50 boosters for "qa" — open source, verified from GitHub, ready to install
Model QA Specialist is an independent auditing agent that performs comprehensive ML/statistical model validation—from documentation review and data reconstruction through calibration testing, interpretability analysis, and audit-grade reporting. It's ideal for data scientists, ML engineers, and compliance teams who need rigorous, end-to-end model validation.
Evidence Collector is a QA specialist agent that demands visual proof (screenshots) for all findings and refuses to report unverified issues, helping teams avoid false-positive bug reports and maintain rigorous testing standards.
Workflow Architect is a specialized agent that maps complete workflow specifications including happy paths, failure modes, and recovery strategies before implementation, enabling developers and QA to build and test against comprehensive, build-ready specs.
Transforms complex business information into polished executive summaries using proven consulting frameworks (SCQA, Pyramid Principle) tailored for C-suite decision-makers. Ideal for consultants, strategists, and business leaders who need to distill lengthy analyses into actionable insights quickly.
Create a Codex-compatible animated pet from a concept, brand cue, company/prospect name, one or more reference images, or any combination of those inputs. This workflow keeps the deterministic hatch-pet pipeline for atlas geometry, validation, visual QA, and packaging, while using concise state-spec
[ULTRAQA ACTIVATED - AUTONOMOUS QA CYCLING] You are now in ULTRAQA mode - an autonomous QA cycling workflow that runs until your quality goal is met. Parse the goal from arguments. Supported formats:
You test through the eyes of a user: browser, screenshots, console, E2E. Report issues with evidence. Never fix code. 1. Determine scope from the invoking prompt: 2. Preflight — verify app is running. Probe the app URL. If unavailable:
1. Vectorization discipline (from logo-vectorizer-minimal-smooth): fit the raster source with the lowest-complexity editable geometry that passes visual QA. 2. Motion discipline (from Disney's 12 Principles of Animation): choreograph that geometry into brand-appropriate motion with evidence-based ti
Validate behavior against intent. Look for null/edge cases (0, -1, int.MaxValue, empty collections), error paths, exception handling, thread safety. Check for performance traps (allocations in hot paths, O(n²) where O(n) is possible), resource leaks (IDisposable not disposed), missing null checks on
"name": "novel-to-game", "description": "Turn any novel into a source-grounded, fully playable game — a 7-skill adaptation pipeline covering gameable deconstruction, concept selection, world and art design, target-platform build, and evidence-based QA. 把小说转成有原著依据、可在目标平台完整游玩的游戏。", "name": "worldwonde
"description": "Canary browser automation + recorded QA sessions: a sandbox scripting reference, verify/automate/session/review skills, JTBD subagents, and /canary slash commands.", "name": "wizenheimer", "url": "https://github.com/wizenheimer"
Mission: own the target, pixel for pixel. Read every value off the live page (never a screenshot guess), rebuild it, prove the match with measured computed-style assertions, then make it yours. This skill runs as a workflow inside a live Claude session, not a background script. When it's invoked, YO
Scalable query engine for web scrapping/data mashup/acceptance QA, powered by Apache Spark
Use this skill for verification and optional publish handoff. If the telemetry consent prompt appears and no prior choice is recorded, stop and follow ../../references/telemetry-consent.md before continuing. If comparing against an older preview run, pass the previous health baseline:
A quality assessment skill that runs automated validation, AI-based evaluation, and risk scoring on SpecWeave increments to make informed quality gate decisions. Developers using SpecWeave will benefit from automated quality checks and structured decision-making.
Use this skill for verification and optional publish handoff. If comparing against an older preview run, pass the previous health baseline: Run outside sandboxed environments by default. Do not first attempt the Playwright browser step inside the sandbox and then retry after it is intercepted.
Use this skill as the end-to-end coordinator for GA4 + GTM tracking delivery. Do not assume the user wants the full workflow. <!-- event-tracking auto-update bootstrap:start -->
<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly --> <!-- Regenerate: bun run gen:skill-docs --> If is , do not proactively suggest ostack skills — only invoke
"name": "firecrawl-workflows", "displayName": "Firecrawl Workflows", "description": "Outcome-focused Firecrawl workflow skills for research, SEO audits, QA, knowledge bases, lead lists, dashboard reporting, shopping, and design-system extraction.",
CLI tool for persistent browser automation with multi-session support, featuring Chromium/Real/Remote browser modes, cookie management, JavaScript execution, and long-running automation workflows.
Turkey-build is a multi-agent orchestration system for building production-ready applications across 7 modes (greenfield, iteration, bugfix, refactor, UI polish, migration, audit), with PM-driven coordination and runtime verification for teams that need structured, quality-gated development workflows.
You are a QA validation agent. Execute user stories against web apps using the skill. Walk through each step, screenshot every step, and report a structured pass/fail result. 1. Parse the user story into discrete, sequential steps (support all formats below) 2. Setup — derive a named session from t
