perf-theory-gatherer

仓库创建 2025年10月22日最近提交 1 天前SkillHot 收录 11 小时前
▸ 精选理由

快速产出有证据支持的待测假设,指导后续试验。

这个 Skill 做什么

根据 git 历史和代码证据为性能问题生成最多五条可验证假设。

通过查看 git 历史和代码证据,帮你为特定性能场景形成最多五条可验证的假设。适合在排查回归或突发慢速问题前做取证,会把相关 commit、文件和调用链当证据并标注可信度。产出直接可用于后续实验验证的假设清单,避免盲目改动和无效调优。

▸ 展开 SKILL.md 英文原文

Use when generating performance hypotheses backed by git history and code evidence.

开发编程假设生成git 历史证据驱动通用
1.8k
Stars
518
Forks
23
仓库内 Skill
积累中
7 日增星
安装 / 使用
给你的 Agent 一句话(通用)
帮我安装这个 skill:https://raw.githubusercontent.com/composio-community/awesome-claude-plugins/master/perf/skills/theory/SKILL.md
或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/composio-community/awesome-claude-plugins/master/perf/skills/theory/SKILL.md"
SKILL.MD 节选查看完整文件 ↗
# perf-theory-gatherer

Generate performance hypotheses for a specific scenario.

Follow `docs/perf-requirements.md` as the canonical contract.

## Required Steps

1. Review recent git history (scope to relevant paths when possible).
2. Identify code paths involved in the scenario (repo-map or grep).
3. Produce up to 5 hypotheses with evidence + confidence.

## Output Format

```
hypotheses:
  - id: H1
    hypothesis: <short description>
    evidence: <file/path or git change>
    confidence: low|medium|high
  - id: H2
    ...
```

## Constraints

- MUST check git history before hypothesizing.
- No optimization suggestions; only hypotheses.
- Keep to 5 hypotheses maximum.
via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有