/search

> Search the knowledge base for signals, contexts, and decisions.

170 stars

byMiosa-osa

View on GitHub Installation ↓

Best use case

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

> Search the knowledge base for signals, contexts, and decisions.

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

Manual Installation

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

How /search Compares

Feature / Agent	/search	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?

> Search the knowledge base for signals, contexts, and decisions.

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

# /search

> Search the knowledge base for signals, contexts, and decisions.

## Usage
```
/search "<query>" [--node <node>] [--type <type>] [--genre <genre>] [--limit <n>]
```

## What It Does
Queries the OptimalOS knowledge base using FTS5 full-text search. Returns L0 abstracts (~100 tokens each) ranked by relevance. Use before answering questions about past context -- search first, don't guess which file to read.

## Implementation
Runs: `cd engine && mix optimal.search "<query>" [flags]`

The engine searches across all indexed markdown files, returning:
- File path (optimal:// URI)
- L0 abstract (compressed summary)
- Relevance score
- Node and genre metadata

## Examples
```bash
# Search for past decisions about pricing
/search "pricing decision"

# Search within a specific node
/search "Ed Honour" --node ai-masters

# Search for signals of a specific genre
/search "revenue" --type signal --genre decision-log

# Limit results
/search "Bennett" --limit 3
```

Related Skills

autoresearch

170

from Miosa-osa/canopy

Autonomous iterative improvement loop. Agent modifies code, verifies against metrics, keeps improvements or reverts failures, and repeats. Uses git as memory — each change is committed, measured, and kept or discarded. Runs until a target metric is hit or max iterations reached. Triggers on: "autoresearch", "auto improve", "iterative improvement", "autonomous loop", "hill climb"