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
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
Skill Claude CodeCodex
Commit hygiene and self-contained pull requests. Highlights production impact, uses gh CLI for opening/updating PRs, and adding proof comments (test runs, coverage reports).
Skill Claude CodeCodex
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
Skill Claude CodeCodex
Write production-grade Deno code with secure-by-default permissions, deliberate import and dependency strategy, testing conventions, and Node/npm interoperability rules. Use when authoring, reviewing, or migrating Deno applications, libraries, CLIs, scripts, or deno.json task workflows. Do NOT use for generic…
Skill Claude CodeCodex
Rules for ESM-first TypeScript projects using "type": "module" with moduleResolution: "nodenext". Contains 4 rules targeting the most common ESM runtime errors.
Skill Claude CodeCodex
Guide writing, configuring, testing, and migrating Firebase Cloud Functions for Node.js (JavaScript/TypeScript). Distinguish v1 (deprecated) from v2 functions by import path. Use when writing a new Cloud Function, adding a trigger (HTTP, PubSub, Firestore), configuring environment or secrets, testing functions locally…
Skill Claude CodeCodex
Use when the user wants to infer HTTP contracts and endpoint documentation from a React or TypeScript frontend instead of relying on a backend-owned source of truth.
Skill Claude Code
Query and extract Google Cloud Logging entries using the Logging query language DSL and gcloud CLI. Covers Cloud Run, Firebase Functions (1st gen), GKE, Compute Engine, and other GCP resource types. Use when the user asks to read logs, debug Cloud Run errors, tail Firebase Functions output, build Logging filters…
Skill Claude CodeCodex
Set up and use Google Cloud Error Reporting in Node.js applications. Explains when to rely on automatic error capture (Cloud Run / Cloud Run functions) vs the @google-cloud/error-reporting client library, and how to format Cloud Logging entries so Error Reporting ingests them. Use when the user asks about Error…
Skill Claude CodeCodex
Provides OpenTelemetry explicit instrumentation methodology and Google Cloud LogEntry formatting rules for Node.js workloads. Use when instrumenting Cloud Run services or Firebase Functions gen2, correlating traces with logs, configuring structured logging, or integrating with Cloud Error Reporting.
Skill Claude CodeCodex
Verify whether a GitHub issue is implemented in the current codebase by collecting evidence from the GitHub issue, git history, docs, code, and tests, then producing a structured report with verdict, proof, gaps, confidence, and scope-clarity doubts. Use when the user asks whether an issue was resolved or whether a…
Skill Claude CodeCodex
Create and update GitHub pull requests using gh CLI for repositories that use a .github/pullrequesttemplate.md with comment markers. PRs are written in Brazilian Portuguese and staged in .work/ body files. Use when the user asks to create a PR, open a PR, update a PR description, or prepare a PR body.
Skill Claude CodeCodex
Rewrite a PR body around what a reviewer actually needs. Use for "distill this PR", "tighten the description", "this body is a thesis", or after a long implementation session where the PR body grew with the investigation.
Skill Claude CodeCodex
Use when creating, reviewing, or hardening GitHub Actions CI/CD workflows where deployment topology, promotion safety, release identity, cache discipline, OIDC, environments, or production readiness matter.
Skill Claude CodeCodex
Use when authoring or reviewing Go command-line applications, especially when deciding command grammar, output contracts, exit codes, config precedence, thin CLI architecture, testing strategy, automation safety, or agent-friendly behavior.
Skill Claude CodeCodex
Go package documentation (doc.go) following official conventions. Use when creating package-level documentation, writing doc.go files, or ensuring compliance with go doc, godoc, and pkg.go.dev standards. Triggers on tasks involving package comments, API documentation, or Go documentation review.
Skill Claude CodeCodex
Build and review server-side HTMX applications with Hono using typed HTMX attributes, architecture-first route design, and production-safe server patterns. Use when creating a new Hono + HTMX app, choosing page and fragment boundaries, or implementing HTMX-driven forms, navigation, realtime flows, and partial page…
Skill Claude CodeCodex
Write, execute, and assert HTTP requests safely using Hurl text files. Triggers on API testing, HTTP request generation, REST/GraphQL validation, or when .hurl files are mentioned. Do NOT use this skill for UI/browser testing or for internal unit testing.
Skill Claude CodeCodex
Type-safe SQL query building in TypeScript using Kysely. Use when writing or reviewing Kysely queries, schema types, migrations, raw SQL snippets, dynamic filters, conditional selects, transactions, or reusable query helpers.
Skill Claude Code
Use when the user wants to audit, tidy, or reality-check a Linear board using MCP-first evidence, especially for project hierarchy, labels, statuses, stale work, and whether Linear reflects the current state of work.
Skill Claude CodeCodex
Design and review repository-local agent guidance using root and nested AGENTS.md, .cursor/rules, skills, packs, and optional pack-bundled skills. Use when organizing monorepo AI instructions, deciding where routing knowledge should live, or authoring directory-specific AGENTS.md files for Cursor-first projects.
Skill Claude CodeCodex
Scaffold and maintain Nx monorepo structure with hexagonal architecture, project tags, TypeScript project references, and npm workspaces linking. Use when creating new apps/libs/tools, fixing build or linking errors, configuring project tags, or enforcing module boundary rules.
Skill Claude CodeCodex
Expert guidance for configuring and deploying the OpenTelemetry Collector. Use when setting up a Collector pipeline, configuring receivers, exporters, or processors, deploying a Collector to Kubernetes or Docker, or forwarding telemetry to Dash0. Triggers on requests involving collector, pipeline, OTLP receiver…
Skill Claude CodeCodex
Configures OpenTelemetry trace spans, metrics, and log exporters. Use ONLY when instrumenting applications specifically with OpenTelemetry (OTel). Triggers on requests explicitly mentioning OpenTelemetry, OTel, or OTLP.
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: