView on GitHub
Ask a natural-language question of the brain. Reads wiki/, decisions/, and log.md, synthesizes an answer grounded in accumulated knowledge, cites every claim. Optionally files the synthesis as a new wiki concept page. Use when the user asks a question that should be answered from what they've already ingested.
38 other projects use a version of this.
Adopted by
Most recently taken up by
- hydra-db/hydradb-claude-codetheir own version, first seen Nov 8, 2026
- justmytwospence/strava-mcptheir own version, first seen Nov 8, 2026
- levi-qiao/obsidian-llm-wikitheir own version, first seen Nov 8, 2026
- prdlk/skillstheir own version, first seen Nov 1, 2026
- honeydew-ai/honeydew-ai-coding-agents-pluginstheir own version, first seen Nov 1, 2026
- aibtcdev/skillstheir own version, first seen Oct 26, 2026
Used with
Projects with it also use attach-db, install-duckdb and 7 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.
duckdbSkillattach-db
Attach a DuckDB database file for use with /duckdb-skills:query. Explores the schema (tables, columns, row counts) and writes a SQL state file so subsequent queries can restore this session automatically via duckdb -init.
Also in 3 projects that use this
carlopiSkillinstall-duckdb
Install or update DuckDB extensions. Each argument is either a plain extension name (installs from core) or name@repo (e.g. magic@community). Pass --update to update extensions instead of installing.
Also in 3 projects that use this
carlopiSkillread-file
Read and explore any data file (CSV, JSON, Parquet, Avro, Excel, spatial, …) by filename only — resolves the path automatically. Uses DuckDB + the magic extension for format auto-detection. Installs magic if needed.
Also in 4 projects that use this
seongjaeryuSkillsave
Complete and save your current thinking to Bindly
Also in 4 projects that use this
AnthropicSkillstart
Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.
Also in 4 projects that use this
MicrosoftSkilldoctor
Diagnose an Amplifier CLI environment through the CLI doctor agent. USE WHEN a user requests CLI runtime, settings or missing-capability inspection. DO NOT USE for project bugs or other hosts.
Also in 3 projects that use this
Other versions38 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 38
- garrytan/gbrain★ 32ksame name
- facebookincubator/velox★ 4.3ksame name
- jason-effi-lab/karpathy-llm-wiki-vault★ 718same name
- duckdb/duckdb-skills★ 598same name
- ArtemXTech/claude-code-obsidian-starter★ 225same name
- HurricaHjz/SecondSelf★ 156same name
- romarayt/raytsystem-public-os★ 140same name
- HurricaHjz/second-yourself★ 105same name
- StarRocks/starrocks-debug-skills★ 77same name
- MetamusicX/zissa-wiki★ 58same 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.
In this repository12 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- absorbSkill
- captureSkill
- deep-syncSkill
- extract-entitiesSkill
- helpSkill
- ingestSkill
- lintSkill
- new-pageSkill
- orientSkill
- publish-contextSkill
- quick-syncSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 31 edited versions we read keep these.
6
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
- Distinctive: line 49
Never answer from page titles or grep snippets alone.
- Distinctive: line 53
Write an answer of ≤6 sentences (shorter is better).
- Distinctive: line 61
Do not hallucinate: If no source supports a claim, omit it or say "brain has no record of X."
- Distinctive: line 63
Preserve disagreement: If sources contradict, say so — don't pick one.
- Distinctive: line 81
If the synthesis produces a novel connection not present in any single source:
- Distinctive: line 90
Write the synthesized answer as the page body
- Very specific: line 91
Call /absorb on each source used
“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
Answer questions from the brain. Cite everything. Never hallucinate.
Usage
/query "<question>"Examples:
/query "what did I decide about pricing?"
/query "what does Ravi think about platform vs tool?"
/query "who has the most unresolved threads right now?"
/query "summarize everything I know about Meridian"Steps
1. Parse the question
Identify:
- Keywords — content terms for grep
- Named entities — people, products, partners, concepts with existing pages
- Intent — retrieve facts, summarize, compare, trace a decision chain
2. Search the brain
Grep in order of priority:
decisions/*.md— explicit judgment calls with contextwiki/people/*.md— if question mentions a personwiki/concepts/*.md— for topic questionswiki/{products,partners,competitors,org}/*.md— entity-specificjournal/NOW.md+ last 10 rows oflog.md— for "right now" questions
Rank hits by:
- Named-entity match > keyword match
- Recency of last enrichment (newer wins on ties)
- Frequency across sources
3. Read top 3-8 pages in full
Never answer from page titles or grep snippets alone. Read full pages before synthesizing.
4. Synthesize
Write an answer of ≤6 sentences (shorter is better). Every factual claim cites its source inline:
Ravi favors platform-shaped architecture [[2026-04-18-strategy-offsite-notes]], but agreed
to tool-first at the offsite [[decisions/2026-04-18-tool-first-platform-at-18-months]].Rules:
- Do not hallucinate. If no source supports a claim, omit it or say "brain has no record of X."
- Quote exactly where useful. Short verbatim quotes from sources are fine, marked with quotes.
- Preserve disagreement. If sources contradict, say so — don't pick one.
- Link, don't summarize at length. Point the user at the page for depth.
5. Output format
Answer: <≤6 sentences with inline [[source]] citations>
Sources consulted:
- wiki/people/ravi.md — <one-line why relevant>
- decisions/2026-04-18-<slug>.md — <one-line why relevant>
- ... (up to 8)
Pages searched but not used: N6. Offer to file (opt-in)
If the synthesis produces a novel connection not present in any single source:
This answer synthesizes knowledge from N sources into a new framing: "<one-line>".
File this as wiki/concepts/<slug>.md? [y/n]On yes:
- Call
/new-page concept <slug> - Write the synthesized answer as the page body
- Call
/absorbon each source used - Append to
log.md:## [YYYY-MM-DD] query-filed: <slug>
On no: return to prompt. Nothing written.
Failure modes
- No matching sources → Return: "Brain has no knowledge about
<topic>. Ingest sources first, then re-query." - Question too vague → Return: "Question is ambiguous. Narrow it: are you asking about [option A] or [option B]?"
- Grep returns >50 files → Too broad. Ask user to constrain to a time range, entity, or folder.
- Conflicting sources → Surface both claims in the answer. Do not silently pick one.
Non-goals
/querydoes not modify wiki pages unless the user opts in at step 6./querydoes not replace human judgment. It retrieves and synthesizes; the user decides./queryis not RAG. No embeddings, no vector DB. Grep + read is enough at personal-brain scale (hundreds to low-thousands of pages).
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.

