New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Logseq Answer Machine

by logseq in logseq/logseq

Answer user questions about the Logseq repository by researching source code, docs, tests, runtime behavior, and local tools.

AGPL-3.0Auto-check: warningsKnowledge Management

Install Logseq Answer Machine

The automated check flagged lines worth reading first. See the safety section below.

skills CLI
$ npx skills add logseq/logseq --skill logseq-answer-machine -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install logseq/logseq logseq-answer-machine --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/logseq/logseq.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/logseq-answer-machine .claude/skills/logseq-answer-machine && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
logseq-answer-machine
GitHub stars
45k
Token cost
~1.2k tokens
SKILL.md length
488 words
Files
2
Skills in repo
12
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Answer user questions about the Logseq repository by researching source code, docs, tests, runtime behavior, and local tools.

  • Works in 6 steps: Restate the question as the exact… → Read root AGENTS.md and any relevant… → Locate evidence with fast repo search → …
  • Codex needs to explain how Logseq works
  • SKILL.md covers Guardrails, Investigation Workflow, Runtime Experiments and Answer Format
  • Calls rg

What it does

Logseq Answer Machine is an agent skill from logseq/logseq. Answer user questions about the Logseq repository by researching source code, docs, tests, runtime behavior, and local tools. Use when Codex needs to explain how Logseq works, why behavior happens, where logic lives, how CLI/Desktop/Web flows interact, or what evidence supports an answer, without implementing features or fixing bugs.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Knowledge Management. The repository describes itself as: A privacy-first, open-source platform for knowledge management and collaboration. Download link: http://github.com/logseq/logseq/releases. roadmap: https://logseq.io/p/NX4mcggEV. The licence is AGPL-3.0.

When your agent uses it

  • Codex needs to explain how Logseq works
  • Why behavior happens
  • Where logic lives
  • How CLI/Desktop/Web flows interact

Example prompts

  • “/logseq-answer-machine”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Restate the question as the exact behavior, subsystem, or data flow to explain.
  2. Read root AGENTS.md and any relevant directory-specific AGENTS.md files for touched paths.
  3. Locate evidence with fast repo search
  4. Build a concise evidence map
  5. Run experiments only when static evidence is insufficient or the user asks for runtime confirmation.
  6. Answer in outline form with file and command references precise enough for another engineer to verify.

What it can do on your machine

Read from SKILL.md and the folder at commit 22a29b3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • rg

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Logseq Answer Machine loads about 1.2k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 488 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: warnings

The automated check found patterns that need a careful read before installing.

  • WarningMentions a credentials file (SSH keys, cloud or package-manager tokens)SKILL.md:43
    - **Web app behavior**: Use the `Chrome` skill when browser cookies/profile state or the web UI is needed.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from logseq/logseq at commit 22a29b3, republished under its AGPL-3.0 licence (© logseq). 488 words, ~1,157 tokens.

Download SKILL.mdSave it as .claude/skills/logseq-answer-machine/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
logseq-answer-machine
description
Answer user questions about the Logseq repository by researching source code, docs, tests, runtime behavior, and local tools. Use when Codex needs to explain how Logseq works, why behavior happens, where logic lives, how CLI/Desktop/Web flows interact, or what evidence supports an answer, without implementing features or fixing bugs.

Logseq Answer Machine

Use this skill to answer questions from the Logseq repo itself. Produce evidence-backed explanations, not product changes.

Guardrails

  • Do not implement features, fix bugs, refactor code, create migrations, or make permanent behavior changes while using this skill.
  • Default to read-only investigation: source search, file reading, docs, tests, command output, REPL probes, and UI observation.
  • If a question turns into an implementation or bugfix request, stop using this skill and switch to the appropriate implementation/debug workflow.
  • If any temporary edit is necessary for exploration, keep it minimal, explain why it is needed, avoid user data, and revert it after the question has been explored.
  • Revert every exploration-time modification before the final answer. Do not leave temporary logs, probes, config changes, generated debug files, or test edits in the worktree.
  • Respect all applicable AGENTS.md files before any file edit, including temporary logs.
  • Clearly separate observed facts, source-backed conclusions, runtime experiment results, and inference.

Investigation Workflow

  1. Restate the question as the exact behavior, subsystem, or data flow to explain.
  2. Read root AGENTS.md and any relevant directory-specific AGENTS.md files for touched paths.
  3. Locate evidence with fast repo search:
    • Use rg or rg --files for symbols, namespaces, routes, commands, UI labels, config keys, schema keywords, and tests.
    • Prefer primary repo evidence: source files, tests, docs, migrations, EDN config, package manifests, and scripts.
    • Use git history only when the question asks about intent, regression timing, or historical behavior.
  4. Build a concise evidence map:
    • owning namespace/file
    • caller/callee chain or data flow
    • relevant tests and fixtures
    • docs or agent-guide references
    • runtime surface: CLI, Desktop renderer, Electron main, db-worker-node, web app, server/worker, or mobile
  5. Run experiments only when static evidence is insufficient or the user asks for runtime confirmation.
  6. Answer in outline form with file and command references precise enough for another engineer to verify.
Show full SKILL.md (183 more words)Show less

Runtime Experiments

Choose the narrowest tool that can verify the claim.

  • CLI behavior: Load .agents/skills/logseq-cli/SKILL.md before running or interpreting logseq commands. Use disposable graphs or explicit user-approved graph paths for mutating commands.
  • Desktop, renderer, Electron, or db-worker-node internals: Load .agents/skills/logseq-repl/SKILL.md and use the correct REPL target for focused probes.
  • Web app behavior: Use the Chrome skill when browser cookies/profile state or the web UI is needed.
  • Desktop UI behavior: Use the computer-use skill when the local Desktop app window must be operated directly.
  • Temporary logging: Add only targeted logs when REPL/UI observation cannot expose the needed state. Revert all logging changes and re-check the diff before finalizing.

Record exact commands, REPL expressions, UI steps, and observed outputs when they materially support the answer. If a relevant experiment cannot run, state the blocker and do not present the claim as verified.

Answer Format

Produce the final answer as a detailed outline. Keep it proportional to the question, but include these sections when useful:

markdown
1. Short Answer
   - Direct conclusion in one or two bullets.

2. Evidence
   - `path/to/file.ext:line`: what this proves.
   - command or REPL probe: observed result.

3. How It Works
   - Step-by-step control flow, data flow, state transition, or runtime interaction.

4. Runtime Verification
   - What was tested through CLI, REPL, Chrome, or Desktop UI.
   - What could not be tested and why.
   - Whether any temporary modifications were made and confirmation that they were reverted.

5. Edge Cases and Open Questions
   - Important limitations, ambiguity, or repo areas not covered.

6. Practical Takeaways
   - Where to look next, which tests cover it, or what constraints matter.

Use the active conversation language for explanatory prose, while keeping code, identifiers, file paths, command names, and quoted repo text exact.

© logseq, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/logseq-answer-machine of logseq/logseq.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 22a29b3

Compare with similar skills

Logseq Answer Machine next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Logseq Answer Machine compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Logseq Answer Machine this skilllogseq/logseq45k—~1.2kAutomated safety check: WarnAGPL-3.0
Baoyu URL To Markdownsdyckjq-lab/llm-wiki-skill2.5k2 repos~3.2kAutomated safety check: PassNone
Obsidian CLIAtmosphere/atmosphere3.8k13 repos~795Automated safety check: PassApache-2.0
Karpathy LLM WikiAstro-Han/karpathy-llm-wiki2.4k—~3.6kAutomated safety check: PassMIT
Zlibrary To Notebooklmzstmfhy/zlibrary-to-notebooklm1.7k1 repos~968Automated safety check: PassMIT
Multi-Source to NotebookLM Processorjoeseesun/qiaomu-anything-to-notebooklm6.2k—~3.6kAutomated safety check: PassMIT

Similar skills

  • Baoyu URL To Markdown

    sdyckjq-lab/llm-wiki-skill

    Fetch any URL and convert to markdown using Chrome CDP. An agent skill from sdyckjq-lab/llm-wiki-skill.

    2.5k GitHub starsUsed in 2 repos~3.2k tokens
    Knowledge ManagementAuto-check passed

  • Obsidian CLI

    Atmosphere/atmosphere

    Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more.

    3.8k GitHub starsUsed in 13 repos~795 tokens
    Knowledge ManagementAuto-check passed

  • Karpathy LLM Wiki

    Astro-Han/karpathy-llm-wiki

    A skill your agent uses when building or maintaining a personal LLM-powered knowledge base.

    2.4k GitHub stars~3.6k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed

  • Zlibrary To Notebooklm

    zstmfhy/zlibrary-to-notebooklm

    自动从 Z-Library 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式，自动转换，一键创建知识库。

    1.7k GitHub starsUsed in 1 repo~968 tokens
    Knowledge ManagementAuto-check passed

  • Multi-Source to NotebookLM Processor

    joeseesun/qiaomu-anything-to-notebooklm

    Collects content from WeChat articles, web pages, YouTube, podcasts, documents and more, uploads it to NotebookLM and generates podcasts, slides or mind maps.

    6.2k GitHub stars~3.6k tokensUpdated 2 days ago
    Knowledge ManagementAuto-check passed

  • Soul

    aeonfun/soul.md

    Embody this digital identity. An agent skill from aeonfun/soul.md.

    686 GitHub starsUsed in 2 repos~1.1k tokens
    Knowledge ManagementAuto-check passed

More from logseq/logseq

All 12 skills in this repo

  • Logseq Review Workflow Eval

    logseq/logseq

    Compare two revisions of the Logseq logseq-review-workflow skill by running the same review prompt against isolated before and after skill snapshots, collecting both outputs, and producing a…

    45k GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Esm Cjs Risk Scan

    logseq/logseq

    Scan Logseq ClojureScript Node/Electron targets for npm module loading risks, especially ESM-only packages that may fail when loaded through js/require or shadow-cljs require-based shims.

    45k GitHub stars~3.3k tokensUpdated today
    Auto-check passed

  • Logseq Plugin SDK

    logseq/logseq

    Build, debug, or review Logseq plugins with the @logseq/libs SDK (TypeScript/JavaScript, iframe/shadow sandboxed).

    45k GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • Logseq CLI

    logseq/logseq

    Operate the current Logseq command-line interface to inspect or modify graphs, pages, blocks, tasks, tags, and properties; run Datascript queries; show page/block trees; manage graphs; and manage…

    45k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

  • Logseq Dependency Upgrade

    logseq/logseq

    Audit, plan, and refresh dependency upgrades for the Logseq repository by scanning every non-gitignored package.json, deps.edn, bb.edn and nbb.edn manifest, checking latest upstream versions…

    45k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Logseq I18n

    logseq/logseq

    Logseq i18n workflow for adding, renaming, reviewing, or editing translation keys and user-facing strings.

    45k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

Categories

Questions about Logseq Answer Machine

What does Logseq Answer Machine do?

Answer user questions about the Logseq repository by researching source code, docs, tests, runtime behavior, and local tools. Logseq Answer Machine is an agent skill from logseq/logseq. Answer user questions about the Logseq repository by researching source code, docs, tests, runtime behavior, and local tools.

When should I use Logseq Answer Machine?

Logseq Answer Machine fits situations like: Codex needs to explain how Logseq works; why behavior happens; where logic lives; how CLI/Desktop/Web flows interact.

How do I install Logseq Answer Machine in Claude Code?

Run `npx skills add logseq/logseq --skill logseq-answer-machine -a claude-code`. Or copy the skill folder (.agents/skills/logseq-answer-machine in logseq/logseq) into .claude/skills/logseq-answer-machine in your project. Claude Code loads it when a task matches its description.

How do I install Logseq Answer Machine in Codex?

Run `npx skills add logseq/logseq --skill logseq-answer-machine -a codex`. Or copy the skill folder (.agents/skills/logseq-answer-machine in logseq/logseq) into .agents/skills/logseq-answer-machine in your project. Codex loads it when a task matches its description.

Can I use Logseq Answer Machine in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add logseq/logseq --skill logseq-answer-machine -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/logseq-answer-machine, .gemini/skills/logseq-answer-machine, .github/skills/logseq-answer-machine and .opencode/skills/logseq-answer-machine in your project.

What does Logseq Answer Machine need to run?

Going by SKILL.md and its folder, Logseq Answer Machine needs the command-line tools its instructions call (rg).

Does Logseq Answer Machine access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Logseq Answer Machine safe to install?

Our automated static check of SKILL.md flagged 1 warning(s): mentions a credentials file (ssh keys, cloud or package-manager tokens). Read the flagged lines before installing; the check is not a guarantee either way.

What licence does Logseq Answer Machine use?

Logseq Answer Machine is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Logseq Answer Machine use?

About 1.2k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Logseq Answer Machine?

Skills that share tags, products or a category with Logseq Answer Machine: Baoyu URL To Markdown (sdyckjq-lab/llm-wiki-skill, 2.5k stars), Obsidian CLI (Atmosphere/atmosphere, 3.8k stars), Karpathy LLM Wiki (Astro-Han/karpathy-llm-wiki, 2.4k stars) and Zlibrary To Notebooklm (zstmfhy/zlibrary-to-notebooklm, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Logseq Answer Machine?

logseq (a GitHub organization) maintains it in logseq/logseq, which has 45,158 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 7, 2026.

Source: logseq/logseq on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.