/reflect

> Find entities that co-occur frequently but lack explicit connections.

170 stars

byMiosa-osa

View on GitHub Installation ↓

Best use case

/reflect is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

> Find entities that co-occur frequently but lack explicit connections.

Teams using /reflect 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/reflect/SKILL.md --create-dirs "https://raw.githubusercontent.com/Miosa-osa/canopy/main/library/skills/knowledge/reflect/SKILL.md"

Manual Installation

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

How /reflect Compares

Feature / Agent	/reflect	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

> Find entities that co-occur frequently but lack explicit connections.

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

# /reflect

> Find entities that co-occur frequently but lack explicit connections.

## Usage
```
/reflect [--min <n>]
```

## What It Does
Scans the knowledge base for entities that appear together in multiple contexts but have no explicit edge in the knowledge graph. These are implicit relationships that may deserve explicit documentation. The `--min` flag sets the co-occurrence threshold.

## Implementation
Runs: `cd engine && mix optimal.reflect [--min <n>]`

Process:
1. Extract all entity mentions across files.
2. Build co-occurrence matrix.
3. Compare against explicit graph edges.
4. Report entity pairs with high co-occurrence but no edge.

## Examples
```bash
# Find unconnected co-occurring entities
/reflect

# Require at least 3 co-occurrences
/reflect --min 3
```

## Command