Browse the directory

Instrument AI agent systems with high-signal telemetry and runbook-driven incident response for reliability and safety.

Expert MCP capability skill for secure server authoring, tool schema discipline, authorization boundaries, and prompt-injection risk review.

Official AWS Labs MCP server for Amazon SNS and SQS that lets AI assistants list and manage SNS topics, subscriptions, and SQS queues and send/receive messages, with resource tagging so it only modifies what it created.

Expert Claude Code Chrome browser QA capability pack applying documented Claude in Chrome enablement, browser automation boundaries, and web QA checkpoint workflows.

Community reusable agent prompt for end-to-end GUI validation with Claude Code computer use using official documentation: enable the computer-use MCP server, per-app session approval, screenshot checkpoints, and documented example workflows for native apps.

Expert GitHub Actions security review capability pack applying documented workflow hardening, GITHUB_TOKEN least privilege, secrets handling, and fork PR safety checks from official GitHub Actions security documentation.

Expert subagent foreground background delegation capability pack for choosing when to run Claude Code subagents interactively versus in the background, coordinating parallel work, and returning summarized results safely.

Expert Claude Code deep links runbook capability pack for building safe claude-cli:// URLs, embedding them in incident runbooks, and validating cwd, repo, and prompt parameters before users press Enter.

Source-backed agent for reviewing Atlas database schema migrations with migration lint, analyzers, drift detection, CI/CD evidence, dev-database simulation, rollout risk, rollback planning, and production safety gates.

Source-backed agent for reviewing local-first Jupyter notebook workflows that use Jupytext text notebooks, paired notebooks, command-line sync, and version-control friendly reproducibility checks.

Add Better Auth to a Next.js App Router project with API route handlers, database-backed sessions, client helpers, protected route checks, and production auth safety review.

Add Clerk authentication to a Next.js App Router project with middleware, route protection, session-aware UI, environment hygiene, and production auth safety checks.

PreToolUse hook that inspects a database migration before it is written and blocks irreversible or lock-heavy operations — DROP TABLE/COLUMN, TRUNCATE, table/column RENAME, and CREATE INDEX without CONCURRENTLY — following the strong_migrations safe-migration checks.

Design and review Drizzle ORM schemas, typed SQL queries, drizzle-kit migrations, database-first pulls, codebase-first generates, and production migration safety plans.

Add or maintain next-intl internationalization in a Next.js App Router project with messages, request configuration, locale-based routing, proxy or middleware behavior, Server and Client Components, typed message keys, localized navigation, SEO review, testing, and rollout planning.

Source-backed Claude agent prompt for contributing to the official Vercel AI SDK monorepo using its AGENTS.md guidance, pnpm workspace commands, package build and test boundaries, provider architecture, Zod compatibility rules, JSON parsing safety, ADR review, and documentation sources.

Source-backed rules for reviewing AI-generated regular expressions before merge, covering catastrophic backtracking and ReDoS risk, input bounds, anchor and escaping correctness, validation versus parsing, safe engines, and privacy-safe test evidence.

Source-backed rules for reviewing event-sourcing implementation changes, covering immutable event design, event schema evolution without breaking projections, idempotent event handlers, snapshot and replay correctness, and consistent event-store access patterns.

Transform Claude into a Kotlin specialist with deep knowledge of coroutines, null safety, data classes, sealed types, and JVM/Android API design patterns.

Expert capability pack for drafting accurate safetyNotes and privacyNotes on HeyClaude hooks, MCP servers, skills, commands, and statuslines using CONTRIBUTING.md disclosure requirements and submission examples.

A maintainer guide for securing agentic coding workflows in open-source repositories: version-controlled MCP configs, permission defaults, contributor PR review for AI-generated changes, hooks, sandbox boundaries, and public disclosure hygiene.

Source-backed Claude Code subagent prompt for reviewing Agent Skills before adoption or publication, checking SKILL.md scope, descriptions, invocation control, supporting files, tool permissions, helpfulness, safety, and privacy risks against official Claude Code skills guidance.

Source-backed rules for reviewing production database migrations before merge with lock-risk checks, expand-contract rollout, backfill controls, rollback limits, and privacy-safe migration evidence.

A Stop hook that runs npm audit, pip-audit, safety, or bundler-audit automatically at the end of every Claude Code session, detecting CVEs and outdated packages across Node.js, Python, and Ruby projects.

PreToolUse Bash guardrail implementing the Claude Code hooks guide drop-table example: exit 2 with stderr feedback when Bash command text contains a case-insensitive DROP TABLE pattern.

A source-backed safety checklist for introducing Claude Code hooks with scoped events, minimal authority, reviewable commands, clear ownership, and a rollback path.

Use Claude Code's built-in checkpointing: run /rewind or press Esc twice to restore code, conversation, or both to an earlier point in a session, and summarize parts of the chat.

Automatically creates timestamped backups of files before modification to prevent data loss. This hook runs before file editing operations (Edit, Write, Multiedit) and creates versioned backups in a centralized .backups directory with ISO 8601-compliant timestamps including nanoseconds for collision prevention.

A Stop hook that syncs your changed files to cloud storage when a Claude Code session ends, using rclone to push to S3, Google Cloud Storage, or any of its 70+ supported backends.

Prevents direct edits to protected branches like main or master, enforcing PR-based workflows.