Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add KhazixW2/Everything-Maa --skill maa-pipeline-testinggit clone --depth 1 https://github.com/KhazixW2/Everything-MaaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/khazixw2/everything-maa/maa-pipeline-testing)<a href="https://agentmods.dev/skills/khazixw2/everything-maa/maa-pipeline-testing"><img src="https://agentmods.dev/badge/skills/khazixw2/everything-maa/maa-pipeline-testing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/khazixw2/everything-maa/maa-pipeline-testing"><img src="https://agentmods.dev/badge/skills/khazixw2/everything-maa/maa-pipeline-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00084 | $0.04438 |
| Opus 5 | $0.00042 | $0.02219 |
| Sonnet 5 | $0.00017 | $0.00888 |
| Haiku 4.5 | $0.00008 | $0.00444 |
Grade A, and why
maa-pipeline-testing scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
agent_proc = subprocess.Popen( How it starts
The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline Testing Skill
官方依据核对
测试命令、schema 字段或 MaaFramework API 行为以原始官方来源为准。涉及版本差异、binding 兼容性或语义变化时,通过 $maa-wiki 定位官方文档、schema 与源码后再下结论;测试通过不能替代对官方契约的核对。
如果用户要求验收一个尚未定义目标状态和完成条件的端到端自动化需求,先交给 $maa-workflow-build 建立任务契约;已有契约时,再用本 skill 为其中的验收条件收集测试证据。
诊断边界
本 skill 的测试证据已经能定位责任方时,直接把证据交回对应 skill:识别或动作节点问题回 $maa-pipeline-generate,option 与 override 接线问题回 $maa-pipeline-option,状态模型或集成问题回 $maa-workflow-build。不要因为聚焦识别失败就触发 $maa-diagnose 的广义诊断流水线。只有失败已经发生、且聚焦测试仍无法归属责任方(原因可能同时落在运行日志、静态定义、环境或 harness)时,才由 $maa-workflow-build 的 RECOVER 请求 $maa-diagnose 收集只读证据。
项目初始化接力
测试前先查目标项目根目录的 basic_info.md。存在且包含第 0 节时,读取“0. Maa Skills 接力协议”和第 2/5/7/8/9/10 节,用 task/resource、公共返回节点、OCR/模板/ROI 和风险清单规划测试;随后以当前截图、当前源码和 TaskDetail 为准。优先把公共 Click 节点复制成临时 DoNothing 探针做初始化 smoke test,完成后调用 stop_pipeline 并删除临时文件。文件缺失或没有第 0 节时按本 skill 直接发现测试所需上下文;不得自动调用 $maa-project-init,只有用户明确要求初始化或刷新时才调用。源码更新更晚时视为缓存可能过期并以源码为准,不自动刷新或覆盖。
测试对象发现规则
从主 interface.json / interface.jsonc 读取 task entry、import[] 和 resource[].path。import[] 与资源路径都相对主 Interface 目录解析;测试只针对声明资源根内的 Pipeline、图片和项目声明的 agent 入口。assets/... 是常见打包布局示例,但不是可以脱离 Interface 声明猜测的协议默认值。
概述
测试 MaaFramework Pipeline JSON 中的 node,验证识别和操作是否正常工作。
历史审查后的测试边界
- 资源加载检查是 smoke test,不是端到端证明:目标项目锁定的 Interface / resource 检查(例如 M9A 的
pnpm check)能证明声明和资源包可加载,但不能证明 CustomAction/CustomRecognition 名称存在、参数路径正确、run_task()分支判断正确。 - Custom 映射必须单独查:所有
action: Custom/action.type = Custom的custom_action都要能映射到@AgentServer.custom_action(...);所有recognition.type = Custom的custom_recognition都要能映射到@AgentServer.custom_recognition(...)。 - CustomRecognition 也要测:M9A 证明复杂 OCR/list/image 逻辑经常放在 CustomRecognition,不要只测 CustomAction。
- 高风险链路要复测稳定态:购买、消耗、战斗开始、继续挑战、结算确认等动作后,先识别稳定页面或完成态,再继续危险动作。
- 关闭节点不能继续调用:当 option 把可执行节点的
enable/enabled设为 false 时,Python 必须先短路,不能再调用该节点的run_recognition()/run_task();同时验证关闭可选分支后,同级战斗/调查分支仍会继续识别。 - 识别成功不等于点对位置:识别命中只证明找到了元素。带
target/target_offset的节点必须在点击后再截一次图确认落点,否则写死的坐标会在换设备后静默点错。审查写法见 coordinate-hygiene。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 364 lines · 84 tokens per session scan A eb5fa0d5257b
maa-pipeline-testing is a skill published in the GitHub repository KhazixW2/Everything-Maa (12 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 4,438 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
asc-shots-pipeline
Orchestrate iOS screenshot automation with xcodebuild/simctl for build-run, AXe for UI actions, JSON settings and plan files, Koubou-based framing (asc screenshots frame), and screenshot upload (asc screenshots upload). Use when users ask for automated screenshot capture, AXe-driven simulator flows, frame composition…