Agent Skills: evaluation
Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.
ID: abdullah1854/ClaudeSuperSkills/evaluation
1
Install this agent skill to your local
Skill Files
The files that make up evaluation.
Loading file tree…
More agent skills
- swiftui-performance-auditSwiftUI performance: render, scroll, CPU/memory, updates, layout, Instruments.
- react-native-testingGenerate and write tests for React Native applications using React Native Testing Library (RNTL), Jest, and userEvent. Use this skill when the user asks to write tests, create test files, add unit tests, add component tests, or generate test suites for React Native or Expo projects. Also use when working with .test.tsx files, jest.config.js, or when the user mentions testing React Native components, screens, hooks, or forms. Covers getByRole, getByText, getByLabelText queries, userEvent.press, userEvent.type interactions, waitFor, findBy async patterns, and toBeOnTheScreen matchers.
- internal-dev-workbenchSpin up a portless + tmux dev session for the Workflow SDK that gives each git worktree isolated `<branch>.<name>.localhost` URLs for the Next.js workbench and the observability UI, plus a Claude statusline that surfaces those URLs. Use only when the user asks for a "portless dev session", a "tmux dev layout for workflow", "worktree-isolated dev URLs", or wants to wire workflow dev URLs into the Claude statusline. Do not activate for the generic "start the dev server" / "run pnpm dev" task.
- firebaseFirebase gives you a complete backend in minutes - auth, database, storage, functions, hosting. But the ease of setup hides real complexity. Security rules are your last line of defense, and they're often wrong. Firestore queries are limited, and you learn this after you've designed your data model. This skill covers Firebase Authentication, Firestore, Realtime Database, Cloud Functions, Cloud Storage, and Firebase Hosting. Key insight: Firebase is optimized for read-heavy, denormalized data. I
- plain-upgradeUpgrades Plain packages and applies required migration changes. Use when updating to newer package versions.
- render-envAdd a new Terraform Cloud variable for the Render-hosted backend across production, sandbox, and test. Declares the tfe_variable in terraform/global/{production,sandbox,test}.tf and the matching variable {} block in terraform/{production,sandbox,test}/variables.tf, then reminds the user to wire it into render.tf / the render_service module.