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-generategit 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-generate)<a href="https://agentmods.dev/skills/khazixw2/everything-maa/maa-pipeline-generate"><img src="https://agentmods.dev/badge/skills/khazixw2/everything-maa/maa-pipeline-generate/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-generate"><img src="https://agentmods.dev/badge/skills/khazixw2/everything-maa/maa-pipeline-generate.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 | $0.00069 | $0.05077 |
| Opus 5 | $0.00034 | $0.02538 |
| Sonnet 5 | $0.00014 | $0.01015 |
| Haiku 4.5 | $0.00007 | $0.00508 |
Grade A, and why
maa-pipeline-generate scanned grade A with 0 findings 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 11d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maa Pipeline Generate
如果用户提出的是尚未定义起始状态、安全边界和验收条件的端到端自动化目标,先交给 $maa-workflow-build 建立任务契约与状态机;已有契约时,再用本 skill 生成其中的具体节点与识别参数。
项目初始化接力
生成节点前先在目标项目根目录查找 basic_info.md。存在且包含第 0 节时,读取“0. Maa Skills 接力协议”和第 3/4/5/7/8/9 节,用它快速定位目标文件、公共节点、返回路径、OCR 文本、模板目录与 ROI 基准。它是缓存,不替代当前目标文件和当前设备画面;生成前仍须核实目标文件语法风格,并重新 OCR/截图确认页面。文件缺失或没有第 0 节时按本 skill 直接发现项目结构;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。若相关源码更新更晚,则把缓存视为可能过期并以当前源码为准,不自动刷新或覆盖。
概念
Pipeline 由 Node 组成。本 skill 针对OCR 文本识别节点,按 Pipeline 协议生成节点 JSON 并合并到目标 pipeline 文件。
核心流程:连接设备 → ocr() 拿 box → 扩大 ROI → 合并节点
自带脚本(位于本 skill 的 scripts/ 目录):
| 脚本 | 用途 |
|---|---|
scripts/generate_node.py |
单节点生成(默认 expand=20) |
scripts/generate_sweep.py |
多 expand 变体扫描,找最佳 ROI |
MCP 工具绑定
依赖 maa-mcp MCP 服务。
| 工具 | 说明 |
|---|---|
find_adb_device_list / connect_adb_device |
连接设备 |
ocr |
截图 + OCR 一步完成(内部已调 screencap,外部不要再调) |
load_pipeline / save_pipeline |
读/写 pipeline JSON |
check_and_download_ocr |
首次需下载 OCR 模型 |
run_pipeline |
测试 pipeline 节点 |
输入参数
| 参数 | 必填 | 默认 | 说明 |
|---|---|---|---|
target_text |
✅ | — | 要识别的目标中文文字 |
node_name |
✅ | — | 节点名(PascalCase) |
pipeline_file |
✅ | — | 目标 pipeline 路径(推荐传主 Interface 声明资源根下的项目相对或绝对路径;assets/resource/base/pipeline/xxx.json 是 boilerplate-family 项目示例) |
action_type |
❌ | Click |
Click / DoNothing / LongPress / Swipe / ClickKey / InputText |
expand_offset |
❌ | 20 |
ROI 扩边像素(推荐先用 sweep 找最佳) |
post_delay |
❌ | 500 |
|
timeout |
❌ | 2000 |
|
overwrite |
❌ | False |
节点名冲突时是否覆盖 |
3 步工作流(伪代码)
# === Step 1: 连接设备 ===
from maa_mcp.adb import find_adb_device_list, connect_adb_device
controller_id = connect_adb_device(find_adb_device_list()[0])
# === Step 2: OCR 拿 box + 算 ROI ===
from maa_mcp.vision import ocr
from maa_mcp.download import check_and_download_ocr
ocr_results = ocr(controller_id)
if isinstance(ocr_results, str) and "OCR 模型文件不存在" in ocr_results:
check_and_download_ocr()
ocr_results = ocr(controller_id)
matched = [r for r in ocr_results if target_text in (r.text if hasattr(r, "text") else r["text"])]
best = max(matched, key=lambda r: r.score if hasattr(r, "score") else r["score"])
box = best.box if hasattr(best, "box") else best["box"]
# 扩大 ROI(720p 硬编码 + 4 边裁剪)
SCREEN_W, SCREEN_H = 720, 1280
x, y, w, h = box
E = expand_offset
roi = [
max(0, x - E),
max(0, y - E),
min(SCREEN_W - max(0, x - E), w + 2 * E),
min(SCREEN_H - max(0, y - E), h + 2 * E),
]
# === Step 3: 合并到目标 pipeline ===
from maa_mcp.pipeline_tools import load_pipeline, save_pipeline
from pathlib import Path
# Read resource[].path from the project's main Interface and resolve the
# supplied path against that project root before reading or writing it.
project_root = find_project_root()
pipeline_path = resolve_pipeline_path(pipeline_file)
existing = load_pipeline(str(pipeline_path)) or {}
if node_name in existing and not overwrite:
raise RuntimeError(f"节点 '{node_name}' 已存在")
existing[node_name] = {
"recognition": "OCR",
"expected": [target_text],
"roi": roi,
"action": action_type,
"post_delay": post_delay,
"timeout": timeout,
}
save_pipeline(
pipeline_json=json.dumps(existing, ensure_ascii=False, indent=4),
output_path=str(pipeline_path),
overwrite=True,
)
What ships with it
4 files 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.
- 11d ago First seen · 313 lines · 69 tokens per session scan A c98df059c856
maa-pipeline-generate is a skill published in the GitHub repository KhazixW2/Everything-Maa (12 stars, last pushed 3d ago), licensed MIT. It adds 69 tokens to every session and 5,077 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
qa
QA test your code changes by reading your git diff, choosing the right validation path for frontend/browser and backend changes, and reporting pass/fail with evidence.
gemigo-cli
Use when the user wants to publish an already-built static website or front-end app through GemiGo, such as a Vite/React/Vue static build, plain HTML/CSS/JS page, landing page, demo, docs site, or small browser app, and get a hosted public URL.
ui-ux-pro-max
Use when the user wants professional UI/UX design guidance, design-system generation, UX review, or stack-specific frontend guidance through a bundled local UI/UX Pro Max dataset and Python search runtime.
panel-app-react-vite-creator
Create or update an engineering-style NextClaw Panel component with pnpm, Vite, React, TypeScript, and Tailwind CSS, then build it into a static .panel directory inside a schema v2 package or an explicitly loose workspace Panel. Use for modern, reusable, complex, Agent-powered, typed Panel interfaces.
coding-standards
A set of general coding standards and practical patterns for TypeScript, JavaScript, React, and Node.js. It covers readable naming, simple designs, avoiding repetition, and delaying unnecessary features.
accessibility-patterns
WCAG 2.2 AA compliance, ARIA patterns, keyboard navigation, screen reader optimization.