cog-knowledge-consolidation

Build structured knowledge frameworks from scattered vault notes with source attribution

509 stars

Best use case

cog-knowledge-consolidation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Build structured knowledge frameworks from scattered vault notes with source attribution

Teams using cog-knowledge-consolidation should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/knowledge-consolidation/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/methodologies/cog-second-brain/skills/knowledge-consolidation/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/knowledge-consolidation/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How cog-knowledge-consolidation Compares

Feature / Agentcog-knowledge-consolidationStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Build structured knowledge frameworks from scattered vault notes with source attribution

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# COG Knowledge Consolidation Skill

Build structured knowledge frameworks from scattered notes across the vault, preserving source attribution and maintaining cross-references.

## Capabilities

- Scan vault sections for unconsolidated notes
- Cluster related notes into coherent themes
- Build structured frameworks: concept maps, key principles, examples, applications
- Cross-reference with existing frameworks in 05-knowledge
- Preserve source attribution through consolidation
- Quality-gated framework building with iterative refinement
- Identify knowledge gaps needing additional capture

## Tool Use Instructions

1. Use `file-search` to find notes not yet consolidated into frameworks
2. Use `file-read` to load candidate notes and existing frameworks
3. Cluster related notes by topic similarity
4. Build framework structure: concept map, principles, examples, applications
5. Use `file-write` to create or update frameworks in 05-knowledge
6. Add cross-references between new and existing frameworks
7. Use `git-commit` to commit consolidated frameworks

## Examples

```json
{
  "vaultPath": "./cog-vault",
  "mode": "knowledge-consolidation",
  "userName": "Alex",
  "targetQuality": 80
}
```

Related Skills

knowledge-analytics

509
from a5c-ai/babysitter

Knowledge base analytics, usage reporting, and effectiveness measurement

knowledge-extractor

509
from a5c-ai/babysitter

Extract tribal knowledge from code, documentation, and commit history to preserve institutional memory

knowledge-curation

509
from a5c-ai/babysitter

Context priming before work (bd prime) and self-reflection after completion to extract patterns, gotchas, and decisions into the knowledge base.

knowledge-graph-management

509
from a5c-ai/babysitter

Capture, validate, query, and sync architectural patterns and design decisions in the knowledge graph

process-builder

509
from a5c-ai/babysitter

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

Workflow & Productivity

babysitter

509
from a5c-ai/babysitter

Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)

yolo

509
from a5c-ai/babysitter

Run Babysitter autonomously with minimal manual interruption.

user-install

509
from a5c-ai/babysitter

Install the user-level Babysitter Codex setup.

team-install

509
from a5c-ai/babysitter

Install the team-pinned Babysitter Codex workspace setup.

retrospect

509
from a5c-ai/babysitter

Summarize or retrospect on a completed Babysitter run.

resume

509
from a5c-ai/babysitter

Resume an existing Babysitter run from Codex.

project-install

509
from a5c-ai/babysitter

Install the Babysitter Codex workspace integration into the current project.