Software Development Skills

Question-led planning gate for implementation work. Use when the user wants a project plan, roadmap, feature plan, technical design, implementation plan, migration plan, product workflow, architecture change, or any substantial build before code changes begin. Forces the agent to repeatedly question assumptions, resolve ambiguity, identify risks and dependencies, and reach an explicit shared understanding before implementation starts. For small, low-ambiguity changes it runs a lightweight pass (assumptions stated, only blocking questions asked) instead of the full gate.

Review an existing codebase for redundant, legacy, dead, superseded, or attack-surface-increasing code paths and guide progressive removal with behavior mapping, test coverage, security review, and validation. Use when asked to remove old providers or integrations, clean redundant code paths, reduce tech debt, reduce attack surface, review dead code, retire obsolete routes, remove stale compatibility layers, or clean up after migrations such as Google Drive uploads to Vercel Blob.

Vercel-first, provider-aware review and remediation workflow for web app error logging. Use when a user asks to audit, add, fix, harden, or verify logging, error capture, runtime observability, error boundaries, structured logs, correlation IDs, alerting evidence, or production debuggability in an existing web app.

Tool-agnostic feature design preflight that traces a requirement through production constraints, dependencies, user and system flows, edge cases, security, operations, and tests before implementation. Use before implementing nontrivial features or integrations, especially uploads, media or video, PDFs or documents, file parsing, third-party APIs, long-running operations, background jobs, data migrations, auth or permissions, payments, admin or user portal workflows, AI calls, storage, or any request where a naive implementation could satisfy a surface requirement but fail in real use. Use when the agent must stop and clarify if requirements, provider limits, library choices, failure behavior, or verification are unclear.

Ensure frontend design work follows established repo patterns, minimizes clicks, fills real viewports, stays responsive, avoids text overflow, reduces portal UI clutter, covers content-rich surfaces such as blogs/resources, and is verified with Playwright or equivalent visual screenshots. Use when building, changing, or reviewing frontend UI, pages, portals, dashboards, navigation, forms, content systems, responsive layouts, or user-facing flows in a repo.

Orchestrate a full non-mutating app or repo review across architecture, live flows, frontend quality, testing and coverage, security, observability and error instrumentation, analytics, dependencies, deployment, validation readiness, and redundant code paths. Use when the user asks to fully review an app or repo, perform a full app review, app audit, production readiness review, end-to-end review, comprehensive codebase review, or asks what should be fixed before implementation, push, merge, or production.

Keep this macOS developer laptop current without unsafe repo mutation. Use when asked to update Homebrew, PowerShell, Vercel CLI, Node, gh, dotnet, global developer tooling, package currency, stale CLIs, or to keep the laptop up to date while safely auditing local repo dependencies.

Add privacy-safe Vercel Web Analytics to Next.js apps, including pageview setup, typed client and server custom events, strict no-PII payload rules, App Router or Pages Router placement, and local verification. Use when a user asks to add, implement, instrument, review, or fix Vercel analytics, Vercel Web Analytics, analytics custom events, product tracking, funnel tracking, frontend or backend event tracking, or analytics privacy in a Next.js repo.

Fully automatic GitHub PR review and production deployment gate for trusted repos. Use when configuring or operating a scheduled PR gate that checks open PRs, downloads them locally, runs complete containerized validation with mocked external services, comments or rejects failing PRs, promotes passing PRs through preview and production deployment branches, and updates repo-specific learning so repeated failures are handled before the next run.

Exhaustively document an existing repository's technical architecture and implementation details. Use when asked to work through a whole repo and create, update, reconcile, or refresh technical docs covering API endpoints, UI routes and choices, frameworks, libraries and rationale, data models, integrations, jobs, testing, deployment, observability, operational scripts, or stale documentation.

Pre-test readiness workflow that finds and fixes predictable validation blockers before running expensive local or container test gates. Use before full verification, before push readiness checks, after substantial implementation, or when work is likely to hit common failures such as missing unit/integration/E2E coverage, unseeded or stale test databases, unapplied migrations, production schema not ready for deployed code, missing fixtures, Playwright browser setup gaps, stale snapshots, container drift, env/test-double gaps, unsafe broad gitleaks scans, lockfile/package drift, or CI-only assumptions.

Impact-scoped review that maps user actions, critical paths, roles, states, and mutations to Playwright/E2E plus unit/integration evidence. Use after an accepted plan and before implementation for substantial feature, frontend, workflow, route, mutation, auth/role, upload, save/delete, navigation, admin/user portal, or release-readiness work; rerun before final validation if scope changes.