/impact

> Analyze the downstream impact of a change across all nodes.

170 stars

byMiosa-osa

View on GitHub Installation ↓

Best use case

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

> Analyze the downstream impact of a change across all nodes.

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

Manual Installation

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

How /impact Compares

Feature / Agent	/impact	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?

> Analyze the downstream impact of a change across all nodes.

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

# /impact

> Analyze the downstream impact of a change across all nodes.

## Usage
```
/impact "<change>" [--scope <node>]
```

## What It Does
Maps the ripple effects of a proposed change across the knowledge base. Identifies which nodes, people, revenue streams, and processes are affected. Classifies impacts as direct (1st order) or indirect (2nd/3rd order).

## Implementation
Runs: `cd engine && mix optimal.impact`

Process:
1. **Parse change** -- what is being changed and in which domain.
2. **Map dependencies** -- which nodes reference the affected entity.
3. **Trace effects** -- 1st order (direct), 2nd order (downstream), 3rd order (cascading).
4. **Identify stakeholders** -- who needs to know.
5. **Assess risk** -- probability and severity of negative effects.
6. **Report** -- impact map with affected nodes, people, and recommended mitigations.

## Examples
```bash
# Impact of a team change
/impact "Lead developer takes 2 weeks off"

# Impact of a pricing change
/impact "Raise enterprise pricing to $5K/mo"

# Scoped impact analysis
/impact "Switch from Firecracker to containers" --scope platform
```

## Command