How do I pass a seed to the run skill?

Provide seed YAML content directly or supply a path to a .yaml file when invoking /ouroboros:run. If neither is provided, the skill will check conversation history for a recently generated seed.

What if the MCP server is not configured or unavailable?

The skill will show a fallback message with guidance to enable full execution via /ouroboros:setup. You can still use related skills like /ouroboros:interview or /ouroboros:seed, or manually implement the seed.

How do I resume a previous run to check progress?

Include session_id in the tool call to ouroboros_execute_seed (or refer to the session_id returned in the initial result). This continues tracking progress and can provide a new execution summary or final status.

run

npx machina-cli add skill Q00/ouroboros/run --openclaw

Files (1)

SKILL.md

2.2 KB

/ouroboros:run

Execute a Seed specification through the Ouroboros workflow engine.

Usage

/ouroboros:run [seed_file_or_content]

Trigger keywords: "ouroboros run", "execute seed"

How It Works

Input: Provide seed YAML content directly or a path to a .yaml file
Validation: Seed is parsed and validated (goal, constraints, acceptance criteria, ontology)
Execution: The orchestrator runs the workflow with PAL routing
Progress: Real-time progress updates via session tracking
Result: Execution summary with pass/fail status

Instructions

When the user invokes this skill:

Check if the user provided seed content or a file path:
- If a file path: Read the file with the Read tool
- If inline YAML: Use directly
- If neither: Check conversation history for a recently generated seed

Call the ouroboros_execute_seed MCP tool:

Tool: ouroboros_execute_seed
Arguments:
  seed_content: <the seed YAML>
  model_tier: "medium"  (or as specified by user)
  max_iterations: 10    (or as specified by user)

If resuming an existing session, include session_id:

Tool: ouroboros_execute_seed
Arguments:
  seed_content: <the seed YAML>
  session_id: <existing session ID>

Present the execution results to the user:
- Show success/failure status
- Show session ID (for later status checks)
- Show execution summary
- Suggest /ouroboros:evaluate for post-execution verification

Fallback (No MCP Server)

If the MCP server is not available, inform the user:

Ouroboros MCP server is not configured.
To enable full execution mode, run: /ouroboros:setup

Without MCP, you can still:
- Use /ouroboros:interview for requirement clarification
- Use /ouroboros:seed to generate specifications
- Manually implement the seed specification

Example

User: /ouroboros:run seed.yaml

[Reads seed.yaml, validates, executes via MCP]

Result:
  Seed Execution SUCCESS
  ========================
  Session ID: sess-abc-123
  Goal: Build a CLI task manager
  Duration: 45.2s
  Messages Processed: 12

  Next: /ouroboros:evaluate sess-abc-123

Source

git clone https://github.com/Q00/ouroboros/blob/main/skills/run/SKILL.mdView on GitHub

Overview

Execute a Seed YAML specification using the Ouroboros workflow engine. The skill validates the seed (goal, constraints, acceptance criteria, ontology), runs the workflow with PAL routing, and provides real-time progress plus a final pass/fail summary. It supports inline YAML or a file path and can resume an existing session for status updates.

How This Skill Works

Input a seed YAML content directly or a path to a .yaml file. The seed is parsed and validated against its goal, constraints, acceptance criteria, and ontology. The orchestrator runs the workflow with PAL routing, delivering real-time progress via session tracking and returning a result with pass/fail status. If the MCP server is unavailable, a guided fallback is shown and you can still use related skills or seeds.

When to Use It

Running a new seed YAML to start a workflow
Resuming an existing session to monitor progress
Providing inline YAML or a file path for batch or automated runs
Customizing execution with model_tier or max_iterations for resource control
Verifying results with /ouroboros:evaluate after completion

Quick Start

Step 1: Provide seed YAML content directly or specify a path to seed.yaml
Step 2: Run /ouroboros:run [seed_file_or_content] and note any session_id returned
Step 3: Review the execution results and, if needed, run /ouroboros:evaluate <session_id> for verification

Best Practices

Validate the seed content before execution, ensuring proper goal, constraints, acceptance criteria, and ontology are defined
Provide seed content via a file path or ensure inline YAML is well-formed and readable
Specify model_tier and max_iterations to match the workflow complexity and resources
Always capture and share the session_id for later status checks and evaluations
If MCP is unavailable, use the fallback guidance and proceed with evaluation or interviewing as appropriate

Example Use Cases

User runs /ouroboros:run seed.yaml to build a CLI task manager and receives a session ID for status checks
Inline YAML seed is supplied to quickly initialize and execute a data processing pipeline
Resume a session with sess-abc-123 to monitor progress and fetch a final report
Run a complex workflow with model_tier set to high to ensure thorough exploration of constraints
MCP server is down; user follows fallback steps and later uses /ouroboros:evaluate for verification

Frequently Asked Questions

Add this skill to your agents