MCP App StoreMCP App StoreOffload provides a parallel test runner that distributes test execution across sandboxes (local processes or remote Modal environments). This skill teaches how to invoke Offload, read run summaries and logs, debug failures, and tune retry/config groups for flaky tests. Concrete examples cover calling existing project wrappers, using offload run with common flags, and fallbacks when sandboxes are unavailable.
Use this skill when running integration or end-to-end suites, when total test runtime is large (>~2 minutes), when multiple contributors compete for local CPU, or when a repository contains offload.toml or offload invocations in build scripts. Avoid for single-test TDD loops or when tests rely on local-only hardware.
offload run, offload logs, offload collect, config group examples for retries, and common failure patterns and fixes.Best used by code-capable assistants (Copilot/Codex/Gemini/Claude Code) that can edit configs and suggest CLI invocations or CI changes.
Offload is a parallel test runner skill that distributes test execution across local/Modal sandboxes. The SKILL.md is comprehensive with clear invocation patterns, debugging guides, failure pattern tables, and config reference. No bundled scripts — purely instructional. Clean security posture with no risky patterns detected.
Well-crafted skill for a niche tool. The documentation quality is high — clear trigger conditions, progressive disclosure, and practical troubleshooting tables. Only concern is auto-push of git notes which could be unexpected in some workflows.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
ds-fix — data-science mid-analysis fixer
Orchestrates diagnosis and targeted fixes mid-analysis: diagnose root cause, apply fixes with output-first verification, and update project learnings.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.
Tmux Bridge
Give an agent controlled access to a local tmux terminal bridge so it can run shell commands, capture output, and manage sessions on the user's machine.
Replit — Advanced Troubleshooting
Step-by-step diagnostics and debugging techniques for deep Replit issues: Nix build failures, container crash loops, memory leaks, and platform vs app isolation
Juicebox Common Errors
Identify and remediate common Juicebox API errors (authentication, quotas, rate limits, invalid queries) with quick diagnostics and fixes.
Vercel Common Errors
Diagnose and fix common Vercel build, serverless runtime, and edge/routing errors with step-by-step checks and fixes.