Testing & QA · For developers

Run wally's LLM e2e on Apple Neural Engine (NeuRT) and Snapdragon Hexagon NPU (QHexRT) devices.

RunanywhereAI/wally

Draft GitHub issues for the Gumroad codebase. An agent skill from antiwork/gumroad.

antiwork/gumroad

Interacts with local browser via Chrome DevTools Protocol (only triggered after user explicitly requests to inspect, debug, or interact with pages open in Chrome)

MatrixAges/polywise

Drives a browser through the agent-browser CLI, using compact snapshots with element refs to keep context small in long sessions, plus video recording and cloud browsers.

withkynam/vibecode-pro-max-kit

Guide a new contributor through the rundeck OSS repo. An agent skill from rundeck/rundeck.

rundeck/rundeck

Verify whether an exact T-SQL script is already supported by SqlScriptDOM, then add or update the correct parser tests and baselines.

microsoft/SqlScriptDOM

Chooses the right verification step after a code change in Pierre's monorepo: format and lint, a typecheck, Bun unit tests, snapshots, or Playwright E2E.

pierrecomputer/pierre

Cut a Stylebot release — CHANGELOG entry, version bump, release PR, tag, and store zips.

ankit/stylebot

Defines self-acknowledgments for production declarations and tests.

samchon/nestia

Define, validate, submit, or restart a Marin SkyRL experiment through its artifact main.

marin-community/marin

Run the full Stitch SDK generation pipeline. An agent skill from google-labs-code/stitch-sdk.

google-labs-code/stitch-sdk

Native Rust browser automation CLI for AI agents. An agent skill from gsd-build/gsd-browser.

gsd-build/gsd-browser

Analyzes recent CI failures on pull requests to identify flaky tests, using retry outcomes (failed attempt → green re-run) and cross-PR recurrence as evidence, and maintains a local longitudinal…

opsmill/infrahub

Set up and verify Anserini source-development environments. An agent skill from castorini/anserini.

castorini/anserini

Create an end-to-end Continual Learning Bench task. An agent skill from melandlabs/openloomi.

melandlabs/openloomi

A skill your agent uses when reviewing PRs, code changes, or conducting code audits in obsidian-terminal.

polyipseity/obsidian-terminal

Headless Google Meet bot that joins meetings and captures live captions as transcripts.

sumansid/openutter

智能读取任意URL内容，支持微信公众号、小红书、今日头条、抖音、淘宝、天猫、京东、百度等中国主流平台，自动识别平台类型并提取核心内容。自动保存内容为Markdown，下载图片到本地。

yhslgg-arch/url-reader

Drives a hidden, agent-owned Linux desktop and browser over MCP for GUI testing and web automation without touching the user's real desktop.

agent-sh/agent-workspace-linux

A skill your agent uses when smoke-testing cctop end to end — verifying a real coding-agent session is tracked and shows in the panel.

st0012/cctop

Runs the ONNX Runtime transformers Python tests against a GPU wheel and proves the cuDNN flash attention path was used rather than a silent fallback.

microsoft/onnxruntime

Verify web frontend behavior through real GUI interactions, read-only page inspection, and screenshots.

BytePioneer-AI/codex-host

Disciplined task execution with planning, verification, and self-improvement loops.

vxcozy/workflow-orchestration

tmux for AI agents. An agent skill from remorses/tuistory.

remorses/tuistory

A skill your agent uses when modifying EasyPostman Swing dialogs, popups, wizards, or modal flows to better match IntelliJ IDEA or FlatLaf settings-style visual hierarchy, especially when read-only…

lakernote/easy-postman

Fix and create Svelte 5 tests with vitest-browser-svelte and Playwright.

spences10/sveltest

Save a structured state snapshot the next session can resume from — active plan, decisions and why, file pointers with line numbers, open questions, next 1-3 actions, and what to deliberately forget.

ipea/geobr

Walks the sfdx-hardis training course end to end as a learner would, against a real Developer Edition org and fork, fixing broken steps and screenshots that no longer match.

hardisgroupcom/sfdx-hardis

E2E testing of kon using tmux sessions; IMPORTANT: only trigger this skill when user asks for e2e testing of kon

0xku/kon

A skill your agent uses when adding a new LLM provider to chatlas (a new Chat<Name() / <NameProvider in chatlas/provider.py) — covers the research phase, class and function structure, the standard…

posit-dev/chatlas

Creates phase-based feature plans with quality gates and incremental delivery structure.

serendipity1004/cc-feature-implementer

Guide for implementing features in ClaudeBar following architecture-first design, TDD, rich domain models, and Swift 6.2 patterns.

tddworks/ClaudeBar

Architecture-aware feature scaffolding for .NET 10 projects.

codewithmukesh/dotnet-claude-kit

A skill your agent uses when implementing features or fixing bugs with strict Test-Driven Development (TDD).

thedaviddias/skill-check

A skill your agent uses when you need to run the unslop repo, analyze a domain for repetitive AI defaults, generate a reusable skill file, and verify that the output is specific and materially…

mshumer/unslop

A skill your agent uses when the user explicitly asks for TDD or a tests-first workflow, or when developing a new feature with a test coverage requirement.

cloudnative-co/claude-code-starter-kit

Investigate and fix flaky/random CI test failures in dotnet/macios.

dotnet/macios

Read live production data from Bike Index through the admin OAuth token — Sidekiq and PgHero status, and the user-submitted bug reports — the same data as the cookie-gated dashboards, but…

bikeindex/bike_index

Write Jest integration and unit tests for the Grafana Synthetic Monitoring app using React Testing Library, MSW, and src/test helpers.

grafana/synthetic-monitoring-app

Adversarially review Meridian or scrub changes and preserve reproducible E2E, headless, and visual proof for PRs, critical fixes, merges, and releases.

rynfar/meridian

Add or change a Neru config.toml option end to end: struct field, shared and platform defaults, validation, examples, docs, and hot-reload behavior.

y3owk1n/neru

Drive the EnsoCode Electron renderer via Chrome DevTools Protocol on port 9222.

J3n5en/EnsoCode

Testing conventions for the NGINX Ingress Controller repo: Go table-driven tests, mandatory snapshot regeneration, Helm tests and Python pytest integration tests.

nginx/kubernetes-ingress

Captures PNG or JPEG screenshots and MP4 or GIF clips of cmux windows from the command line, as visual evidence for pull requests and bug reports.

manaflow-ai/cmux

Collapse test-shaped production boundaries while preserving behavior and coverage.

EpicenterHQ/epicenter

Reads your git diff, writes a handful of happy-path browser smoke tests, runs them with Skyvern or Chrome DevTools MCP and posts screenshot evidence to the PR.

Skyvern-AI/skyvern

Run the Antigravity CLI (Gemini) as a collaborating AI inside Claude Code, with intelligent model routing across the software development lifecycle.

yuting0624/antigravity-for-claude-code

Uploads screenshots and other images from the terminal and returns markdown-ready URLs to embed in GitHub pull requests, issues and comments.

trekawek/coffee-gb