agentleFS
AbilityaiAbilityai/cornelius/.claude/skills/integrate-recent-notes/SKILL.md

integrate-recent-notes

Skill109 starsChanged 37 days agoMITView on GitHub

Find notes created in the last 14 days and discover their connections to the knowledge base

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
  1. Distinctive:

    Run connection discovery (wide read-scope: recent notes live in 00-Inbox / Document Insights / Books / 05-Meta - core-only would fail to …

    line 57
  2. Distinctive:

    Document Insights / Books / 05-Meta - core-only would fail to resolve the note itself or its non-core neighbors once scope enforcement is …

    line 58
  3. Distinctive:

    Check BDG layer classification:

    line 64

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Integrate Recent Notes

Find recently created notes and map their connections to the existing knowledge base.

Purpose

New notes often sit unconnected. This playbook identifies notes from the last 14 days and discovers how they integrate with existing knowledge.

State Dependencies

SourceLocationReadWriteDescription
Permanent NotesBrain/02-Permanent/✓Recent notes source
AI Extracted NotesBrain/AI Extracted Notes/✓Recent notes source
Document InsightsBrain/Document Insights/✓Recent notes source
Book scopesBrain/Books/✓Recent notes source (per-book scopes)
Local Brain Searchresources/local-brain-search/✓Connection discovery
Session ChangelogsBrain/05-Meta/Changelogs/✓Integration report

Prerequisites

  • Local Brain Search index up-to-date (/refresh-index)

Process

Step 1: Find Recent Notes

Find notes modified in the last 14 days:

find Brain/02-Permanent -name "*.md" -mtime -14 -type f
find Brain/AI\ Extracted\ Notes -name "*.md" -mtime -14 -type f
find Brain/Document\ Insights -name "*.md" -mtime -14 -type f
find Brain/Books -name "*.md" -mtime -14 -type f

Compile list of recent notes.

Step 2: Get Current Date

date '+%Y-%m-%d'

Step 3: Analyze Connections for Each

For each recent note:

  1. Extract note title from filename
  2. Run connection discovery (wide read-scope: recent notes live in 00-Inbox / Document Insights / Books / 05-Meta - core-only would fail to resolve the note itself or its non-core neighbors once scope enforcement is on):
    BRAIN_READ_SCOPE=core,Books,document-insights,meta,inbox,output resources/local-brain-search/run_connections.sh "Note Title" --json
  3. Record top 5 connections with similarity scores
  4. Check BDG layer classification:
    resources/brain-graph/run_brain_graph.sh inspect "Note Title" --json

Step 4: Identify Integration Opportunities

For each note, categorize:

  • Well-connected (3+ connections > 0.70): Already integrated
  • Partially connected (1-2 connections > 0.70): Needs attention
  • Isolated (0 connections > 0.70): Priority for integration

Step 5: Create Integration Report

Write to Brain/05-Meta/Changelogs/CHANGELOG - Note Integration YYYY-MM-DD.md:

## Note Integration Report: YYYY-MM-DD

### Recent Notes Analyzed
Total: [N] notes from last 14 days

### Integration Status

**Well-Connected** ([N]):
- [[Note A]] - 5 connections

**Partially Connected** ([N]):
- [[Note B]] - 2 connections
  - Suggested: Link to [[X]], [[Y]]

**Isolated - Priority** ([N]):
- [[Note C]] - 0 connections
  - Top semantic matches: [[X]] (0.65), [[Y]] (0.62)
  - Integration suggestion: [brief recommendation]

### Suggested Actions
1. [specific linking recommendations]
2. [synthesis opportunities]

Outputs

  • Integration report in Brain/05-Meta/Changelogs/
  • List of isolated notes needing attention
  • Suggested connections for each

Error Handling

ErrorRecovery
No recent notesLog "no notes in period" and exit
Connection search failsNote error, continue with next note
Index outdatedRun /refresh-index first

Completion Checklist

  • Recent notes identified (last 14 days)
  • Connections analyzed for each note
  • Notes categorized (well-connected, partial, isolated)
  • Integration suggestions provided for isolated notes
  • Report created in Brain/05-Meta/Changelogs/

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.