My personal official collection of agent skills, react ones forked from vercel
This repository also configures its own agents. See what agent-skills tells them →
Skill Claude CodeCodex
OpenTelemetry Transformation Language (OTTL) expert. Use when writing or debugging OTTL expressions for any OpenTelemetry Collector component that supports OTTL (processors, connectors, receivers, exporters). Triggers on tasks involving telemetry transformation, filtering, attribute manipulation, data redaction…
Skill Claude CodeCodex
OpenTelemetry Semantic Conventions expert. Use when selecting, applying, or reviewing telemetry attributes. Triggers on tasks involving attribute selection, semantic convention compliance, attribute migration, or custom attribute decisions. Covers the attribute registry, naming patterns, attribute placement, and…
Skill Claude CodeCodex
Route Node.js/TypeScript backend security questions to the matching OWASP Top 10 category and the correct library reference (express, mysql2). Use when securing Express endpoints, parameterizing mysql2 queries, hardening sessions/headers/CORS, or classifying a finding as A01–A10. Do NOT use for React/frontend XSS…
Skill Claude CodeCodex
Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.
Skill Claude CodeCodex
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…
Skill Claude CodeCodex
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
Skill Claude CodeCodex
Classicist TDD methodology — test-first Red-Green-Refactor cycle, Meszaros test-double taxonomy (dummy/fake/stub/spy/mock), tiered test pyramid (unit → boundary integration → functional → contract → regression → E2E), assertion policies, and contracts-as-spine doctrine. Use when writing tests, choosing test doubles…
Skill Claude CodeCodex
Verify working-tree changes against an 8-tier test pyramid. Runs the right tests for changed files, collects coverage from instrumentable tiers, and returns a structured verification report. Use when the agent modifies production code, the user asks to run tests or check coverage, or the gh-pr-creator skill needs…
Skill Claude CodeCodex
Use when writing or reviewing TypeScript tests, choosing between unit, contract, integration, and end-to-end layers, isolating database or HTTP seams, or fixing flaky, non-hermetic, or mis-layered test suites.
Skill Claude CodeCodex
Ensures all public TypeScript functions, variables, types, and modules are clearly documented with their purpose and provided APIs.
Skill Claude CodeCodex
Use when authoring or reviewing production TypeScript modules, choosing layer and suffix boundaries, modeling domain objects and ports, deciding error ownership, or wiring validation and observability at system boundaries.
Skill Claude CodeCodex
Design and audit TypeScript types as a modeling discipline — making illegal states unrepresentable and encoding domain truth — NOT as a mechanical lint pass. Use whenever the user is modeling a new type, reviewing or refactoring existing types, or asking whether a type is well shaped: "how should I model X", "is this…
Skill Claude CodeCodex
Provides structured error handling patterns for TypeScript, drawing from ZIO principles. Helps distinguish between expected domain errors and unexpected defects. Use when designing API boundaries, handling complex failure scenarios, deciding between thrown exceptions and result types (neverthrow), or ensuring…
Skill Claude CodeCodex
TypeScript test file suffixes, directory layout, tier targeting, and mechanical enforcement. Encodes the .spec tier-suffix policy (.spec.ts, .int.spec.ts, .func.spec.ts, .contract.spec.ts, .e2e.spec.ts), test/support/ conventions (builders/seeds/fakes/stubs/ spies/msw), and audit scripts. Use when naming TS test…
Skill Claude CodeCodex
Configure Vitest in monorepo workspaces with correct workspace root, import.meta.url pattern, and workspace-relative include paths. Use when Vitest shows 0 tests, test discovery fails, or setting up vitest.config.ts in npm/yarn/pnpm workspaces.
Skill Claude CodeCodex
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Skill Claude CodeCodex
Reclaim disk space from git worktree pools by deleting reproducible nodemodules trees from worktrees that show no sign of active work, gated on clean tree, fully-pushed commits, no open files, idleness, and a sibling lockfile. Use when a worktree directory has grown to many GB, when asked why /worktrees is so large…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: