New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Pipeline Debug

by 1204244136 in 1204244136/MDA

调试和优化 MaaFramework Pipeline JSON。用于对照 schema 验证配置，检测缺失引用、循环依赖、孤立节点、命名与行为不匹配、ROI/阈值问题，并给出可靠性、性能和可维护性改进建议。触发词包括 debug pipeline、validate pipeline、optimize pipeline、pipeline error。

MITAuto-check passed

Install Pipeline Debug

skills CLI
$ npx skills add 1204244136/MDA --skill pipeline-debug -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install 1204244136/MDA pipeline-debug --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/1204244136/MDA.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/pipeline-debug .claude/skills/pipeline-debug && rm -rf skills-src

Use ~/.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/

Facts

Skill name
pipeline-debug
GitHub stars
119
Token cost
~835 tokens
SKILL.md length
217 words
Files
5 (incl. references)
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

调试和优化 MaaFramework Pipeline JSON。用于对照 schema 验证配置，检测缺失引用、循环依赖、孤立节点、命名与行为不匹配、ROI/阈值问题，并给出可靠性、性能和可维护性改进建议。触发词包括 debug pipeline、validate pipeline、optimize pipeline、pipeline error。

  • Works in 8 steps: 读取规范文件 → 分析 Pipeline 片段 → 对照 schema 验证 → …
  • SKILL.md covers 功能说明, 使用场景, 工作流程 and 注意事项, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pipeline Debug is an agent skill from 1204244136/MDA. 调试和优化 MaaFramework Pipeline JSON。用于对照 schema 验证配置，检测缺失引用、循环依赖、孤立节点、命名与行为不匹配、ROI/阈值问题，并给出可靠性、性能和可维护性改进建议。触发词包括 debug pipeline、validate pipeline、optimize pipeline、pipeline error。

Its SKILL.md is about 840 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/common-patterns.md`, `references/debug-rules.md` and `references/output-format.md`). Compatibility notes: Designed for Claude Code

The repository describes itself as: Nikke小助手 | Assistant For Goddess of Victory: Nikke. The licence is MIT.

Example prompts

  • “/pipeline-debug”

Requirements

  • Compatibility (from SKILL.md): Designed for Claude Code
  • Pre-approved tools (allowed-tools): Read, Grep, Glob

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. 读取规范文件
  2. 分析 Pipeline 片段
  3. 对照 schema 验证
  4. 通过命名分析节点语义
  5. 分析节点关系
  6. 识别常见问题
  7. 生成优化建议
  8. 提供修正方案

What it can do on your machine

Read from SKILL.md and the folder at commit 9fb9b48. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep
    • Glob

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    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.

  • Compatibility

    Designed for Claude Code

    From compatibility in the SKILL.md frontmatter.

Context cost

Pipeline Debug loads about 835 tokens when it runs, and up to ~8.2k if it reads all its reference files. Until then it costs about 48 tokens; SKILL.md has 217 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~835
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.2k

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 1204244136/MDA at commit 9fb9b48, republished under its MIT licence (© 1204244136). 217 words, ~835 tokens.

Download SKILL.mdSave it as .claude/skills/pipeline-debug/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
pipeline-debug
description
调试和优化 MaaFramework Pipeline JSON。用于对照 schema 验证配置，检测缺失引用、循环依赖、孤立节点、命名与行为不匹配、ROI/阈值问题，并给出可靠性、性能和可维护性改进建议。触发词包括 debug pipeline、validate pipeline、optimize pipeline、pipeline error。
allowed-tools
Read, Grep, Glob
compatibility
Designed for Claude Code
license
MIT

MaaFramework Pipeline 调试

功能说明

  • 对照 tools/schema/pipeline.schema.json 及相关 schema 验证 Pipeline JSON。
  • 检测结构性问题：缺失引用、循环依赖、孤立节点、意外终止。
  • 通过命名规范分析节点角色，从节点名推断其预期行为。
  • 检测命名与代码不匹配，例如 Click 节点没有动作，Visible 节点却执行点击。
  • 提供性能、可靠性和可维护性优化建议。
  • 必要时生成修正后的 Pipeline 片段，可以增删节点以实现正确行为。

使用场景

  • Pipeline JSON 运行不符合预期。
  • 部署前验证 Pipeline 配置。
  • 排查节点跳转、识别失败、重复点击、误点、卡死。
  • 优化 ROI、阈值、流程结构或异常处理。
  • 根据节点名理解流程语义，检查命名是否与实际识别/动作一致。

工作流程

1. 读取规范文件

优先读取当前项目中的 schema：

  1. tools/schema/pipeline.schema.json
  2. tools/schema/interface_import.schema.json
  3. tools/schema/interface.schema.json
  4. tools/schema/custom.recognition.schema.json
  5. tools/schema/custom.action.schema.json

如果项目缺少某个 schema，说明缺失项并继续基于 MaaFramework 通用协议分析。

2. 分析 Pipeline 片段
  1. 解析 JSON，列出所有节点。
  2. 提取关键字段：recognition、action、enabled、next、interrupt、sub、on_error、timeout、max_hit。
  3. 构建节点图：父节点到子节点、反向引用、入口节点、终止节点。
  4. 区分 v1 简写字段和 v2 {type, param} 字段。
3. 对照 schema 验证

逐节点检查：

  • 必需字段是否齐全。
  • 字段类型是否匹配。
  • 枚举值、数值范围、字符串模式是否合法。
  • 识别类型及参数是否正确。
  • 动作类型及参数是否正确。
  • Custom 节点名和参数是否可能与 agent 注册不一致。
4. 通过命名分析节点语义

使用 Pipeline 节点命名规范 理解节点角色：

  • <Domain>Main：入口节点。
  • <Domain><Subtask>Flow：流程编排节点。
  • <Domain>Enter<Page>：进入页面或功能。
  • <Domain>On<Page>Page / <Domain><Object>Visible：页面或 UI 状态检测。
  • <Domain>Click<Object> / Select / Claim / Purchase：动作节点。
  • <Domain>Confirm<Object>：确认弹窗或确认操作。
  • <Domain><Page>Entered：进入成功哨兵节点。
  • <Domain>End / EndTask：终止节点。

重点检查命名与行为不匹配：

  • Click<Object> 但没有 action: Click 或等价动作。
  • Visible / On<Page>Page 却执行点击。
  • Flow 节点包含具体识别或动作。
  • Enter<Page> 点击后没有成功哨兵或重试/异常处理。
  • Detected 暴露底层识别实现，而 Visible / Available / Selected 更符合业务语义。
5. 分析节点关系
  • 所有 next[]、interrupt[]、sub[]、on_error[] 目标都必须存在。
  • 识别循环是否有退出条件、max_hit、timeout 或明确终止节点。
  • 找出无法从入口到达的孤立节点。
  • 找出没有 next 且不像终止节点的死胡同。
  • 检查 [JumpBack]、[Anchor] 等节点属性是否用于合适场景。
6. 识别常见问题

详见 调试规则参考。快速检查：

  • 缺少识别或识别类型错误。
  • TemplateMatch 缺模板、OCR 缺 expected、ColorMatch 缺 lower/upper。
  • ROI 过大、阈值过低或过高。
  • 点击后没有验证下一画面。
  • 重复点击同一按钮，可能误点到下一页元素。
  • enabled 默认值与 Project Interface 选项语义不一致。
7. 生成优化建议

建议按优先级输出：

  1. 正确性问题：会导致执行失败、误点、卡死。
  2. 可靠性问题：弹窗、加载、动画、网络波动下容易失败。
  3. 性能问题：全屏识别、大模板、高频 OCR。
  4. 可维护性问题：命名不清、过度拆分、重复节点、缺少 desc。
8. 提供修正方案

如发现问题，给出修正后的 JSON 片段，并说明每处改动原因。响应格式见 输出格式。

注意事项

  • v1 简写和 v2 object 格式可能共存，应按项目现状判断，不要强行重写无关节点。
  • 无 next 的节点可以是合法终止节点，但必须符合流程语义。
  • enabled 默认为 true，只有显式 false 才默认关闭。
  • interrupt / sub / on_error 的语义依项目使用习惯和 MaaFramework 版本而定，先查 schema 和现有模式。
  • 模板路径通常相对 image/resource 图片目录，具体以当前项目约定为准。
  • OCR expected 可能支持正则；是否自动 i18n 取决于当前项目工具链。
  • 输出问题时优先给高置信度结论；不确定项标为“需要运行日志或截图验证”。

参考资料

© 1204244136, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in .claude/skills/pipeline-debug of 1204244136/MDA.

  • SKILL.md
  • references/common-patterns.md
  • references/debug-rules.md
  • references/output-format.md
  • references/pipeline-node-naming.md

Open the folder on GitHubat commit 9fb9b48

Compare with similar skills

Pipeline Debug 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.

Pipeline Debug compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pipeline Debug this skill1204244136/MDA119—~835Automated safety check: PassMIT
Debugasgeirtj/system_prompts_leaks69k—~439Automated safety check: PassCC0-1.0
Openclaw Debuggingopenclaw/openclaw392k—~1.9kAutomated safety check: PassMIT
Debugging Executionsn8n-io/n8n207k—~2.6kAutomated safety check: PassCustom licence
Debugging Toolkitsickn33/agentic-awesome-skills47k1 repos~344Automated safety check: PassMIT
Runtime Debugvercel/next.js143k1 repos~618Automated safety check: PassMIT

Similar skills

  • Debug

    asgeirtj/system_prompts_leaks

    Enable debug logging for this session and help diagnose issues

    69k GitHub stars~439 tokensUpdated yesterday
    Auto-check passed

  • Openclaw Debugging

    openclaw/openclaw

    Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored…

    392k GitHub stars~1.9k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Debugging Executions

    n8n-io/n8n

    Official

    Debug failed or wrong-output workflow executions using executions tools.

    207k GitHub stars~2.6k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Debugging Toolkit

    sickn33/agentic-awesome-skills

    A skill your agent uses when working with debugging toolkit smart debug (Alias for debugging-toolkit-smart-debug)

    47k GitHub starsUsed in 1 repo~344 tokens
    DevelopmentAuto-check passed

  • Runtime Debug

    vercel/next.js

    Official

    Debug and verification workflow for runtime-bundle and module-resolution regressions.

    143k GitHub starsUsed in 1 repo~618 tokens
    DevelopmentAuto-check passed

  • Hypothesis-Driven Debugging

    code-yeongyu/oh-my-openagent

    Runs a hypothesis-driven debugging loop for crashes, hangs and silent failures in any language, grounding every claim in runtime evidence and locking the fix with a test.

    70k GitHub stars~3.2k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from 1204244136/MDA

All 9 skills in this repo

  • Generate Pi Task

    1204244136/MDA

    根据 MaaFramework Pipeline 定义生成或更新 Project Interface 任务 JSON。用于创建、编辑或扩展 assets/tasks/ 下的任务文件，将 Pipeline 节点映射为用户可配置选项（switch/select/checkbox/input）并绑定 pipelineoverride。

    119 GitHub stars~1k tokensUpdated 3 days ago
    Auto-check passed

  • Dmp Analysis

    1204244136/MDA

    分析 Windows 崩溃转储文件（.dmp），诊断 MaaFramework / MXU 项目及其依赖项的崩溃。用于 issue 日志包或附件中发现 .dmp 文件，或用户要求分析 DMP / 崩溃转储时。

    119 GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed

  • Go Service Guide

    1204244136/MDA

    MaaFramework Go Agent / go-service 编写指南。用于编写、修改或审查 agent/go-service/ 下的 Go 自定义识别器、动作、EventSink，或了解 MaaFramework Go Agent 的注册、日志、目录组织和参数解析模式。

    119 GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed

  • Maa Logging

    1204244136/MDA

    MaaFramework C++ 日志宏用法指南。用于写 C++ MaaFramework 扩展、Custom 组件或工具代码时使用 LogInfo/LogError/LogWarn/LogDebug/LogTrace、VAR、容器输出和自定义类型日志。

    119 GitHub stars~790 tokensUpdated 3 days ago
    Auto-check passed

  • Mda Issue Log Analysis

    1204244136/MDA

    分析 MDA 公开 Issue、日志包或本地日志。用于 https://github.com/1204244136/MDA/issues/...、1234、MDA 日志压缩包、识别失败、任务卡死、控制器差异、Pipeline/Agent/MXU 问题。会从…

    119 GitHub stars~1.7k tokensUpdated 3 days ago
    Auto-check passed

  • Mda Project Guide

    1204244136/MDA

    MDA 项目专属开发指南。用于在 MDA 中编写或审查 MaaFramework Pipeline、Project Interface 任务、locale、go-service 组件时补充项目结构、业务域、命名习惯和现有任务选项示例。与通用 pipeline-guide、pipeline-debug、generate-pi-task、go-service-guide 配合使用。

    119 GitHub stars~1.8k tokensUpdated 3 days ago
    Auto-check passed

Questions about Pipeline Debug

What does Pipeline Debug do?

调试和优化 MaaFramework Pipeline JSON。用于对照 schema 验证配置，检测缺失引用、循环依赖、孤立节点、命名与行为不匹配、ROI/阈值问题，并给出可靠性、性能和可维护性改进建议。触发词包括 debug pipeline、validate pipeline、optimize pipeline、pipeline error。. Pipeline Debug is an agent skill from 1204244136/MDA.

How do I install Pipeline Debug in Claude Code?

Run `npx skills add 1204244136/MDA --skill pipeline-debug -a claude-code`. Or copy the skill folder (.claude/skills/pipeline-debug in 1204244136/MDA) into .claude/skills/pipeline-debug in your project. Claude Code loads it when a task matches its description.

How do I install Pipeline Debug in Codex?

Run `npx skills add 1204244136/MDA --skill pipeline-debug -a codex`. Or copy the skill folder (.claude/skills/pipeline-debug in 1204244136/MDA) into .agents/skills/pipeline-debug in your project. Codex loads it when a task matches its description.

Can I use Pipeline Debug 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 1204244136/MDA --skill pipeline-debug -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pipeline-debug, .gemini/skills/pipeline-debug, .github/skills/pipeline-debug and .opencode/skills/pipeline-debug in your project.

What does Pipeline Debug need to run?

SKILL.md names no scripts, command-line tools or credentials: Pipeline Debug is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep, Glob. Compatibility (from SKILL.md): Designed for Claude Code.

Does Pipeline Debug 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 Pipeline Debug 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 Pipeline Debug use?

Pipeline Debug is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pipeline Debug use?

About 835 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.3k tokens, read only when the agent opens those files.

What are the alternatives to Pipeline Debug?

Skills that share tags, products or a category with Pipeline Debug: Debug (asgeirtj/system_prompts_leaks, 69k stars), Openclaw Debugging (openclaw/openclaw, 392k stars), Debugging Executions (n8n-io/n8n, 207k stars) and Debugging Toolkit (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pipeline Debug?

1204244136 (a GitHub user) maintains it in 1204244136/MDA, which has 119 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 5, 2026.

Source: 1204244136/MDA on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.