QA and bug reports

Run multi-dimensional quality assurance for InstructorPHP. An agent skill from cognesy/instructor-php.

cognesy/instructor-php

Fast headless browser for QA testing and site dogfooding. An agent skill from no-session/pstack.

no-session/pstack

Deployment workflows, pre-deploy validation, smoke testing, and rollback procedures. Use when deploying to staging or production, running smoke…

bybren-llc/safe-agentic-workflow

Drives development with tests. An agent skill from abashev/vfs-s3.

abashev/vfs-s3

A skill your agent uses when working in the traffico repository and needing host-realistic release smoke evidence through the Lima traffico-ebpf VM, including validating the Lima config, starting…

leodido/traffico

Fetch, analyze, reproduce, and minimize GitHub issue reproductions.

pytorch/pytorch

Ship and spec AI features, LLM products, agents, copilots, and generative UX — including when to use a model vs.

andreaskelm/pm-brain

A skill your agent uses when testing Windows 11 desktop apps (WinForms/WPF/UWP) via UFO UIA/Win32 automation MCP.

CodeAlive-AI/ai-driven-development

Canary deployment with smoke tests — deploy to a zero-traffic revision, run health checks, and promote on success.

atelier-fashion/adlc-toolkit

Visual quality assurance — analyze game screenshots for defects, compare against reference, check motion in frame sequences.

liangdabiao/Godogen

A skill your agent uses when testing a bundle-plugin locally before release — generating dev-marketplace environments, verifying component discovery, running hook smoke tests, and validating…

OdradekAI/bundles-forge

Test Daydream Scope through its stdio MCP server, including disconnected startup, connecttoscope, direct Python stdio client fallback, and lightweight smoke tests.

daydreamlive/scope

Builds two throwaway HTML test pages for a Handsontable pull request, one on the released CDN version and one on the local build, to compare behavior side by side.

handsontable/handsontable

Diagnose GitHub bug reports in openai/codex. An agent skill from deonmenezes/mantishack.

deonmenezes/mantishack

Guides visual testing of Warp UI changes by launching the app with an API key and driving it through the computer use tool, with optional mocked state.

warpdotdev/warp

Drives terminal UI apps from the command line for testing, demos and scripted interactions, using a run, screenshot, act, wait loop.

pproenca/agent-tui

End-to-end recipe for adding a new task under examples/ — the three pieces that have to line up (task.yaml, seed/, and grader/), what to put in each, the TaskGrader API surface, the coral validate →…

Human-Agent-Society/CORAL

Ask Google's Antigravity CLI (agy staffer, fast Gemini) a cheap one-shot question - the fast zero-tool mode and the post-install smoke test.

keli-wen/agy-staff

Extends a project's acceptance process to real chat bot channels: Discord, Slack, Telegram, WeChat, Lark, QQ, and iMessage on macOS.

lobehub/lobehub

Covers bringing up and runtime-testing the claude-command-center dashboard server on Linux, including duplicate instances and fresh-install checks.

amirfish1/claude-command-center

Drives the real senpi binary to QA the omo Senpi adapter and task engine, writing every piece of evidence to one canonical, gitignored path.

code-yeongyu/oh-my-openagent

Run a local smoke test for the Stata-MCP server. An agent skill from SepineTam/mcp-for-stata.

SepineTam/mcp-for-stata

A skill your agent uses whenever a warpdroid (Android client) change or bug needs to be verified by actually driving the app's visual UI — any task phrased as "test the warpdroid UI", "click through…

Warp-net/warpnet

Launch a hands-off Project Zomboid measurement run (bench, drive, parity, verify) with harness/run.sh, respecting the shared-machine and run-etiquette rules.

xD3I/PZ_Optimization

Bug-fix routine that fixes the whole class of bug, not just the reported instance.

joetawil7/first-pass

Validate the get-started experience of Open Edge Platform (OEP) software components from the perspective of a first-time user.

open-edge-platform/edge-ai-suites

Rigor Run skill for README-first deep learning repo reproduction.

lllllllama/RigorPilot-Skills

Drafts and iterates on local-development bug reports in the role of a staff-level Tech Lead.

FHIR/fhir-codegen

Compare implementation against specifications, identify gaps and issues.

madebyaris/spec-kit-command-cursor

QA testing skill with real browser automation. An agent skill from blueberrycongee/termcanvas.

blueberrycongee/termcanvas

Onboard a new robot platform to COMPASS: generate robot ArticulationCfg + per-embodiment envcfg, register in EmbodimentEnvCfgMap, smoke-test the spawn with --numenvs 1.

NVlabs/COMPASS

Turn a bug symptom into a structured, reproducible bug report — summary, environment, exact repro steps, actual vs expected, and evidence (logs, error text, failing route/test) — and then optionally…

ucsandman/DashClaw

Reproduce a reported bug on Android/Android TV and capture evidence.

DodoraApp/DodoStream

Provision Azure infrastructure, deploy to Azure Container Apps, and verify via smoke tests.

EmeaAppGbb/spec2cloud

Turns a user's plain-English description of an RL training environment into runnable code across the four target frameworks — OpenEnv, OpenReward (ORS), Verifiers, and NeMo Gym.

adithya-s-k/FineEnvs

Browser QA for a pull request against a running Twenty app: scenarios drawn from the diff, run in a real browser, checked in the database and logs, and closed with a verdict and report.

twentyhq/twenty

A skill your agent uses when asked to run, boot, start, dev-serve, smoke-test, or drive the SEO Office app, or to confirm a change works end-to-end in the real running app (UI → orchestrator → brain…

AgriciDaniel/seo-os

Runs Warp's terminal UI for real, drives it with keystrokes and reads the rendered screen back to confirm that a change looks and behaves as intended.

warpdotdev/warp

Help desk for "MulmoTerminal is broken". An agent skill from receptron/mulmoterminal.

receptron/mulmoterminal

Auto-routes a user request to the matching codexqa skill, then ensures that skill is on disk and follows its SKILL.md.

openqa-cn/codexqa

Goal-driven E2E testing where a browser agent (Playwright MCP / computer-use) reads a natural-language goal and explores the app via the accessibility tree to assert outcomes — no pre-written script.

petrkindlmann/qa-skills

Launches the iPolloWork Electron app inside a Daytona cloud sandbox with a noVNC desktop, and points to focused skills for server, Chrome, secrets and recordings.

Devin-AXIS/iPolloWork

Draft, revise and post privacy-scrubbed Atomic bug reports or enhancements through ordinary conversation.

bastani-inc/atomic

Run, watch, debug, extend, or explain OpenClaw qa-lab and qa-channel scenarios, artifacts, and live lanes.

openclaw/openclaw

Checks a built UI against a human-interface checklist and any reference image, pairing day and night screenshots at two screen widths.

code-yeongyu/oh-my-openagent

Fix bugs, add features to completed plugins. An agent skill from glittercowboy/plugin-freedom-system.

glittercowboy/plugin-freedom-system

A skill your agent uses when writing or reviewing tests for DeepSeek Harness plugins, external DSH plugin packages, or package changes in the deepseek-harness repository.

NanmiCoder/dsh-auto-mode

Test quality assurance workflow for LeetCode problems - verifies reproducibility, fixes linting issues, and ensures test structure matches JSON templates.

wislertt/leetcode-py