rdc-optimizer

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.

12 stars

byhaolange

View on GitHub Installation ↓

Best use case

rdc-optimizer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Teams using rdc-optimizer 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/rdc-optimizer/SKILL.md --create-dirs "https://raw.githubusercontent.com/haolange/RDC-Agent-Frameworks/main/optimizer/common/skills/rdc-optimizer/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/rdc-optimizer/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How rdc-optimizer Compares

Feature / Agent	rdc-optimizer	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

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

# RDC Optimizer

## 目标

你是 `optimizer` framework 的 public main skill 骨架。

当前 framework 仍处于 `incubating`，所以你的职责只到：

- 接住优化/性能归因类请求
- 明确这是 `optimizer` 而不是 `debugger`
- 收敛输入、预算目标、实验预期与输出形式
- 指向 `optimizer/common/` 作为后续 SSOT 起点

## 最小 intake

至少确认：

- 当前性能问题或预算目标是什么
- 可用输入是 capture、trace、profile、A/B 数据还是指标面板
- 用户要的是瓶颈归因、优化方案、实验设计还是收益验证

## 当前边界

- 不把 `optimizer` 伪装成已完成的 GA framework
- 不引用 `debugger/common/` 作为 optimizer 的规则来源
- 不假装当前已存在完整的平台模板、hooks 或验证闭环

Related Skills

症状分类 Skill (Triage Taxonomy)

from haolange/RDC-Agent-Frameworks

## 角色定位

怀疑论审查 Skill (Skeptic)

from haolange/RDC-Agent-Frameworks

## 角色定位

着色器与 IR Skill (Shader IR)

from haolange/RDC-Agent-Frameworks

## 角色定位

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

from haolange/RDC-Agent-Frameworks

## 角色定位

参考合同 Skill (Reference Contract)

from haolange/RDC-Agent-Frameworks

## 角色定位

rdc-debugger

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.