Best QA and bug reports skills, page 2

Drives Qwen Code in a real tmux session the way a user would and saves a readable step-by-step transcript of each screen for maintainers to review.

QwenLM/qwen-code

Run and debug MoaV's end-to-end tests — real protocol connectivity (client-test.sh) and the moav CLI smoke test — against a LIVE server, via the self-hosted e2e workflow or a local test VPS.

MotherofallVPNs/MoaV

Attaches OpenCode browser tools to the OpenWork Electron dev app through CDP to explore its UI, send a composer task and debug, not to give test verdicts.

different-ai/openwork

Handles deduplication of YouTrack issues. An agent skill from JetBrains/ideavim.

JetBrains/ideavim

A skill your agent uses when fixing a Roslynator analyzer false positive or false negative, RCS, RR, or CS/RCF regression, incorrect diagnostic reporting, or bug report citing a specific rule id —…

dotnet/roslynator

Drives and verifies the native macOS Prowl Debug UI through accessibility automation, proving behavior with before-and-after evidence instead of reasoning from code.

onevcat/Prowl

Validates ROSClaw simulation workflows across MuJoCo, ROS 2, Gazebo and Isaac Sim with evidence-backed smoke tests, never touching a real robot.

ros-claw/rosclaw

Spins up an isolated Omnigent server, runner and mock model to prove a user-facing behavior or bug fix with recorded evidence instead of reasoning from code.

omnigent-ai/omnigent

Diagnose a termio hang, beachball, crash, or 'it froze again' from the evidence macOS and termio actually leave behind — live process samples, crash and CPU-burn reports, the unified log, the…

termio-sh/termio

Process conversations or chat logs to identify reported bugs, search for existing GitHub issues, update existing issues when new undocumented details are discovered, and create new issues for…

damus-io/damus

Author a new CORAL task — the three pieces that must line up (task.yaml, seed/, a packaged grader/), the coral init → coral validate → smoke-test loop, and how to pick a grader pattern (stdout…

Human-Agent-Society/CORAL

Run a GitHub issue digest for openai/codex by feature-area labels, all areas, and configurable time windows.

deonmenezes/mantishack

Reproduces an OpenROAD GitHub bug from an attached tarball and shrinks the failing design with whittle.py so maintainers get a minimal test case.

The-OpenROAD-Project/OpenROAD

Expert guidance on iOS accessibility best practices, patterns, and implementation.

dadederk/iOS-Accessibility-Agent-Skill

Turns a description into a structured bug report, or scans code for likely bugs, then verifies and closes reports through four modes.

Donchitos/Claude-Code-Game-Studios

A gate before merge: verify runs the real app against the spec, and review has a different model do a senior code review, without editing code.

jsmastery-pro/skills

Triage, debug, fix, and document issues for the Static Web Server (SWS) project — bug reports, root cause analysis, fix implementation, and regression prevention

static-web-server/static-web-server

Performs manual hands-on testing of a web application using playwright-cli.

ktnyt/cclsp

Verify frontend changes end to end after editing a web app, instead of manually clicking through pages.

ucsandman/marketing-studio

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

antiwork/gumroad

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

marin-community/marin

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

castorini/anserini

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

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

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

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

Controls a running Tiny game engine over its local debug HTTP server, sending key presses, releases and taps so the agent can play or test the game.

minigdx/tiny

A skill your agent uses when creating, migrating, or optimizing skills for this alicloud-skills repository.

cinience/alicloud-skills

Run jit's pre-release QA — a team of QA-engineer subagents (functionality, integrations, UX, bug-hunting, code review) that exercise a release candidate on this real Mac and hand back a consolidated…

jitpass/jit

Selectively monitor important long-running or resource-intensive commands with Haoleme by prefixing them with hao, so status, output, and completion notifications sync to the mobile app.

HaolemeApp/Haoleme

Run E2E browser tests on any web application using Glance MCP.

DebugBase/glance

Build, review, or fix ProjectAtlas plugin/runtime installer integration for Codex, Claude Code, and OpenCode, especially version convergence, stale ProjectAtlas cache repair, MCP config generation…

styler-ai/ProjectAtlas

Reviews the open bug backlog, separates severity from priority, assigns fixes to sprints and reports systemic trends, writing a dated triage file.

Donchitos/Claude-Code-Game-Studios

Write or rewrite pull request descriptions from a branch diff, commit range, existing PR, issue, upstream reference, specification, bug report, or review context.

grafana/ai-sdk

Launch Stylebot in a real, headed Chrome window (via yarn dev:chrome) so the user can manually eyeball a change — in whatever checkout the current session is in, worktree or main.

ankit/stylebot

Build, launch, and drive shunt — the Claude Code LLM gateway (a Rust/axum Anthropic-Messages proxy).

pleaseai/shunt

Triage Chatbook's auto-generated bug-report issues on GitHub by grouping them on their Failure Data signature (the failing Wolfram Language function plus the confirmed expression/pattern), finding…

WolframResearch/Chatbook

Run browser-based web tests against websites using Actionbook CLI.

actionbook/actionbook

Run a mobile QA checklist on a physical Android device over adb for tlon-apps, then triage what fails into fixes.

tloncorp/tlon-apps

Comprehensively diagnose and fix a failing Dependabot PR. An agent skill from axsaucedo/kaos.

axsaucedo/kaos

Takes a screenshot of a running Electron desktop app through playwright-cli over remote debugging, shrinks it and shows it so you can check the UI visually.

keybase/client

Build, test, and validate changes in the vstest repository. An agent skill from microsoft/vstest.

microsoft/vstest

Tests the create-volo-app CLI end-to-end against a local volo-app template.

VoloBuilds/create-volo-app

Sky130A open PDK workflow for ngspice-based analog simulation.

Arcadia-1/gmoverid-skill

Write and run tests for arangodb/spring-data, select regression coverage, and reproduce CircleCI failures.

arangodb/spring-data

Turn a bug the user describes in DeckWerk into a GitHub issue on vsitzmann/deckwerk.

vsitzmann/deckwerk

Decodes QR-code bug report photos and screenshots from the pipensx app into a log, then triages crashes and update, download or install failures.

i3sey/pipensx

GitHub issues, pull requests, bug reports, scope questions, and support threads.

roryeckel/wyoming_openai