mcpField
M
moai-workflow-thinking

moai-workflow-thinking

github.com/modu-aiAgent workflows1.2k51 installsUpdated today
Repository

About moai-workflow-thinking

A MoAI skill for applying Sequential Thinking MCP when the explicit `--deepthink` flag is used. It distinguishes this tool-based mode from Claude’s native `ultrathink` reasoning.

Key features

  1. 01Explicit `--deepthink` activation
  2. 02Step-by-step thought sequencing
  3. 03Revision and branching support
  4. 04Separate handling of `ultrathink`

Use cases

  1. 01Decomposing complex problems
  2. 02Planning designs that may need revision
  3. 03Assessing architecture across multiple files

MCP support

Uses the `mcp__sequential-thinking__sequentialthinking` MCP tool for `--deepthink`; `ultrathink` instead uses Claude’s native reasoning.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/modu-ai/moai-adk --skill moai-workflow-thinking

After installing, type/moai-workflow-thinkingin Claude Code to confirm it loaded.

Details

From the project README

Sequential Thinking MCP (--deepthink)

Structured step-by-step reasoning via mcp__sequential-thinking__sequentialthinking MCP tool.

CRITICAL: Two Distinct Modes

MoAI has TWO independent deep analysis modes. They are NOT the same thing:

ModeTriggerMechanismMCP Tool?GLM Compatible?
--deepthinkExplicit --deepthink flagSequential Thinking MCP toolYES — mcp__sequential-thinking__sequentialthinkingNO — generates server_tool_use content type
ultrathinkKeyword or auto-detectionClaude native extended reasoning (high effort)NO — native to ClaudeYES — no special content type

Rules:

  • --deepthink → ALWAYS invoke Sequential Thinking MCP. NEVER use for native reasoning.
  • ultrathink → ALWAYS use Claude's native extended reasoning. NEVER invoke Sequential Thinking MCP.
  • They can coexist: ultrathink --deepthink activates BOTH modes independently.

Activation Triggers (--deepthink only)

Use Sequential Thinking MCP when --deepthink flag is explicitly present:

  • Breaking down complex problems into steps
  • Planning and design with room for revision
  • Architecture decisions affect 3+ files
  • Technology selection between multiple options
  • Performance vs maintainability trade-offs
  • Breaking changes under consideration
  • Multiple approaches exist to solve the same problem
  • Repetitive errors occur

Tool Parameters

Required Parameters:

  • thought (string): Current thinking step content
  • nextThoughtNeeded (boolean): Whether another step is needed
  • thoughtNumber (integer): Current thought number (starts from 1)
  • totalThoughts (integer): Estimated total thoughts needed

Optional Parameters:

  • isRevision (boolean): Whether this revises previous thinking
  • revisesThought (integer): Which thought is being reconsidered
  • branchFromThought (integer): Branching point for alternatives
  • branchId (string): Branch identifier
  • needsMoreThoughts (boolean): If more thoughts needed beyond estimate

Usage Pattern

Step 1 - Initial Analysis:

thought: "Analyzing the problem: [describe problem]"
nextThoughtNeeded: true
thoughtNumber: 1
totalThoughts: 5

Step 2 - Decomposition:

thought: "Breaking down: [sub-problems]"
nextThoughtNeeded: true
thoughtNumber: 2
totalThoughts: 5

Step 3 - Revision (if needed):

thought: "Revising thought 2: [correction]"
isRevision: true
revisesThought: 2
thoughtNumber: 3
totalThoughts: 5
nextThoughtNeeded: true

Final Step - Conclusion:

thought: "Conclusion: [final answer]"
thoughtNumber: 5
totalThoughts: 5
nextThoughtNeeded: false

Guidelines

  1. Start with reasonable totalThoughts estimate
  2. Use isRevision when correcting previous thoughts
  3. Maintain thoughtNumber sequence
  4. Set nextThoughtNeeded to false only when complete
  5. Use branching for exploring alternatives

Comments

Markdown supported