5,556 tagged Testing, measured the same way as everything else here.
Browse within: agentic-workflow 44agentic-coding 36agent-orchestration 30ai-development 29code-quality 28bug-bounty 27spec-driven-development 26gemini 25claude-plugin 24ai-coding-assistant 22ai-skills 22agentic 21ai-assistant 21ai-workflow 21
Command
Verify a saved Brand Profile. Reports QA findings and a verdict (the role map lives in PROFILE.md; verify does not render a proof). Add --accept to mark a passing profile as accepted.
Command Claude Code
You are running an empirical test comparing .context documentation vs single CLAUDE.md.
Command Claude Code
You are scoring a test output for the .context vs CLAUDE.md comparison study.
Command Claude Code
Test UniFi MCP server across discovered environments, create GitHub issues for failures, and trigger @claude automated fix workflow.
Command Claude Code
Generate a new HydrAIDE data model (Profile or Catalog) with RegisterPattern boilerplate and a test scaffold.
Command
Preserved client-extension command fixture.
Command Claude Code
Run the prompt-eval suite and report scores against the ship thresholds.
Command
Run a task as a bounded, gate-verified loop backed by SuperLocalMemory — iterate until an independent gate passes, never on the agent's own claim.
Command
Start the dev server on a free port.
Command
Run the project's unit test command (pnpm test:ci, bun test, or equivalent). Report failures with file:line references.
automazeio/claude-code-for-power-users
Command
When analyzing large codebases or multiple files that might exceed context limits, use the Gemini CLI with its massive context window. Use gemini -p to leverage Google Gemini's large context capacity.
Command
Run tests for a cli-anything-web CLI and update TEST.md with results.
Command
Validate a cli-anything-web CLI against the tiered quality checklist (Tier 1 critical / Tier 2 comprehensive). Reports per-category and per-tier results.
Command
🚀 Enhanced with Local Validators: This command now uses local JavaScript validators for D1, D2, and D3 dimensions to significantly reduce token consumption while maintaining evaluation quality. Complex reasoning tasks (D4, D5, D6) continue to use LLM evaluation with local pre-analysis.
harunkurtdev/ros2-claude-code-template
Command Claude Code
Scaffold a ros2control controller or broadcaster — base class, command/state interface config, RT-safe update(), generateparameterlibrary, pluginlib export, and a test.
Command Claude Code
Generate a complete PRP for general feature implementation with thorough research. Ensure context is passed to the AI agent to enable self-validation and iterative refinement. Read the feature file first to understand what needs to be created, how the examples provided help, and any other considerations.
Command Claude Code
A command that runs the project's full local checks in a fixed order: frontend linting, tests, frontend build, and Rust compilation checks. Linting checks code style and common mistakes; a build check confirms the application can be compiled.
Command Claude Code
A command that asks the coding agent to carry out the user's request, passed through as command arguments.
Command Claude Code
A command for fixing a defect described by the user or identified by a ticket number, within the current module's boundaries.
Command Claude Code
A command for reviewing the current code difference—the changes between the working files and the previous version—across four areas and giving a verdict.
Command Claude Code
Comprehensive CLI for creating, managing, and interacting with iOS, tvOS, watchOS, and visionOS simulators.
Command Claude Code
Let's commit the changes. Run tests, typechecks, and format checks. Then commit, push, and create a pull request.
Command Claude Code
Analyze and optimize context configuration. Reviews CLAUDE.md, knowledge-core.md, and active context for optimization opportunities. Helps prevent context rot (39% improvement, 84% token reduction).
Command Claude Code
Quick command to invoke code-implementer to execute implementation with self-correction (up to 3 intelligent retries).