A command is the one you type. It runs exactly when you ask it to, and never before.
60 commands across 626 plugins.
Remove menhera-loop UI settings — clingy by default, clean with --farewell.
@borelchuView CommandRecord a brief Architecture Decision Record (ADR) about a recent technical choice.
@yeaight7View CommandAudit a BigQuery SQL query or dbt model for potential cost traps before it hits production.
@yeaight7View CommandRun automated tests and build checks first, then agent code review. For each bug found, propose or document a regression test.
@yeaight7View CommandWalk through a file, function, class, or module and explain what it does, how it works, and why it is structured the way it is. Suited for onboarding onto…
@khaledsaeed18View CommandUse when a build, type check, or test suite is failing and needs to be unblocked with a minimal change.
@yeaight7View CommandRun a systematic cleanup on the provided code to resolve smells, simplify complexity, and enforce best practices.
@yeaight7View CommandReview source files changed during a phase for bugs, security issues, and code quality problems
@yeaight7View CommandIsolate a bug report into a minimal, standalone reproduction script or test case.
@yeaight7View CommandReview or design a data pipeline architecture based on requirements
@yeaight7View CommandBuild a new analytics feature or dbt model guided by business requirements and data exploration
@yeaight7View CommandPerform a technical debt audit on the specified components and generate a prioritized remediation roadmap.
@yeaight7View CommandSystematically analyze a reported error, stack trace, or failure state to identify the root cause and propose a fix.
@yeaight7View CommandGather phase context through adaptive questioning before planning.
@yeaight7View CommandAudit the repository's documentation for broken paths, missing setup commands, and stale code blocks.
@yeaight7View CommandGenerate a comprehensive evaluation report for a trained model, highlighting performance, baselines, and subgroup metrics.
@yeaight7View CommandAudit an ML training script or pipeline for reproducibility, tracking, and basic hygiene before a long run.
@yeaight7View CommandAnalyze codebase with parallel mapper agents to produce .planning/codebase/ documents
@yeaight7View CommandUse to check MCP server prerequisites before activating or using a server.
@yeaight7View CommandUse to verify an MCP server starts and responds before adding it to an agent config.
@yeaight7View CommandBuild or refresh graph-backed memory for a corpus, using graphify first and helper conversions only when they improve corpus quality.
@yeaight7View CommandChoose the cheapest context path across direct read, markdown conversion, graph build, graph update, or graph query.
@yeaight7View CommandQuery an existing graphify graph before rereading the full corpus, using query, path, or explain flows.
@yeaight7View CommandReview a machine learning training run or experiment configuration for soundness, reproducibility, and evaluation rigor.
@yeaight7View CommandRecommend the best model tier for the current task based on complexity, risk, and budget.
@yeaight7View CommandPerform a comprehensive pre-PR check: summarize changes, analyze risk, and generate a review checklist.
@yeaight7View CommandExecute a comprehensive quality gate check (lint, test, build, format) before allowing code to merge.
@yeaight7View CommandRun formatter, linter, and type checks for a file or directory. Report remediation steps.
@yeaight7View CommandReview the README.md to ensure it functions as an executable contract for new developers.
@yeaight7View CommandDraft a step-by-step refactoring strategy for complex code changes to ensure behavior is preserved.
@yeaight7View CommandRun the complete release readiness pipeline (version checks, changelog, final quality gates) and assign a release confidence score.
@yeaight7View Command© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic
