review-domains
Skill9 starsChanged 9 months agoMITView on GitHub
Review the status of all domains in your second brain
In this repository6 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- audit-brainSkill
- audit-projectSkill
- new-domainSkill
- update-memorySkill
- weekly-reviewSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 36
Ask if user wants to dive into any specific domain
- Distinctive: line 71
Don't overwhelm - highlight what's most important
- Distinctive: line 73
Keep the overview scannable - details come when diving in
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/review-domains
Get an overview of all your knowledge domains and their current status.
Process
- Scan all domains:
- List all folders in
domains/(excluding_template) - For each domain, read CLAUDE.md and memory.md
- List all folders in
- Extract key information:
For each domain, identify:
- Domain name and purpose
- Current status/priorities
- Recent decisions (from memory.md)
- Any alerts or blockers
- Last activity (based on content)
- Present the overview:
Format as a clear summary table with:
- Domain name
- Current focus
- Status indicator
- Key metric or next action
- Highlight cross-domain connections:
- Note any domains that relate to each other
- Flag if decisions in one domain affect another
- Offer next steps:
- Ask if user wants to dive into any specific domain
- Suggest any domains that may need attention
Output Format
## Your Second Brain Overview
| Domain | Focus | Status | Next Action |
|--------|-------|--------|-------------|
| finances | [Current focus] | [Status] | [Action] |
| career | [Current focus] | [Status] | [Action] |
| health | [Current focus] | [Status] | [Action] |
| projects | [Current focus] | [Status] | [Action] |
### Connections
- [Domain A] and [Domain B] are connected: [how]
### Needs Attention
- [Domain]: [why it needs attention]
### Recent Activity
- [What was recently updated]Status Indicators
- Active - Regular activity, on track
- Needs Review - No recent updates or stale info
- Alert - Has critical or warning conditions
- New - Recently created, needs setup
Important
- Give an honest assessment of each domain's state
- Don't overwhelm - highlight what's most important
- Suggest concrete next actions when relevant
- Keep the overview scannable - details come when diving in
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.

