Large refactors can change behavior and hide regressions. This skill guides Claude, Codex, and Claude Code through small tested changes with commits after each safe step.

SharePoint permission reviews expose sensitive access paths but can be hard to collect consistently. This skill guides a local audit that produces readable reports.

Bitbucket pipeline failures are slow to inspect across dashboards and large logs. This skill lets agents query runs, analyze failures, and manage selected workflows.

Frontend changes can hide lint violations and type errors. This skill runs ESLint and TypeScript checks, then reports actionable results before any fixes.

Starting multi-service apps often requires repeated setup checks and commands. This skill guides Claude, Codex, or Claude Code through backend and frontend startup steps.

Adding feed events often requires coordinated TypeScript, React, rendering, and WebSocket changes. This skill provides a focused workflow that follows existing project conventions.

Adding backend agent tools requires coordinated changes across implementation, schemas, dispatch, and permissions. This skill provides a focused workflow for those changes.

Collecting structured data across many platforms requires different tools, schemas, and cost controls. This skill guides Actor selection, execution, result retrieval, and troubleshooting through Apify.

Adding managed scraping and automation requires correct client setup, Actor inputs, and result handling. This skill provides practical Apify integration patterns for common application workflows.

Building production-ready Actors requires coordinated code, schemas, tests, deployment settings, and documentation. This skill guides that workflow for scraping, automation, and HTTP services.

Blockchain event bots require precise triggers, network settings, and safety controls. This skill guides Silverback bot design, project structure, testing, and operation.

Uniswap integration requires current SDK knowledge and careful transaction planning. This skill guides Ape-based pricing, routing, swaps, and Silverback automation with practical safeguards.

Release notes often miss the app changes users care about. This skill reviews Git history, follows existing Fastlane style, and updates the latest changelog.

Unit tests often drift from project conventions and become hard to maintain. This skill gives Claude, Codex, and Claude Code a focused workflow for creating reliable tests that match Android and Kotlin project standards.

Adding libraries without review can create version drift and unnecessary maintenance. This skill guides approval, version discovery, catalog updates, and build verification.

Multi-account browser setups can leak identity through shared storage, mismatched network signals, or unstable fingerprints. This skill provides repeatable checks for authorized profiles, QA fixtures, and anti-fraud testing.

Agents often lose login state and get blocked by headless browser signals. This skill gives Claude, Codex, and Claude Code a persistent fingerprinted browser they can drive through MCP tools for authorized workflows.

Browser tests can fail when fingerprints, sessions, and regional signals are inconsistent. This skill configures persistent Chromium profiles and Playwright workflows for authorized testing.

Stripe offers several APIs, and outdated choices can create migration or payment risks. This skill recommends current integration patterns for payments, subscriptions, and platforms.

Skill authors need a clear reference for structuring and describing plugin skills. This guide explains required files, optional resources, frontmatter, activation wording, and practical design guidelines.