agentleFS
agamaroraagamarora/second-brain/.claude/skills/query/SKILL.md

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

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.
  • duckdbSkill

    attach-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

  • carlopiSkill

    install-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

  • carlopiSkill

    read-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

  • seongjaeryuSkill

    save

    Complete and save your current thinking to Bindly

    Also in 4 projects that use this

  • AnthropicSkill

    start

    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

  • MicrosoftSkill

    doctor

    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

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
  1. Distinctive:

    Never answer from page titles or grep snippets alone.

    line 49
  2. Distinctive:

    Write an answer of ≤6 sentences (shorter is better).

    line 53
  3. Distinctive:

    Do not hallucinate: If no source supports a claim, omit it or say "brain has no record of X."

    line 61
  4. Distinctive:

    Preserve disagreement: If sources contradict, say so — don't pick one.

    line 63
  5. Distinctive:

    If the synthesis produces a novel connection not present in any single source:

    line 81
  6. Distinctive:

    Write the synthesized answer as the page body

    line 90
  7. Very specific:

    Call /absorb on each source used

    line 91

“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

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:

  1. decisions/*.md — explicit judgment calls with context
  2. wiki/people/*.md — if question mentions a person
  3. wiki/concepts/*.md — for topic questions
  4. wiki/{products,partners,competitors,org}/*.md — entity-specific
  5. journal/NOW.md + last 10 rows of log.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: N

6. 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:

  1. Call /new-page concept <slug>
  2. Write the synthesized answer as the page body
  3. Call /absorb on each source used
  4. 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

  • /query does not modify wiki pages unless the user opts in at step 6.
  • /query does not replace human judgment. It retrieves and synthesizes; the user decides.
  • /query is not RAG. No embeddings, no vector DB. Grep + read is enough at personal-brain scale (hundreds to low-thousands of pages).

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.