Developer Tools & Repos Agent Skills for Zed

Start or standardize a new repository with privacy-first Git defaults, public/private visibility decisions, conservative ignore rules…

Use when creating a new repository, or auditing an existing repo's hygiene and developer tooling.

ALWAYS START HERE for any LangChain, Deep Agents, or LangGraph agent building project.

Legacy refactoring orchestrator. Use when user says 'refactor', 'modernize', 'clean up this mess', 'rescue', or when dealing with…

Internal skill. Synthesis guidance loaded via SKILL_HINTS by planner and bug-investigator when research files are available.

Research WoW addon development topics using CLI tools, Blizzard UI source, and documentation.

Resolve an active merge or rebase conflict, including safe renumbering of colliding plans and chronicles.

Resolve all PR comments using parallel processing.

Uses ResolveContext to extract services inside factory closures or custom extractors.

Use when creating data containers in Godot — custom Resources for configuration, items, stats, and editor integration

Respond to review comments on a PR after evaluation and fixes

Use when handling multiple resolutions — stretch modes, aspect ratios, DPI scaling, and mobile/desktop adaptation

Draft a clean, standardized REST/HTTP API specification as a Markdown document.

Restore local dev-only working-tree changes in the distributionprintplatformapi repo that stub out the Address API and point…

Retell AI multi env setup \u2014 AI voice agent and phone call automation.\n\

This skill should be used when the user asks "how should I configure retries", "why is the service still down after we fixed the cause"…

Comprehensive assistance with RevenueCat in-app subscriptions and purchases

Analyze uncommitted changes before committing.

Audit a Cursor plugin for marketplace readiness.

Review technical spec documents from completeness, feasibility, risk, and code consistency perspectives.

Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.