TPR Framework for Openclaw

The TPR Framework is a cognitive closed-loop system designed to transform ambiguous requirements into verifiable, executable, and reviewable results.

spzwin
v2.0.1
Apr 8, 2026
0
333
1

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install tpr-framework-main

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install tpr-framework-main using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is TPR Framework?

The TPR Framework (Think / Probe / Review) provides a unified methodology for navigating complex tasks. It functions as both a cognitive mindset and a formal execution process, leveraging a triple-department structure (Zhongshu, Menxia, and Shangshu) to ensure high-quality delivery. By centering all work on contractual benchmarks (GRV) and maintaining rigorous documentation, the framework ensures that no decision is made without systematic justification and user approval.

At its core, the framework emphasizes that orchestration should focus on scheduling rather than manual execution, and that documentation is the sole source of truth. This approach is essential for Openclaw Skills users who require professional-grade rigor in AI-driven project management and complex analytical workflows.

TPR Framework Use Cases

  • Analyzing complex technical problems through structured cognitive decomposition.
  • Starting new projects or drafting technical proposals (GRV) and review protocols.
  • Facilitating multi-agent collaboration and 'Battle' sessions to expose blind spots.
  • Systematic decision-making where risk assessment and verifiable outcomes are critical.

How TPR Framework Works

  1. Decision Matrix Assessment: Determine if the task requires the Full Flow or Cognitive Thinking mode based on delivery needs and agent capabilities.
  2. Discovery Phase: Engage in Think and Probe activities to generate a DISCOVERY.md file defining the problem space.
  3. GRV Alignment: Transition to the Review phase to establish the Goal, Results, and Vital actions in a GRV.md contract.
  4. Battle Protocol: Conduct a Probe and Review session (BATTLE.md) to challenge assumptions and refine the solution architecture.
  5. Implementation: Execute the plan through micro-TPR cycles, producing organized output in the designated project directory.

TPR Framework Setup

To integrate this methodology into your agent environment, declare your configuration in your AGENTS.md file:

# Example configuration for orchestrator agents
tpr_mode: full
can_spawn: true
model_config: config/tpr-model-config.md

Ensure all reference documents from the references/ directory are accessible to the agent for on-demand loading during specific workflow stages.

TPR Framework Data Schema & Taxonomy

The skill organizes data through a strict documentation hierarchy to ensure transparency and traceability:

Document Phase Purpose
DISCOVERY.md Discovery Requirement analysis and initial probing results.
GRV.md Alignment The 'Contract' containing Goals, Results, and Vital actions.
BATTLE-*.md Review Records of critical challenges and solution refinements.
output/* Implementation Final deliverables and generated technical assets.

TPR Framework Advanced Features

  • Multi-agent orchestration support for agents with sub-agent spawning capabilities.
  • Automated project grading to assess complexity and determine appropriate review rigor.
  • Cognitive templates for rapid 'Think-Probe-Review' speed-memos.
  • Strict red-line protocols to prevent unauthorized agent decisions or private communications.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*