Skill Claude CodeCodex
Evaluates received review results before they generate work by separating problems from proposed fixes and comparing responses in a fixed decision order. Use whenever review results may lead to artifact changes; does not produce reviews.
Skill Claude CodeCodex
Guides subagent coordination through implementation workflows. Use when: orchestrating multiple agents, managing workflow phases, determining autonomous execution mode, or coordinating recipe execution.
Skill Claude CodeCodex
Analyzes standalone task essence, task type, applicable skills, and metacognitive execution risks.
Skill Claude CodeCodex
Repository-aware test execution rules for TDD, observable proof, and boundary selection. Use when writing, reviewing, or fixing tests.
Plugin Claude Code
Plugin marketplace listing 1 plugin: rashomon.
Plugin Claude Code
Evaluate prompts and skills through parallel execution comparison in git worktrees. Prompt optimization with BP-001009 patterns, skill creation/update with quality grading, and blind A/B evaluation.
Agent
Collects user feedback on comparison results and optimizes the knowledge base. Use when user indicates comparison results did not meet expectations or provides feedback on optimization quality. Adjusts confidence scores and manages knowledge entries.
Agent
Analyzes prompts against BP-001 through BP-009 and returns the prompt-optimization skill's gated JSON result. Use when prompt text or a prompt file is provided for optimization.
Agent
Executes a prompt in an isolated worktree environment and captures results. Use when worktree path and prompt are provided for execution. Returns execution status, outputs, and observations with strictly factual reporting only.
Agent
Performs blind comparison of repeated prompt-execution pairs, then maps observed differences to optimization findings after identity reveal. Use when original and optimized prompt trials are available.
Agent
Generates or modifies optimized skill files. In creation mode, builds from raw user knowledge. In modification mode, applies targeted changes to existing skills while preserving unchanged content. Use when creating new skills or updating existing ones.
Agent
Compares repeated paired execution results using blind A/B methodology and generates a skill effectiveness report. Use when valid skill-evaluation result pairs are available.
Agent
Evaluates skill file quality against optimization patterns and editing principles. Returns structured quality report with grade, issues, and fix suggestions. Use when reviewing created or modified skill content.
Skill Claude CodeCodex
Analyzes and optimizes prompts using BP-001009 patterns and a gated 3-step flow. Use when "optimize this prompt", "review prompt quality", "analyze prompt issues", or creating/reviewing rashomon skill content.
Skill Claude CodeCodex
Project-specific prompt optimization knowledge management. Use when storing or retrieving learned patterns from comparisons. Provides schema, extraction criteria, capacity management, and retention scoring.
Skill Claude CodeCodex
Compares original and optimized prompts through repeated blind paired execution in git worktrees. Use when evaluating prompt improvement effects or learning prompt engineering through concrete examples.
Skill Claude CodeCodex
Creates or updates Claude Code skills through interactive dialog, then evaluates effectiveness with sequential paired comparisons. Use when creating new skills, updating existing skills, or evaluating skill quality.
Skill Claude CodeCodex
Git worktree management for isolated parallel prompt execution. Use when creating isolated environments for prompt comparison or managing worktree lifecycle. Provides creation, cleanup, and orphan detection scripts.
Plugin Claude Code
Local Galley workflow plugins.
Plugin Claude Code
Session-only guard hooks for Galley Claude executor runs.
Hook
Runs before the agent uses a tool for Bash tool calls, executing block-finalizer-commands.py. From shinpr/galley.
Hook
Runs when the agent finishes a response, executing require-final-json.py. From shinpr/galley.
Plugin Claude Code
Create, validate, queue, set up, and troubleshoot Galley AFK task workflows.
Skill Claude CodeCodex
Authors and validates Galley task YAML, profiles, daemon handoff, run evidence, and queueing. Use when the user asks to create/repair/queue a Galley task, configure profiles/daemon/PR automation, or diagnose a Galley run.