/assemble

> Build a tiered context bundle for a topic with token-aware loading.

170 stars

byMiosa-osa

View on GitHub Installation ↓

Best use case

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

> Build a tiered context bundle for a topic with token-aware loading.

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

Manual Installation

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

How /assemble Compares

Feature / Agent	/assemble	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?

> Build a tiered context bundle for a topic with token-aware loading.

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

# /assemble

> Build a tiered context bundle for a topic with token-aware loading.

## Usage
```
/assemble "<topic>" [--depth <l0|l1|full>]
```

## What It Does
Assembles a multi-tier context bundle for a given topic. Searches across all nodes, collects relevant files, and loads them at appropriate tiers (L0 = 100 tokens, L1 = 2K tokens, L2 = full). Returns a structured bundle with token counts so you know exactly what you're loading.

## Implementation
Runs: `cd engine && mix optimal.assemble "<topic>"`

Process:
1. Search all nodes for topic relevance.
2. Rank results by relevance score.
3. Load L0 abstracts for all matches.
4. Load L1 summaries for top matches.
5. Load full content only for highest-relevance hits.
6. Return structured bundle with token counts per tier.

## Examples
```bash
# Assemble context for a meeting topic
/assemble "AI Masters pricing"

# Assemble context before a call
/assemble "enterprise deal status"

# Quick L0-only scan
/assemble "team bandwidth" --depth l0
```

## Command