Results for “truthfulqa”

QA cycling workflow - test, verify, fix, repeat until goal met

Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a feature is ready for testing or asks "does this work?". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only. (gstack) Voice triggers (speech-to-text aliases): "quality check", "test the app", "run QA".

Adversarial dynamic e2e QA workflow - generate hostile scenarios, test, verify, fix, report, and clean up

Evaluates the faithfulness of abstractive summaries by generating questions from summary sentences and verifying if the answers can be extracted from the source document, reporting Pearson and Spearman correlations with human judgments.

Live-device iOS QA for SwiftUI apps. (gstack)

Ai Content Qa

TextVQA: Towards Reasoning about Text in Images

Create systematic QA checklists to verify that design implementations match specifications across visual accuracy, layout, interaction, content, accessibility, and cross-platform categories.

Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".

Use when reporting bugs, doing QA, or filing GitHub issues conversationally

Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".

Use to audit QA coverage and scorecard health in a Rulebase workspace via the Rulebase MCP server. Trigger for "audit our QA coverage", "which agents or channels aren't being evaluated", "are our QA scores meaningful", "is our scorecard working", QA blind spots, score distribution or ceiling effects, and checking whether QA scores relate to SLA or complaint outcomes.

Validates rendered UI with browser or Playwright screenshots after implementation, redesign, responsive changes, or visual regressions.

将 PRD、原型、网页、接口、代码、测试记录和多轮上下文转成可追踪的 QA 基线、风险用例、执行证据、Bug 与发布判断。适用于 Web/API/App/小程序测试、回归、热修复、测试方案、Bug 复核和 QA 收口。用户指定 Markdown、Office、豆包文档/表格/PPT 或飞书载体时严格服从；未指定时默认创建与内容匹配的豆包在线载体。纯开发实现、纯排版和无测试目标的数据分析不触发。

Runs a comprehensive QA audit on Unity, Unreal, Godot, or web game projects, covering null references, missing assets, scene transitions, physics, input, save/load, localization, audio, and platform certification.

Orchestrates a complete bulk RNA-seq differential-expression study from raw FASTQ reads through QC, alignment, quantification, differential expression, pathway enrichment, and publication figures.

Generic webapp QA fallback — use only when no project-specific QA skill applies (project-local QA wins; native builds → mobile-emulator-test). Use when "QA the app", "test CRUD", or "smoke test". Monkey / guest vs logged-in → test-exploratory. Dead buttons → plan-stub-checker. Pixel diffs → test-visual-regression.

Runs a comprehensive mobile QA audit covering permissions, deep links, push notifications, offline mode, background/foreground transitions, memory leaks, network conditions, accessibility, and platform edge cases for Flutter, React Native, and native iOS/Android apps.

Runs a QA validation cycle followed by bugfix until all criteria pass clean, with automated verification and re-validation.

Verify the accuracy of claims and statements by extracting individual assertions, identifying authoritative sources, cross-referencing evidence, and assigning confidence-scored verdicts. Use when the user requests fact checking or provides relevant inputs for this workflow.

Exploratory QA of web apps: find bugs, evidence, reports.

Provides a structured workflow for unit, integration, E2E, and performance testing, including browser automation, code review, and quality gates.

Routes rendered UI testing, visual regression, browser QA, accessibility, responsive, performance, or frontend review to a leaf skill.

Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead. Proactively suggest when the user wants a bug report without any code changes. (gstack) Voice triggers (speech-to-text aliases): "bug report", "just check for bugs".

Runs an interactive QA session, clarifying user-reported problems, exploring the codebase for context, and filing durable, user-focused GitHub issues.

Systematically QA test a web application and fix bugs found. (gstack)

Use this skill for mobile viewport testing, tap targets, safe areas, responsive navigation, device constraints. Trigger when the task involves qa work related to Mobile First Qa, production implementation, audits, debugging, strategy, or validation.

Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".

Systematically QA test a web application and fix bugs found. (gstack)

Use this skill for browser verification, console/network errors, layout checks, user-flow QA, DevTools evidence. Trigger when the task involves qa work related to Browser Devtools Qa, production implementation, audits, debugging, strategy, or validation.

QA a completed analysis for methodology, accuracy, and bias before it is shared, shipped, or acted on.

Performs a comprehensive cross-artifact QA/QC review of a virtual team pipeline, checking completeness, consistency, security, and compliance, then issues an advisory verdict with quality, compliance, and sign-off reports.

Reviews all pipeline artifacts from a virtual software team and produces quality, compliance, and sign-off reports with an advisory release verdict.

Use when asked to "QA this", "is this ready to ship?", "test it like a user", "bug hunt", "sign off this build/phase", or before declaring a web app / feature shippable — a real-user QA pass that files severity-ranked bug reports and returns a binary ship verdict. Not for visual/CRO polish (frontend-audit) or fixing an already-reported UI bug (ui-fix-observe-first).