AGENT SKILL

brain-status

Show a dashboard of all projects in the Claude Brain graph, or graph analytics. Dashboard triggers: "brain status", "show projects", "show brain", "what's in my brain", "project dashboard", "brain overview", "list projects", "summary". Analytics triggers: "brain stats", "graph analytics", "graph activity over time". Don't fire for loads (use brain-load) or saves (use brain-save).

适用职业数据分析师
使用场景分析与可视化
License 许可
MIT
最近更新
2026-11-10
Stars
★ 18
Forks
5

01 前言 Front Matter

name
brain-status
description
Show a dashboard of all projects in the Claude Brain graph, or graph analytics. Dashboard triggers: "brain status", "show projects", "show brain", "what's in my brain", "project dashboard", "brain overview", "list projects", "summary". Analytics triggers: "brain stats", "graph analytics", "graph activity over time". Don't fire for loads (use brain-load) or saves (use brain-save).

02 资源文件 1

03 SKILL.md 正文

Brain Status

Running the helper

  • Bash: sh "<this skill's base directory>/../_shared/bin/brain" <command> …
  • PowerShell-only Windows: & "$(Split-Path (Split-Path (Get-Command git).Source))\bin\bash.exe" "<base>/../_shared/bin/brain" <command> …
  • Neither works: stop and say "logseq-brain needs Git for Windows (Git Bash) — https://git-scm.com/download/win".
  • In Cowork, always pass --graph <connected folder>. Elsewhere pass --graph only when the graph is not configured. It may go anywhere on the line. On exit 2 with graph not resolved, follow skills/_shared/path-resolution.md, then pass --graph.
  • Put text arguments in single quotes; a ' inside becomes '\''. In double quotes the shell runs backticks and expands $.
  • Exit 0 clean, 1 findings (act on them), 2 error (act on its reason; don't retry blindly). Quote every coverage: line. Never recompute a figure it printed. Its graph: line is the folder for your own Read, Edit and Write calls.

Run brain info once first. For "brain stats", follow references/analytics.md instead of the dashboard.

Dashboard

  1. brain status: a TSV row per project and task page, then a counts line. The columns are page type status last-updated digest-updated drift staleness focus next open. A page with no property block is listed as no properties — run brain-doctor.
  2. Projects are the Projects/ rows whose type is project. Leave other types out of the list and the counts.
  3. Phrase staleness per skills/_shared/staleness.md. When drift is over 30, flag the row, and give the count once.
  4. No digest (digest-updated is -), one page at a time:
    • "Currently:": the first bullet of brain read <page> 'Current Plan' --max 8192. Over the cap, say "Current Plan is N KB — not read".
    • Latest activity: brain tail <page> 'Session Log' --entries 1 --max 2048.
    • End with "<N> projects have no digest — run brain-doctor to backfill".
  5. Cross-project decisions: brain tail Decisions 'Decision Log' --entries 10 --max 4096. Keep those from the last 30 days.
  6. Meta date: Read pages/Meta.md with limit 5, for last-updated::.
  7. Tasks: list active and blocked tasks by ID (with focus). Collapse done tasks into "N done". List tasks with no status as "legacy — run brain-doctor to backfill".
  8. Present, per project: name, status, staleness, drift, focus, open. Then tasks, decisions and totals. With no projects: "Your brain is empty. Use 'init brain project [name]' to add your first project."
  9. brain activity 'viewed dashboard'.

04 同仓库更多 Skills

jame581
jame581/LogseqBrain

brain-save

Save session context, decisions, progress, and plans to the Claude Brain Logseq graph. Triggers: "save to brain", "save this", "remember this", "store this decision", "log this", "save progress", "before I quit", "wrap up". Don't fire for read operations (use brain-load) or status checks (use brain-status).

★ 18
jame581
jame581/LogseqBrain

brain-load

Load project context from the Claude Brain Logseq graph into the current session. Triggers: "load brain", "load <project>", "resume <project>", "continue work on <project>", "what do we know about <topic>". Don't fire for write operations (use brain-save), generic questions about Logseq itself, or "open <file>" / "switch to <branch>" requests that mean opening files or switching git branches rather than loading project memory.

★ 18
jame581
jame581/LogseqBrain

brain-init

Set up the Claude Brain Logseq graph (first-time) or add a new project page. Triggers: "init brain", "setup brain", "init brain project <name>", "add project to brain". Don't fire for loads, saves, or status checks — those are handled by brain-load, brain-save, and brain-status.

★ 18
jame581
jame581/LogseqBrain

brain-doctor

Lint and repair the Claude Brain Logseq graph — find and fix format violations that create phantom pages or broken macros. Triggers: "brain doctor", "lint brain", "check brain health", "clean up brain", "fix brain", "graph hygiene", "why are there empty pages", "find broken pages", "backfill digests", "rebuild digest for <project>". Don't fire for loads (use brain-load), saves (use brain-save), status/analytics (use brain-status), or first-time setup (use brain-init).

★ 18
jame581
jame581/LogseqBrain

release

Cut a logseq-brain release — eval gate, version bump in plugin.json and BRAIN_VERSION, tag, GitHub release, .plugin rebuild, skillsmith marketplace bump. Invoke only when the user asks to release.

★ 18
jame581
jame581/LogseqBrain

eval

Run the logseq-brain eval suite in WSL2 as the logseq-eval user — free --check by default, a paid full or single-case run only after confirmation. Invoke only when the user asks to run evals.

★ 18