AI Agent Skill HUB

命令列表与管线 Skill (Pass Graph Pipeline)

## 角色定位

12 stars
byhaolange
View on GitHubInstallation ↓

Best use case

命令列表与管线 Skill (Pass Graph Pipeline) is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

## 角色定位

Teams using 命令列表与管线 Skill (Pass Graph Pipeline) should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/pass-graph-pipeline/SKILL.md --create-dirs "https://raw.githubusercontent.com/haolange/RDC-Agent-Frameworks/main/debugger/common/skills/pass-graph-pipeline/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/pass-graph-pipeline/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How 命令列表与管线 Skill (Pass Graph Pipeline) Compares

Feature / Agent命令列表与管线 Skill (Pass Graph Pipeline)Standard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

## 角色定位

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# 命令列表与管线 Skill (Pass Graph Pipeline)

## 角色定位

你负责从 pass graph、pipeline state 与 resource dependency 的角度收敛问题。

## 必读依赖

- `../../agents/04_pass_graph_pipeline.md`
- `../../knowledge/spec/registry/active_manifest.yaml`

## 输出要求

- pass divergence 结论
- pipeline/resource chain 证据
- 候选 `root_drawcall` 或 `first_divergence_event`
- 是否需要回到 re-anchor

## 禁止行为

- 不在没有结构化证据时仅凭截图给出 pipeline 根因
- 不绕过 `causal_anchor` 直接裁决

Related Skills

rdc-optimizer

12
from haolange/RDC-Agent-Frameworks

Public main skill for the incubating optimizer framework. Use when the user wants to analyze performance, identify bottlenecks, design experiments, or validate optimization gains from captures, traces, or profiling evidence. This skill is the future optimizer entry and currently provides the minimum intake contract only.

症状分类 Skill (Triage Taxonomy)

12
from haolange/RDC-Agent-Frameworks

## 角色定位

怀疑论审查 Skill (Skeptic)

12
from haolange/RDC-Agent-Frameworks

## 角色定位

着色器与 IR Skill (Shader IR)

12
from haolange/RDC-Agent-Frameworks

## 角色定位

报告与知识整理 Skill (Report Knowledge Curator)

12
from haolange/RDC-Agent-Frameworks

## 角色定位

参考合同 Skill (Reference Contract)

12
from haolange/RDC-Agent-Frameworks

## 角色定位

rdc-debugger

12
from haolange/RDC-Agent-Frameworks

Public main skill for the RenderDoc/RDC GPU debugger framework. Use when the user wants defect diagnosis, root-cause analysis, regression explanation, or fix verification from one or more `.rdc` captures. This skill owns intent gate classification, plan/intake normalization, debug_plan handoff, execution gating, broker-owned specialist dispatch, redispatch, timeout handling, and verdict gating.

调试计划编译 Skill (Plan Compiler)

12
from haolange/RDC-Agent-Frameworks

## 角色定位

像素取证 Skill (Pixel Value Forensics)

12
from haolange/RDC-Agent-Frameworks

## 角色定位

驱动与设备 Skill (Driver Device)

12
from haolange/RDC-Agent-Frameworks

## 角色定位

规划补料 Skill (Clarification)

12
from haolange/RDC-Agent-Frameworks

## 角色定位

Capture / Repro Specialist

12
from haolange/RDC-Agent-Frameworks

当前角色是 internal/debug-only specialist。