“qa”的搜索结果

在OpenClaw的QA Lab中验证Telegram草稿与最终消息的送达顺序，通过QA Channel和实际Telegram插件运行同一场景。

• 检查Telegram草稿与最终消息的送达
• 通过QA Channel验证消息流程
• 通过实际Telegram插件运行验证

Automate Booqable tasks through Rube MCP, a connection for agent tools. Discover supported actions, check the service connection, and execute with current input requirements, including workflows for bulk processing and collecting results across multiple pages.

中文简介正在准备中。当前显示英语简介。

• Find tools for a Booqable task
• Verify the Booqable connection
• Execute multiple Booqable operations together

Coordinate QA agents to plan testing for a game development sprint or feature. Produce test cases, collect results from human testers, document bugs and visual evidence, and prepare a sign-off report based on recorded findings.

中文简介正在准备中。当前显示英语简介。

• Planning QA for a sprint or game feature
• Preparing manual test cases from acceptance criteria
• Recording test results, bugs, and screenshot evidence

Automate Booqable tasks through Rube MCP, a connection for agent tools. Discover supported actions, check the service connection, and execute with current input requirements, including workflows for bulk processing and collecting results across multiple pages.

中文简介正在准备中。当前显示英语简介。

• Find tools for a Booqable task
• Verify the Booqable connection
• Execute multiple Booqable operations together

Sequenced launcher that bootstraps QA on a project with no QA in place. Chains qa-project-context → test-strategy → test-planning in one guided run, then points you at automation. Use when: "set up QA on a new project," "QA from scratch," "no QA exists yet," "/qa-start." Not for: onboarding a QA engineer to an existing team with existing tests — use qa-project-bootstrap. Not for: "which skill do I use" with no clear match — use qa-do. Related: qa-project-context, test-strategy, test-planning, qa-project-bootstrap, qa-do.

中文简介正在准备中。当前显示原文说明。

根据OpenClaw的功能分类和QA证据，复核质量、功能完整性及长期支持评价，验证输入数据并更新成熟度评分卡文档，同时记录评价理由和复核条件。

• 复核各功能领域的成熟度
• 检查预期使用流程是否完整
• 根据QA证据更新评分文档

使用模拟环境或真实服务运行OpenClaw质量验证场景，调查并修复失败原因、检查结果报告，还可比较多个模型的表达方式和角色表现。

• 在模拟环境或真实服务中运行质量验证
• 调查失败场景并重新验证
• 比较多个模型的角色表现

Investigate failed Agent QA runs using recorded steps, logs, and saved evidence. Classify each failure, explain confidence and supporting findings, and identify the likely area to fix and the next action.

中文简介正在准备中。当前显示英语简介。

• Investigating a failed or interrupted Agent QA run
• Reviewing saved evidence and execution logs
• Comparing recurring failures across recent runs

Check a game build before handing it to QA, the team responsible for quality checks. Run automated tests, review coverage gaps, confirm critical paths with the developer, and produce a report with results and unresolved checks.

中文简介正在准备中。当前显示英语简介。

• Checking a build before QA hand-off
• Rechecking a build after fixing a failure
• Reviewing platform-specific controls and behavior

Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit," "first 30 days," "QA mentorship," "joining QA team." Not for: setting up QA on a brand-new project from scratch — use `qa-start`. Related: qa-start, qa-project-context, shift-left-testing, ai-qa-review.

中文简介正在准备中。当前显示原文说明。

Test the Senpi adapter and task engine against the real senpi binary in an isolated environment. Check task and team behavior, record evidence in a consistent location, and verify that the existing agent directory remains untouched.

中文简介正在准备中。当前显示英语简介。

• Verify adapter behavior after code changes
• Test task execution and team recovery
• Check that skills reach child tasks

Investigate failed Agent QA runs using logs, recorded artifacts, and local source code. Make a focused code or test-definition repair, then verify the affected behavior while keeping product and infrastructure defects visible.

中文简介正在准备中。当前显示英语简介。

• Repair a failed staging test from recorded evidence
• Update an outdated Agent QA YAML definition
• Distinguish test failures from product or infrastructure defects

Pre-publish QA framework for content. Brief adherence, voice consistency, fact accuracy, structure and clarity, AI-content audit, SEO and AEO compliance, internal linking and schema validation, QA at scale via sampling, the QA workflow, and the discipline that distinguishes catch-problems QA from checkbox QA. Triggers on editorial QA, content review, pre-publish review, content audit, content QA process, AI-content audit, hallucination check, content sampling, programmatic QA, voice consistency check, brief adherence check. Also triggers when a content team is shipping sloppy work, when AI-co-authored content is reaching publish unaudited, when a QA process burns reviewers out, or when a programmatic SEO set needs sampling discipline. On a voice consistency check, this skill owns checking a draft against an existing voice system at the publish gate; use `brand-voice` when the voice system itself needs defining or documenting.

中文简介正在准备中。当前显示原文说明。

Create and fill .agents/qa-project-context.md with the project's tech stack, test frameworks, CI/CD pipeline, environments, quality goals, risk areas, team structure, and conventions. This is the one file every other QA skill reads first, so they skip redundant discovery and give context-aware advice. Use when: "set up QA context," "configure testing," "initialize project," first use of any QA skill. Not for: bootstrapping a brand-new project's QA end-to-end — use qa-start (which calls this skill as its first step). Related: qa-start, risk-based-testing, test-strategy, qa-metrics, playwright-automation.

中文简介正在准备中。当前显示原文说明。

Routing skill of last resort. Takes a plain-language QA situation and names the right 1-2 skills to use and in what order. Use ONLY when the request does not match any other skill's trigger phrases. Use when: "which skill should I use," "where do I start," "I'm not sure what to test," "/qa-do," or any vague QA situation that doesn't map to one skill. Not for: bootstrapping a brand-new project with no QA — use qa-start. Not for: capturing project setup/context — use qa-project-context. If the request clearly matches another skill, invoke that skill directly instead of routing through here. Related: qa-start, qa-project-context, test-strategy.

中文简介正在准备中。当前显示原文说明。

Organize GitHub issues and pull requests found during quality assurance testing. Apply release tracking labels, classify bugs by four severity levels, and label multiple findings while keeping documentation issues and feature requests outside the severity scheme.

中文简介正在准备中。当前显示英语简介。

• Group QA findings by release
• Classify bugs by severity
• Apply labels to multiple issues and pull requests

[omh] Hostile scenario testing: adversarial QA and fix loops. Use when the user says: ultraqa, adversarial qa, hostile scenarios, e2e qa, real-world qa, qa scenario, release qa, 敵対的QA.

中文简介正在准备中。当前显示原文说明。

Create and edit Agent QA tests, test suites, and hooks, then validate their structure and tool-generated IDs before running them. Use MCP, an agent tool connection, or the CLI within a configured workspace.

中文简介正在准备中。当前显示英语简介。

• Create and validate a checkout test for staging
• Update an existing test suite
• Check YAML definitions and IDs

Create a game development test plan for a sprint, feature, or individual task. Classify the work and specify automated tests, manual checks, basic functionality checks, and playtest needs from documented requirements.

中文简介正在准备中。当前显示英语简介。

• Plan testing before a sprint starts
• Separate automated tests from manual checks
• Define basic checks before a QA handoff

[omh] Rendered UI needing a visual verdict: prepare observed-only rendered QA gates for web, frontend, image, document, and TUI surfaces. Use when the user says: visual-qa, visual qa, visual QA, visual quality assurance, visual check, web qa, web visual qa, screenshot qa.

中文简介正在准备中。当前显示原文说明。

Manual QA harness for the senpi coding agent itself. MUST USE after changing packages/ai, packages/agent, packages/coding-agent, or packages/tui — a green typecheck and `npm test` are NOT QA. Drives the real CLI from source in an isolated sandbox (never touches ~/.senpi or real credentials) across four channels: remote RPC (--mode rpc JSONL stdio), TUI smoke (node-pty on Windows, tmux on POSIX), mock loop (a local fake model server for deterministic, zero-token agent-loop runs), and CLI smoke (--help/--print/--list-models). Every helper ships a --self-test. Use whenever someone says qa senpi, test the agent, verify my change, rpc qa, tui qa, mock-loop qa, smoke the cli, or needs evidence that an agent-loop, tool, keybinding, or provider change works end to end. Capture evidence to local-ignore/qa-evidence/.

中文简介正在准备中。当前显示原文说明。

从PM、架构、开发和QA四个角度同时审视新功能或提案，整理各角色的主要顾虑、首要行动及团队问题，并汇总共识与意见分歧。

• 从四种角色审视新功能
• 实施前检查提案中的顾虑
• 梳理新项目的首要行动

Clean up an iOS app after /ios-qa by removing the DebugBridge package and its debug wiring. The cleanup covers StateServer, DebugOverlay, generated accessor code, and hooks added to the app.

中文简介正在准备中。当前显示英语简介。

• Cleaning up an iOS app after /ios-qa
• Removing the DebugBridge package
• Removing StateServer and DebugOverlay

Create acceptance criteria and a manual validation plan for feature changes. Cover successful flows, unusual inputs, failures, and performance limits, with observable outcomes and clear evidence requirements so reviewers can decide whether each criterion passes.

中文简介正在准备中。当前显示英语简介。

• Preparing a feature change for QA
• Reviewing a PR that changes user-visible behavior
• Planning regression checks after an incident