Review implementation plans for security gaps, missing requirements, and resilience issues.
npx skills add https://github.com/Reidond/Banshee --skill plan-critic-reidond
Please help me install this Agent Skill. Skill: plan-critic Source: https://github.com/Reidond/Banshee/tree/main/.claude/skills/plan-critic Command: npx skills add https://github.com/Reidond/Banshee --skill plan-critic-reidond
This Skill prevents flawed implementation plans from reaching users by performing adversarial reviews that identify security gaps, missing requirements, resilience issues, and unnecessary complexity before execution.
Ask the plan-critic skill to review the implementation plan for security, completeness, resilience, and architectural risks before sharing it with stakeholders.
High-intent search queries and answers about installing and using this skill.
Reviewing an implementation plan for security gaps requires an adversarial evaluation against structured criteria covering completeness, stability, and impact analysis to identify flaws before execution. This process challenges architectural decisions and detects missing requirements.
Catching architectural flaws before implementation involves critically evaluating design documents and task plans to identify overengineering, resilience issues, and unnecessary complexity. This ensures unsafe assumptions are uncovered prior to approval.
Validating AI system workflows for integration risks requires analyzing AI-specific failure modes and missing contracts within the design. This detects unsafe assumptions and ensures rigorous validation of AI-powered workflows before execution.
Detecting overengineering in task plans uses structured review criteria to evaluate architectural decisions and eliminate unnecessary complexity. This ensures the design maintains stability without adding excessive components before approval.
Plan review works for AI-integrated system workflows by detecting AI-specific failure modes and integration risks during the evaluation. It validates missing contracts and unsafe assumptions to ensure workflow stability before implementation.
Adversarial review for software architecture documents should be avoided if the plan lacks sufficient detail for impact analysis and completeness evaluation. Without structured criteria, the review cannot effectively identify resilience issues or missing requirements.
loriensleafsCritique decisions through decomposed claims, evidence verification, and adversarial review.
robertdpAnalyze targets for issues and guide evidence-based resolution.
isihigameKoudaiGenerate documentation and task plans from manually drafted specifications.
LeoWSY-hashblueScan source code for vulnerabilities, secrets, and dependency CVEs.
