project-eval

项目全面评估报告生成——基于真实源码生成全面评估报告（8 维度评估 + 问题清单 + Top 5 改进——强化：分步评估 + 打磨循环）。用户说"评估 XX 项目 / 全面评估一下项目"时使用。

IndexedMIT

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/idontplaygenshinimpact-project-eval

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found
Runs as: Node.js package

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/project-eval

What's inside

Skill name: project-eval
Description: 项目全面评估报告生成——基于真实源码生成全面评估报告（8 维度评估 + 问题清单 + Top 5 改进——强化：分步评估 + 打磨循环）。用户说"评估 XX 项目 / 全面评估一下项目"时使用。
License: MIT
Instructions: 25 lines in SKILL.md · view on GitHub

Before installing

Ships executable scripts

Files (2)

SKILL.md
skill.mjs

SKILL.md (first lines)

# project-eval：项目全面评估

## 何时使用

用户说以下任一触发：
- "评估 XX 项目 / 全面评估一下项目"
- "这个项目有什么问题 / 代码质量怎么样"
- "帮我做一次项目体检"

## 使用流程

1. **确认项目**：调 `skill__project_eval__evaluate_project`（project=项目名——personal_projects 配置中的 name）
2. **生成报告**：工具读项目全部核心源码（排除测试/配置——核心目录优先）→ subagent 串行分析（源码要点）→ **分步评估 8 维度**（架构/代码质量/测试/安全/性能/可维护性/技术债/风险——每维度单独 subagent——详细）→ 汇总（总评/问题清单/亮点/Top 5）→ **打磨循环**（评审/修正——上下文累积——不缩水）→ 存档 `output/project-evals/项目·xxx-评估报告.md`
3. **查看报告**：总评（评分 1-10）+ 8 维度评估（现状/问题/建议——引用具体文件/函数）+ 问题清单（按严重度排序）+ 亮点 + Top 5 改进
4. **重新评估**：用户说"重新评估" → force=true

## 纪律

- **只基于真实源码**——不编造——引用具体文件/函数/行号
- **问题要具体**（不是"代码质量一般"——是"xxx 函数重复实现 3 次——建议抽象"）
- **平衡**（不只挑刺——亮点也要——评估客观）
- **建议可落地**（不是"优化性能"——是"xxx 处用 memo 避免重渲染——预计收益"）
- **打磨循环**（评审对照质量标准清单——修正只补差距不缩水——上下文累积）

From idontplaygenshinimpact/mashiro-desktop, MIT.

Signals

Stars: 0
Forks: 0
Open issues: 0
Last commit (this folder): Sep 10, 2026 (1 month ago)
Last release: Aug 23, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/idontplaygenshinimpact/mashiro-desktop
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from idontplaygenshinimpact

Cite this page

project-eval skill. Agent Mart. https://agentmart.dev/skills/idontplaygenshinimpact-project-eval (last updated 2026-10-24)