tbm-decision-eval

Community

Get better yes/no decisions faster.

Authorblucsigma05
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It helps produce high-quality worth-it recommendations by forcing evidence-first evaluation and clear decision output for legacy TBM-named requests.

Core Features & Use Cases

  • Legacy name compatibility: Lets teams keep using the old TBM-prefixed skill name when LT explicitly invokes it.
  • Decision-only recommendations: Produces exactly one final decision (Do / Do, but narrow / Spike first / Defer / Do not do) with structured rationale and next move.
  • Evidence-first evaluation: Instructs the model to read the referenced artifact first, and to explicitly report when required evidence is missing.

Quick Start

Ask the assistant to evaluate whether a proposed change is worth doing, and include the artifact or evidence to review by name (issue, PR, file, or thread text) so it can make an evidence-backed decision.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: tbm-decision-eval
Download link: https://github.com/blucsigma05/tbm-apps-script/archive/main.zip#tbm-decision-eval

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.