crash
Organize and break down complex tasks into structured, iterative steps for analysis, planning, and problem-solving. Use adaptive reasoning, confidence tracking, and revision mechanisms to explore multiple solution paths systematically.
Instructions
Facilitates structured, iterative reasoning for complex problem-solving and analysis. Use this to organize thoughts, break down tasks, and plan actions step-by-step. This tool is ideal for scenarios requiring careful consideration of multiple factors, such as code optimization, system design, or strategic planning.
When to use CRASH:
- When user says "use crash" or similar phrases
- For multi-step or complex tasks requiring careful breakdown
- For understanding, planning, or analyzing codes or content
- When systematic reasoning is needed
- When you need to revise or correct previous reasoning
- When exploring multiple solution paths
Key Features:
- Flexible purpose types (analysis, action, validation, exploration, hypothesis, etc.)
- Confidence tracking for uncertain situations
- Revision mechanism to correct previous steps
- Branching support for parallel exploration
- Structured tool integration
- No rigid formatting requirements (configurable)
Instructions:
- Each step must specify a clear purpose and reasoning approach
- Track context to avoid redundancy
- Use confidence scores when uncertain (0-1 scale)
- Revise previous steps when needed using revises_step
- Branch to explore alternatives using branch_from
- Continue until task completion or solution found
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| branch_from | No | Step number to branch from for alternative exploration | |
| branch_id | No | Unique identifier for this branch | |
| branch_name | No | Descriptive name for this branch | |
| confidence | No | Confidence level in this step (0-1 scale) | |
| context | Yes | What is already known or has been completed to avoid redundancy | |
| dependencies | No | Step numbers this step depends on | |
| estimated_total | Yes | Current estimate of total steps needed (can be adjusted) | |
| external_context | No | External data or tool outputs relevant to this step | |
| next_action | Yes | Next tool or action to use (string or structured object) | |
| outcome | Yes | Expected or actual result from this step | |
| purpose | Yes | What this step accomplishes (analysis, action, validation, exploration, hypothesis, correction, planning, or custom) | |
| rationale | Yes | Why using this next action (natural language, no prefix required) | |
| revises_step | No | Step number being revised/corrected | |
| revision_reason | No | Why this revision is needed | |
| session_id | No | Session identifier for grouping related reasoning chains | |
| step_number | Yes | Sequential step number | |
| thought | Yes | Current reasoning. Express naturally without forced prefixes. | |
| tools_used | No | Tools used in this step | |
| uncertainty_notes | No | Notes about uncertainties or doubts |