Maa Cyber Fortune Master
MaaAssistantArknights/MaaAssistantArknights
用“赛博道士 + 故障玄学 + 半懂不懂技术分析”的风格回复 MAA 用户的简略求助。用于用户只给一句模糊问题、没有日志、没有截图、没有报错时，做一段短小离谱但认真的玄学诊断。触发词可包括“赛博算卦”“玄学回复”“评论区整活”“帮我写一段离谱但正经的故障分析”
MAAPunish 任务流水线 JSON/JSONC 编写与审查指南。含 Pipeline 速查表（识别类型、动作类型、节点字段默认值、JumpBack/Anchor、Custom）。基于 MaaFramework 协议与本仓库 protocol-3.1-task-pipeline.md。在编写或审查 pipeline、排查超时/onerror、或使用…
MITAuto-check passed
Install Maa Punish Pipeline Guide
$ npx skills add overflow65537/MAA_Punish --skill maa-punish-pipeline-guide -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install overflow65537/MAA_Punish maa-punish-pipeline-guide --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/overflow65537/MAA_Punish.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/maa-punish-pipeline-guide .claude/skills/maa-punish-pipeline-guide && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "maa-punish-pipeline-guide" agent skill from https://github.com/overflow65537/MAA_Punish/tree/main/.cursor/skills/maa-punish-pipeline-guide into .claude/skills/maa-punish-pipeline-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "maa-punish-pipeline-guide", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/overflow65537/MAA_Punish/tree/main/.cursor/skills/maa-punish-pipeline-guideType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add overflow65537/MAA_Punish --skill maa-punish-pipeline-guide -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install overflow65537/MAA_Punish maa-punish-pipeline-guide --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/overflow65537/MAA_Punish.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.cursor/skills/maa-punish-pipeline-guide .agents/skills/maa-punish-pipeline-guide && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "maa-punish-pipeline-guide" agent skill from https://github.com/overflow65537/MAA_Punish/tree/main/.cursor/skills/maa-punish-pipeline-guide into .agents/skills/maa-punish-pipeline-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "maa-punish-pipeline-guide", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add overflow65537/MAA_Punish --skill maa-punish-pipeline-guide -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install overflow65537/MAA_Punish maa-punish-pipeline-guide --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/overflow65537/MAA_Punish.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.cursor/skills/maa-punish-pipeline-guide .cursor/skills/maa-punish-pipeline-guide && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "maa-punish-pipeline-guide" agent skill from https://github.com/overflow65537/MAA_Punish/tree/main/.cursor/skills/maa-punish-pipeline-guide into .cursor/skills/maa-punish-pipeline-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "maa-punish-pipeline-guide", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/overflow65537/MAA_Punish.git --path .cursor/skills/maa-punish-pipeline-guide--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add overflow65537/MAA_Punish --skill maa-punish-pipeline-guide -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install overflow65537/MAA_Punish maa-punish-pipeline-guide --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/overflow65537/MAA_Punish.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.cursor/skills/maa-punish-pipeline-guide .gemini/skills/maa-punish-pipeline-guide && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "maa-punish-pipeline-guide" agent skill from https://github.com/overflow65537/MAA_Punish/tree/main/.cursor/skills/maa-punish-pipeline-guide into .gemini/skills/maa-punish-pipeline-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "maa-punish-pipeline-guide", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install overflow65537/MAA_Punish maa-punish-pipeline-guideInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add overflow65537/MAA_Punish --skill maa-punish-pipeline-guide -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/overflow65537/MAA_Punish.git skills-src && mkdir -p .github/skills && cp -r skills-src/.cursor/skills/maa-punish-pipeline-guide .github/skills/maa-punish-pipeline-guide && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "maa-punish-pipeline-guide" agent skill from https://github.com/overflow65537/MAA_Punish/tree/main/.cursor/skills/maa-punish-pipeline-guide into .github/skills/maa-punish-pipeline-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "maa-punish-pipeline-guide", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add overflow65537/MAA_Punish --skill maa-punish-pipeline-guide -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install overflow65537/MAA_Punish maa-punish-pipeline-guide --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/overflow65537/MAA_Punish.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.cursor/skills/maa-punish-pipeline-guide .opencode/skills/maa-punish-pipeline-guide && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "maa-punish-pipeline-guide" agent skill from https://github.com/overflow65537/MAA_Punish/tree/main/.cursor/skills/maa-punish-pipeline-guide into .opencode/skills/maa-punish-pipeline-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "maa-punish-pipeline-guide", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
maa-punish-pipeline-guide- GitHub stars
- 371
- Token cost
- ~1.5k tokens
- SKILL.md length
- 383 words
- Files
- 1
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- MIT
At a glance
MAAPunish 任务流水线 JSON/JSONC 编写与审查指南。含 Pipeline 速查表（识别类型、动作类型、节点字段默认值、JumpBack/Anchor、Custom）。基于 MaaFramework 协议与本仓库 protocol-3.1-task-pipeline.md。在编写或审查 pipeline、排查超时/onerror、或使用…
- Works in 4 steps: 分辨率：ROI / 模板均以 1280×720 为基准（与 README… → 资源路径：assets/resource//pipeline//*.jsonc；图… → 默认值文件：例如… → …
- SKILL.md covers 文档索引, Pipeline 速查表, 识别算法速查表 and 动作类型速查表, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Maa Punish Pipeline Guide is an agent skill from overflow65537/MAA_Punish. MAAPunish 任务流水线 JSON/JSONC 编写与审查指南。含 Pipeline 速查表（识别类型、动作类型、节点字段默认值、JumpBack/Anchor、Custom）。基于 MaaFramework 协议与本仓库 protocol-3.1-task-pipeline.md。在编写或审查 pipeline、排查超时/onerror、或使用 TemplateMatch/OCR/Custom 时使用。
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: 战双帕弥什每日任务自动化 | Assistant For Punishing Gray Raven. The licence is MIT.
Example prompts
- “/maa-punish-pipeline-guide”
Requirements
- Python 3
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- 分辨率：ROI / 模板均以 1280×720 为基准（与 README 模拟器说明一致）。
- 资源路径：assets/resource//pipeline//*.jsonc；图片相对各自 bundle 的 image/ 等目录。
- 默认值文件：例如 assets/resource/base/default_pipeline.json 会与框架 default_pipeline.json 机制合并；改全局默认时注意多 bundle 加载顺序（见协议「多 Bundle」）。
- Python Custom（v2 示例骨架）
What it can do on your machine
Read from SKILL.md and the folder at commit c2f24bb. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are jsonc).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Maa Punish Pipeline Guide loads about 1.5k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 383 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from overflow65537/MAA_Punish at commit c2f24bb, republished under its MIT licence (© overflow65537). 383 words, ~1,516 tokens.
Download SKILL.mdSave it as
.claude/skills/maa-punish-pipeline-guide/SKILL.md (or your agent's skills folder).- name
- maa-punish-pipeline-guide
- description
- MAA_Punish 任务流水线 JSON/JSONC 编写与审查指南。含 Pipeline 速查表（识别类型、动作类型、节点字段默认值、JumpBack/Anchor、Custom）。基于 MaaFramework 协议与本仓库 protocol-3.1-task-pipeline.md。在编写或审查 pipeline、排查超时/on_error、或使用 TemplateMatch/OCR/Custom 时使用。
MAA_Punish Pipeline 编写指南
文档索引
| 需求 | 优先看 |
|---|---|
| 速查表（本节下方） | 识别/动作/字段默认值/节点属性 |
| 完整语义与边界情况 | 仓库根目录 protocol-3.1-task-pipeline.md |
| 上游原文 | 3.1-PipelineProtocol |
| JSON Schema 校验 | tools/schema/pipeline.schema.json、custom.*.schema.json |
| 自动战斗专项 | docs/自动战斗框架开发指南.md |
| Python 自定义实现 | agent/recognition/、agent/action/ |
Pipeline 速查表
v1 / v2 写法
- v1：
"recognition": "TemplateMatch"，参数字段与节点平级混写（老写法）。 - v2（推荐）：
"recognition": { "type": "TemplateMatch", "param": { ... } }，action同理；除 recognition/action 外的字段（next、timeout、pre_delay等）仍在节点根上，与协议一致。
roi / box / target（易混）
| 字段 | 含义 |
|---|---|
roi | 识别搜索区域 [x,y,w,h]，可与 roi_offset 叠加 |
box | 识别命中结果区域（运行时产生） |
target | 动作作用区域；默认 true 表示用当前识别结果的 box |
节点通用字段 · 默认值速查
以下为协议常见内置默认（节点未写时使用；实际可能被 assets/resource/**/default_pipeline.json 覆盖，见下节）。
| 字段 | 典型默认 | 说明 |
|---|---|---|
rate_limit | 1000 ms | 每轮识别间隔下限 |
timeout | 20000 ms | 本节点 next 整轮识别超时；-1 表示无限等 (v5.5) |
pre_delay / post_delay | 200 ms | 识别→动作前、动作→截下一帧前；易引入隐性等待，按需显式写 0 |
pre_wait_freezes / post_wait_freezes | 0 | 画面静止再前进；对象形式见协议「等待画面静止」 |
repeat | 1 | 动作重复次数 (v5.3) |
repeat_delay / repeat_wait_freezes | 0 | 重复间隔 (v5.3) |
inverse | false | 反转识别结果 |
enabled | true | false 时其他节点 next 里会跳过该节点 |
max_hit | 无限制 | 命中次数上限 (v5.1) |
执行顺序（单节点内）
pre_wait_freezes → pre_delay → action（及 repeat 分支）→ post_wait_freezes → post_delay → 截图 → 识别 next。
next / on_error
| 机制 | 说明 |
|---|---|
next | 按顺序尝试子节点识别，第一个命中则执行其 action 并进入该子节点上下文 |
| 全未命中 | 循环等待直到 timeout（或无限），再进当前节点的 on_error |
| 动作失败 | 进命中子节点的 on_error（若写了） |
| 任务结束 | next 为空且无需 JumpBack；或 StopTask；或外部 post_stop |
节点属性（next / on_error 列表里）
| 写法 | 作用 |
|---|---|
[JumpBack]节点名 或 { "name": "节点名", "jump_back": true } | 子链跑完后回到父节点，从父 next 头再扫；用于弹窗/加载。在 on_error 路径上不回跳 (v5.9) |
[Anchor]锚点名 | 解析为最后一次被赋值的锚点指向的节点；anchor 字段可在节点上设为字符串 / 数组 / 对象 (v5.7) |
识别算法速查表
recognition.type（v2）或 v1 的 recognition 字符串。
| 类型 | 用途提要 | 关键 param（节选） |
|---|---|---|
| DirectHit | 不识别，直接当命中 | roi |
| TemplateMatch | 模板找图 | template（image/ 相对路径）、roi、threshold（默认 0.7）、method（如 5 常用）、green_mask、index / order_by |
| FeatureMatch | 特征点匹配，透视/尺度变化 | template、count、detector（如 SIFT） |
| ColorMatch | 找色 | method（如 40=HSV）、lower、upper、count、connected |
| OCR | 文字 | expected（可正则）、model、only_rec、color_filter（引用 ColorMatch 节点名）v5.8 |
| NeuralNetworkClassify | 固定区域分类 | model（model/classify）、labels、expected（类下标） |
| NeuralNetworkDetect | 检测框 | model（model/detect）、expected、threshold |
| And v5.3 | 逻辑与 | all_of（节点名字符串 v5.7 或内联识别）、box_index |
| Or v5.3 | 逻辑或，首个命中即停 | any_of |
| Custom | 自定义识别（本项目为 Python 注册） | custom_recognition、custom_recognition_param、roi |
Show full SKILL.md (166 more words)Show less
动作类型速查表
action.type（v2）或 v1 的 action 字符串。
| 类型 | 用途提要 | 关键 param（节选） |
|---|---|---|
| DoNothing | 无操作 | — |
| Click | 点击 | target（true / 节点名 / [Anchor]名 / 坐标 / 区域）、target_offset、contact、pressure v5.0 |
| LongPress | 长按 | duration、target 等同 Click |
| Swipe | 滑动 | begin、end（支持折线列表）、duration、only_hover |
| MultiSwipe | 多指滑动 | swipes[]：begin/end/starting/… |
| TouchDown / TouchMove / TouchUp v5.0 | 细分触控 | contact、target |
| Scroll v5.1 | 滚轮（Win/mac 等） | target、dx、dy（建议 Win 下取 120 倍数） |
| ClickKey / LongPressKey | 按键 | key（虚拟键码） |
| KeyDown / KeyUp v5.0 | 组合键时序 | key |
| InputText | 文本 | input_text |
| StartApp / StopApp | 启停应用 | package |
| StopTask | 停止当前任务链 | — |
| Command | 外部进程 | exec、args（支持 {ENTRY} {NODE} {IMAGE} 等占位） |
| Shell v5.3 | ADB shell | cmd、shell_timeout（原 timeout v5.8 改名） |
| Screencap | 保存截图到 log 目录 | filename、format、quality |
| Custom | 自定义动作（本项目 Python） | custom_action、custom_action_param、target |
本项目约定
- 分辨率：ROI / 模板均以 1280×720 为基准（与 README 模拟器说明一致）。
- 资源路径：
assets/resource/**/pipeline/**/*.jsonc；图片相对各自 bundle 的image/等目录。 - 默认值文件：例如
assets/resource/base/default_pipeline.json会与框架default_pipeline.json机制合并；改全局默认时注意多 bundle 加载顺序（见协议「多 Bundle」）。 - Python Custom（v2 示例骨架）
"MyStep": {
"recognition": {
"type": "Custom",
"param": {
"custom_recognition": "YourRecoName",
"custom_recognition_param": {},
"roi": [0, 0, 1280, 720]
}
},
"action": {
"type": "Custom",
"param": {
"custom_action": "YourActionName",
"custom_action_param": {},
"target": true
}
},
"next": ["NextNode"]
}注册名必须与 assets/agent 内实现一致；调试看 custom.log 或 debug/custom_*.log。
核心原则（审查时自检）
- 状态驱动：识别 → 操作 → 再识别；少凭假设点击后的画面。
- 高命中率：
next覆盖分支（含弹窗、加载、异常界面）。 - 慎用纯延迟：优先加识别节点与
*_wait_freezes；需要「无等待」时对默认敏感字段显式0。 - Schema：提交前用仓库工具/IDE 校验
tools/schema/pipeline.schema.json。 - 勿照搬其他项目：Custom 名称以本仓库为准。
审查清单
- 字段符合 schema；Custom 与 Python 注册名一致
-
next/on_error覆盖主要分支；JumpBack 用于可恢复中断 - ROI / 模板基于 720p
- 任务入口与
assets/interface.json、assets/tasks一致 - 需要文案展示时对照 interface / 任务定义
参考（本仓库）
protocol-3.1-task-pipeline.md（权威细节）docs/自动战斗框架开发指南.mdtools/schema/pipeline.schema.json- 成熟范例：同目录其它
*.jsonc（如Role_Selection.jsonc）
© overflow65537, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .cursor/skills/maa-punish-pipeline-guide of overflow65537/MAA_Punish.
Open the folder on GitHubat commit c2f24bb
Compare with similar skills
Maa Punish Pipeline Guide next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Maa Punish Pipeline Guide this skilloverflow65537/MAA_Punish | 371 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Maa Cyber Fortune MasterMaaAssistantArknights/MaaAssistantArknights | 24k | — | ~692 | Automated safety check: Pass | AGPL-3.0 | |
| Maa Issue Log AnalysisMaaAssistantArknights/MaaAssistantArknights | 24k | — | ~4k | Automated safety check: Pass | AGPL-3.0 | |
| Maa LoggingMaaEnd/MaaEnd | 4k | — | ~807 | Automated safety check: Pass | AGPL-3.0 | |
| Maa Wikiduorua/narutomobile | 340 | — | ~436 | Automated safety check: Pass | AGPL-3.0 | |
| Maa Project Initduorua/narutomobile | 340 | — | ~2.2k | Automated safety check: Pass | AGPL-3.0 |
Similar skills
Maa Issue Log Analysis
MaaAssistantArknights/MaaAssistantArknights
分析 MaaAssistantArknights 上游仓库公开 Issue（https://github.com/MaaAssistantArknights/MaaAssistantArknights/issues/...
Maa Logging
MaaEnd/MaaEnd
MaaFramework 日志宏用法指南，适用于 MaaEnd cpp-algo。Use when writing logging code, using LogInfo/LogError/LogWarn/LogDebug/LogTrace, outputting containers or custom types to logs, or when the user asks about…
Maa Wiki
duorua/narutomobile
Route MaaFramework questions and other Maa skills to authoritative official documentation, schemas, APIs, bindings, release history, and semantic-change facts through the MaaLLMWiki catalog.
Maa Project Init
duorua/narutomobile
Scan and initialize a MaaFramework game or app automation project for Maa skills and MaaMCP workflows.
Maa Project Create
duorua/narutomobile
Create, extend, diagnose, and update MaaFramework application projects through the create-maa-project MCP server or CLI.
More from overflow65537/MAA_Punish
Git Commit Message
overflow65537/MAA_Punish
Generate precise git commit messages for this repository from staged or working tree diffs.
Maa Punish Log Analysis
overflow65537/MAA_Punish
分析用户给出的本地日志目录或日志文件路径，结合 MAAPunish（MaaFramework + Python 自定义 + MFW-cfa）仓库定位任务卡死、识别失败、Pipeline 与自定义逻辑问题。主日志为 gui.log（cfa 图形界面）、custom.log（Python/agent 自定义）、debug/maa.log（框架运行时）。不下载或解压…
Questions about Maa Punish Pipeline Guide
What does Maa Punish Pipeline Guide do?
MAAPunish 任务流水线 JSON/JSONC 编写与审查指南。含 Pipeline 速查表（识别类型、动作类型、节点字段默认值、JumpBack/Anchor、Custom）。基于 MaaFramework 协议与本仓库 protocol-3.1-task-pipeline.md。在编写或审查 pipeline、排查超时/onerror、或使用…. Maa Punish Pipeline Guide is an agent skill from overflow65537/MAA_Punish.
How do I install Maa Punish Pipeline Guide in Claude Code?
Run `npx skills add overflow65537/MAA_Punish --skill maa-punish-pipeline-guide -a claude-code`. Or copy the skill folder (.cursor/skills/maa-punish-pipeline-guide in overflow65537/MAA_Punish) into .claude/skills/maa-punish-pipeline-guide in your project. Claude Code loads it when a task matches its description.
How do I install Maa Punish Pipeline Guide in Codex?
Run `npx skills add overflow65537/MAA_Punish --skill maa-punish-pipeline-guide -a codex`. Or copy the skill folder (.cursor/skills/maa-punish-pipeline-guide in overflow65537/MAA_Punish) into .agents/skills/maa-punish-pipeline-guide in your project. Codex loads it when a task matches its description.
Can I use Maa Punish Pipeline Guide in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add overflow65537/MAA_Punish --skill maa-punish-pipeline-guide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/maa-punish-pipeline-guide, .gemini/skills/maa-punish-pipeline-guide, .github/skills/maa-punish-pipeline-guide and .opencode/skills/maa-punish-pipeline-guide in your project.
What does Maa Punish Pipeline Guide need to run?
SKILL.md names no scripts, command-line tools or credentials: Maa Punish Pipeline Guide is instructions for the agent only. Our summary lists: Python 3.
Does Maa Punish Pipeline Guide access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Maa Punish Pipeline Guide safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Maa Punish Pipeline Guide use?
Maa Punish Pipeline Guide is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Maa Punish Pipeline Guide use?
About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Maa Punish Pipeline Guide?
Skills that share tags, products or a category with Maa Punish Pipeline Guide: Maa Cyber Fortune Master (MaaAssistantArknights/MaaAssistantArknights, 24k stars), Maa Issue Log Analysis (MaaAssistantArknights/MaaAssistantArknights, 24k stars), Maa Logging (MaaEnd/MaaEnd, 4k stars) and Maa Wiki (duorua/narutomobile, 340 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Maa Punish Pipeline Guide?
overflow65537 (a GitHub user) maintains it in overflow65537/MAA_Punish, which has 371 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 10, 2026.
Source: overflow65537/MAA_Punish on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.