skills.rest
GenEducation
GenEducationOFFICIAL
Explore all skills by this author →
GitHub

bmad-os-review-prompt

Review LLM workflow prompts for silent failures, ambiguity, and execution risks.

Updated Mar 30, 2026
Search Tags:#prompt engineering#failure modes#agent systems#severity scoring#prompt auditing#llm workflows
One-click install
npx skills add https://github.com/GenEducation/GenedUIProject --skill bmad-os-review-prompt
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-os-review-prompt
Source: https://github.com/GenEducation/GenedUIProject/tree/main/.gemini/skills/bmad-os-review-prompt
Command: npx skills add https://github.com/GenEducation/GenedUIProject --skill bmad-os-review-prompt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill reviews LLM workflow prompts for execution risks that can cause silent failures, ambiguous behavior, scope creep, or inconsistent results at scale.

Core Features & Use Cases

  • Failure Mode Detection: Identifies prompt patterns that break under load, across model vendors, or in multi-step agent workflows.
  • Risk-Ready Review Output: Produces quoted findings with severity, mitigation guidance, and rewritten examples for production use.
  • Use Case: Use it to audit an autonomous workflow prompt before deploying it to a high-volume agent system.

Quick Start

Ask the skill to review a workflow prompt and return a severity-ranked audit with exact quotes and concrete rewrites.

Frequently Asked Questions about bmad-os-review-prompt

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit LLM workflow prompts for silent failures and scope creep?▼

To audit LLM workflow prompts for silent failures, review exact prompt quotes against failure-mode classifications and apply severity scoring to identify execution risks. This process detects ambiguity and scope creep before deploying autonomous agent systems.

What is prompt hardening for multi-step agent systems?▼

Prompt hardening for multi-step agent systems is the process of reviewing and rewriting prompts to eliminate silent failures and inconsistent behavior under load. It produces risk-ready outputs with severity scores and mitigated prompt rewrites for production use.

How do I review a workflow prompt for execution risks before production deployment?▼

Review a workflow prompt for execution risks by analyzing exact prompt quotes and classifying failure modes that break across model vendors. Generate severity-ranked findings with concrete mitigations and rewritten examples to ensure production readiness.

Does prompt auditing work for autonomous agent workflows at scale?▼

Yes, prompt auditing works for autonomous agent workflows at scale by identifying prompt patterns that cause silent failures or inconsistent results under heavy load. It generates severity-scored mitigations with rewritten examples to ensure robust multi-step execution.

What are common prompt failure modes in multi-step LLM workflows?▼

Common prompt failure modes in multi-step LLM workflows include silent failures, ambiguous behavior, scope creep, and inconsistent results across model vendors. Identifying these execution risks requires classifying exact prompt quotes and applying severity scoring.

Related Skills

Explore More Content & Communication Skills→
TonyQ-AITonyQ-AI
9

workflow-runner

Execute multi-agent YAML orchestration workflows with role-based task dependencies.

Community
Advanced
mobster570mobster570

agent-development

Generate and validate autonomous agent configurations for Claude Code plugins.

Community
Advanced
pazdedavpazdedav

workflow-engine

Define DAG workflow graphs with JSON schema for agent orchestration.

Community
Advanced
sayasaya8039sayasaya8039
2

eval-harness

Define pass/fail criteria and run regression evals for Claude Code agents.

Community
Advanced