Loading...
Loading...
Found 1,594 Skills
Requires detailed type annotations for all Python functions, methods, and class members.
Build, validate, and deploy LLM-as-Judge evaluators for automated quality assessment of LLM pipeline outputs. Use this skill whenever the user wants to: create an automated evaluator for subjective or nuanced failure modes, write a judge prompt for Pass/Fail assessment, split labeled data for judge development, measure judge alignment (TPR/TNR), estimate true success rates with bias correction, or set up CI evaluation pipelines. Also trigger when the user mentions "judge prompt", "automated eval", "LLM evaluator", "grading prompt", "alignment metrics", "true positive rate", or wants to move from manual trace review to automated evaluation. This skill covers the full lifecycle: prompt design → data splitting → iterative refinement → success rate estimation.
Guide for automating Chrome browser interactions using the rodney CLI. This skill should be used when performing web automation tasks such as navigating to pages, taking screenshots, clicking elements, filling forms, extracting page content, or any other browser-based interaction.
Guide for how to develop Go apps and modules/libraries. Always use this skill when reading or writing Go code.
Perform a high-level flow audit of an implementation plan, analyzing phase-to-phase dependencies, data flow consistency, ordering logic, stale artifacts, and risk assessment. Use when asked to 'audit the plan', 'check plan flow', 'review plan dependencies', 'find plan discrepancies', or 'assess plan coherence'. Do NOT use for per-phase template compliance (use /review-plan) or creating plans (use /create-plan).
Write, review, or debug end-to-end tests using Playwright. Use when asked to 'write e2e tests', 'add Playwright tests', 'test this user flow', 'fix flaky tests', 'create a test suite', or 'debug this e2e failure'. Invoke with /playwright-e2e or when user mentions e2e tests, Playwright, or test automation. Do NOT use for live browser interaction via MCP tools — use playwright-mcp for that. Do NOT use for unit/integration tests — use tdd-guide agent instead.
Create client-side forms with react-hook-form, shadcn/ui form components, and server action integration for Next.js/Supabase applications. Use when building forms with validation, error handling, and loading states ('create a form', 'build the settings form', 'add form validation', 'wire up the edit form'). Generates complete form components with Zod schemas, toast feedback, and data-test attributes. Do NOT use for server-side logic (use server-action-builder or service-builder), database schemas (use postgres-expert), or E2E tests (use playwright-e2e).
Improve a rough or thin prompt into a detailed, actionable one using project context. Use when the user types '/improve-prompt <rough idea>' or '/?? <rough idea>'. Takes a vague request and returns a well-structured prompt with specific file paths, project patterns, acceptance criteria, and relevant context. Do NOT use for executing tasks — this only improves the prompt text.
Regression troubleshooting workflow for hook/router/memory/search failures with enforced evidence and fix validation
Provides SEO and Meta Tags guidelines in SvelteKit.
Specifies standards for RestController classes, including API route mappings, HTTP method annotations, dependency injection, and error handling with ApiResponse and GlobalExceptionHandler.
Specifies the preferred syntax for asynchronous operations using async/await and onMount for component initialization. This results in cleaner and more readable asynchronous code.