critic-cache
OfficialSkip redundant critic runs.
Authorclosedloop-ai
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill prevents unnecessary re-runs of critic agents by checking if the plan and critic configurations have changed since the last run, saving computational resources and time.
Core Features & Use Cases
- Cache Validation: Compares content hashes of
plan.jsonandcritic-gates.jsonagainst a stored hash. - Conditional Execution: Triggers on entering Phase 2.5, before launching critics, to determine if critics can be skipped.
- Use Case: If the codebase plan and critic configurations haven't changed since the last review cycle, this skill will identify that the existing reviews are still valid, allowing the process to bypass the critic phase entirely.
Quick Start
Execute the check_critic_cache.sh script with the current working directory as the argument.
Dependency Matrix
Required Modules
None requiredComponents
scripts
💻 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: critic-cache Download link: https://github.com/closedloop-ai/claude-plugins/archive/main.zip#critic-cache Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.