OST stands for Opportunity Solution Tree and is a workflow for organizing outcomes, opportunities, solutions, and assumptions in a graph based structure.

How do I start using OST

Initialize the local graph DB, pick a workspace, then select or create an outcome, and finally load the phase reference you want to work on.

ost

npx machina-cli add skill kasperjunge/agent-resources/ost --openclaw

Files (1)

SKILL.md

2.6 KB

OST

Run a full Opportunity Solution Tree workflow from a single skill, backed by a lightweight graph database and CLI.

Entry Flow (Minimize File Loading)

Goal: Start a session, pick a workspace, and select or create an outcome.

Ensure DB exists

If .agr/ost.db is missing, initialize it:
- uv run python scripts/ost.py init --path .agr/ost.db

Select workspace

List workspaces:
- uv run python scripts/ost.py workspace list
If needed, create one:
- uv run python scripts/ost.py workspace create \"<name>\"

Select outcome

List outcomes:
- uv run python scripts/ost.py outcome list --workspace <name>
If needed, create one:
- uv run python scripts/ost.py outcome add --workspace <name> \"<title>\"

Route to phase (load only the relevant file)

Outcomes: references/outcomes.md
Opportunities: references/opportunities.md
Solutions: references/solutions.md
Assumptions/Experiments: references/assumptions.md

Data Model + Storage

Use a lightweight graph DB at .agr/ost.db with multi-workspace support. The CLI manages nodes and edges; do not edit DB files manually.

CLI

Use the CLI to read/write the OST graph. The CLI is expected to live in this skill’s scripts/ directory and be run via uv run.

Commands (intended):

uv run python scripts/ost.py init --path .agr/ost.db
uv run python scripts/ost.py workspace list
uv run python scripts/ost.py workspace create "<name>"
uv run python scripts/ost.py outcome list --workspace <name>
uv run python scripts/ost.py outcome add --workspace <name> "<title>"
uv run python scripts/ost.py opportunity add --outcome <id> "<title>"
uv run python scripts/ost.py solution add --opportunity <id> "<title>"
uv run python scripts/ost.py assumption add --solution <id> "<title>"
uv run python scripts/ost.py show --outcome <id>

If the CLI is not yet implemented, document the intended command and proceed with non-destructive guidance only.

Output Format

## OST Session

### Selected Workspace
- Name: ...

### Selected Outcome
- ID: ...
- Title: ...

### Next Action
- [What the user wants to do next]

### Next Step
- Load the relevant phase reference file

What NOT to Do

Do NOT edit .agr/ost.db directly.
Do NOT invent node IDs.
Do NOT run destructive commands without explicit user intent.

Source

git clone https://github.com/kasperjunge/agent-resources/blob/main/skills/product-development/ost/SKILL.mdView on GitHub

Overview

Run or maintain an Opportunity Solution Tree workflow using a lightweight graph database and a CLI. It provides a single entry skill that routes to outcomes, opportunities, solutions, and assumptions/experiments through progressive disclosure to keep work organized across multiple workspaces.

How This Skill Works

Start a session and select a workspace and outcome. If the graph DB at .agr/ost.db does not exist, initialize it via the OST CLI (uv run python scripts/ost.py init --path .agr/ost.db). After choosing the workspace and outcome, the skill routes you to the relevant phase reference file (outcomes.md, opportunities.md, solutions.md, or assumptions.md) for guided work.

When to Use It

Starting a new OST session: initialize the DB, pick a workspace, and choose an outcome
Managing workspaces and outcomes without editing the database files manually
Adding opportunities, solutions, or assumptions to an existing OST
Loading the correct phase reference file to work on a specific phase
Maintaining OST across multiple workspaces with non destructive, CLI driven actions

Quick Start

Step 1: uv run python scripts/ost.py init --path .agr/ost.db
Step 2: uv run python scripts/ost.py workspace list
Step 3: uv run python scripts/ost.py outcome add --workspace <name> "<title>"

Best Practices

Initialize and verify the DB exists before performing any OST actions
Use the CLI to list and select workspaces and outcomes to avoid guessing IDs
Operate strictly through the provided OST CLI commands rather than editing DB files
Route to the correct phase by loading the appropriate references file
Do not perform destructive commands without explicit user intent

Example Use Cases

A product team starts a new OST session for a SaaS feature and creates a workspace and initial outcome
An initiative manager adds a new opportunity and links it to the existing outcome
A designer adds a corresponding solution under an opportunity and captures it in the OST
A researcher adds an assumption to test for a solution and records the experiment plan
The team switches between outcomes and phases to review progress using the references files

Frequently Asked Questions

Add this skill to your agents