unstuck
Scannednpx machina-cli add skill Q00/ouroboros/unstuck --openclaw/ouroboros:unstuck
Break through stagnation with lateral thinking personas.
Usage
/ouroboros:unstuck [persona]
Trigger keywords: "I'm stuck", "think sideways"
Available Personas
| Persona | Style | When to Use |
|---|---|---|
| hacker | "Make it work first, elegance later" | When overthinking blocks progress |
| researcher | "What information are we missing?" | When the problem is unclear |
| simplifier | "Cut scope, return to MVP" | When complexity is overwhelming |
| architect | "Restructure the approach entirely" | When the current design is wrong |
| contrarian | "What if we're solving the wrong problem?" | When assumptions need challenging |
Instructions
When the user invokes this skill:
-
Determine the context:
- What is the user stuck on? (Check recent conversation)
- What approaches have been tried?
- Which persona would help most?
-
If a specific persona is requested, use it. Otherwise, choose based on context:
- Repeated similar failures → contrarian (challenge assumptions)
- Too many options → simplifier (reduce scope)
- Missing information → researcher (seek data)
- Analysis paralysis → hacker (just make it work)
- Structural issues → architect (redesign)
-
Call the
ouroboros_lateral_thinkMCP tool:Tool: ouroboros_lateral_think Arguments: problem_context: <description of the stuck situation> current_approach: <what has been tried> persona: "contrarian" (or chosen persona) failed_attempts: ["attempt1", "attempt2"] (previous failures) -
Present the lateral thinking result:
- Show the persona's approach summary
- Present the reframing prompt
- List the questions to consider
- Suggest concrete next steps
Fallback (No MCP Server)
If the MCP server is not available, delegate to the matching agent:
ouroboros:contrarian- "What if we're solving the wrong problem?"ouroboros:hacker- "Make it work, elegance comes later"ouroboros:simplifier- "Cut scope to the absolute minimum"ouroboros:researcher- "Stop coding. Read the docs."ouroboros:architect- "Question the foundation. Rebuild if needed."
These agents use prompt-based lateral thinking without numerical analysis.
Example
User: I'm stuck on the database schema design
/ouroboros:unstuck simplifier
# Lateral Thinking: Reduce to Minimum Viable Schema
Start with exactly 2 tables. If you can't build the core feature
with 2 tables, you haven't found the core feature yet.
## Questions to Consider
- What is the ONE query your users will run most?
- Can you use a single JSON column instead of normalized tables?
- What if you started with flat files and added a DB later?
Overview
unstuck helps you break out of stagnation by adopting dedicated lateral thinking personas. By switching perspective to hacker, researcher, simplifier, architect, or contrarian, you can reframe problems, surface missing data, trim scope, or challenge assumptions, then plan concrete next steps.
How This Skill Works
Invoke /ouroboros:unstuck [persona] to select a mindset. The system uses context to pick a persona (or uses the one you specify) and calls the ouroboros_lateral_think MCP tool with problem_context, current_approach, persona, and failed_attempts. It returns a persona approach summary, a reframing prompt, a list of clarifying questions, and concrete next steps.
When to Use It
- When overthinking blocks progress
- When the problem is unclear
- When complexity is overwhelming
- When the current design is wrong
- When assumptions need challenging
Quick Start
- Step 1: Run /ouroboros:unstuck [persona] or omit to let the system pick
- Step 2: The MCP tool runs and returns a persona approach, reframing prompt, questions, and next steps
- Step 3: Act on the suggested steps, iterate, and share results
Best Practices
- Define the exact stuck point and choose a matching persona
- Note what has already been tried before invoking the tool
- Use the reframing prompt and questions to surface new angles
- Limit scope or challenges before taking next steps
- Test and validate the suggested actions with quick experiments
Example Use Cases
- Stuck on database schema design? Use simplifier to start with exactly 2 tables to test the core feature
- Problem unclear? Use researcher to identify missing data and required inputs
- Too many options? Use contrarian to challenge whether the problem is the right one
- Current design is wrong? Use architect to restructure the approach
- Overthinking blocks progress? Use hacker to make it work first