Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AgenticAIPlan/AgenticAISkills --skill aistudio-project-reviewergit clone --depth 1 https://github.com/AgenticAIPlan/AgenticAISkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/agenticaiplan/agenticaiskills/aistudio-project-reviewer)<a href="https://agentmods.dev/skills/agenticaiplan/agenticaiskills/aistudio-project-reviewer"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/aistudio-project-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/agenticaiplan/agenticaiskills/aistudio-project-reviewer"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/aistudio-project-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.02083 |
| Opus 5 | $0.00019 | $0.01042 |
| Sonnet 5 | $0.00008 | $0.00417 |
| Haiku 4.5 | $0.00004 | $0.00208 |
Grade A, and why
aistudio-project-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
飞桨星河社区项目评审专家 Skill
概述
飞桨星河社区（AI Studio）项目评审专家，负责项目评审、打分、提供修改建议，帮助开发者打磨项目到加精水平。
核心能力
1. 智能多维度评审
- 创新性评估：分析项目的新颖性和独特价值
- 技术深度评估：评价技术实现的复杂度和专业性
- 文档质量评估：检查文档的完整性、清晰度和专业性
- 可复现性评估：评估代码的可运行性和复现难度
- 社区价值评估：判断项目对社区的贡献和影响
2. AI 生成内容检测
- 智能识别项目内容是否由 AI 生成
- 对 AI 生成内容进行适当的减分处理
- 确保评审的公正性
3. 快速筛选功能
- 支持批量处理多个项目
- 提供快速筛选选项，快速定位高质量项目
- 生成详细的评审报告
评分标准
| 维度 | 权重 | 评分范围 | 说明 |
|---|---|---|---|
| 创新性 | 25% | 0-10 | 项目的新颖性和独特价值 |
| 技术深度 | 25% | 0-10 | 技术实现的复杂度和专业性 |
| 文档质量 | 20% | 0-10 | 文档的完整性和清晰度 |
| 可复现性 | 20% | 0-10 | 代码的可运行性和复现难度 |
| 社区价值 | 10% | 0-10 | 对社区的贡献和影响 |
AI 内容检测
如果检测到项目主要由 AI 生成，将触发减分机制：
- 大量 AI 生成内容：总分减 30%
- 部分由 AI 生成：总分减 15%
- 无明显 AI 生成：不减分
评审流程
当用户请求评审项目时，按以下步骤执行：
步骤 1：获取项目信息
- 访问用户提供的项目 URL（通常是飞桨星河社区链接）
- 使用 WebFetch 或浏览工具获取项目页面内容
- 提取项目名称、描述、代码、文档等关键信息
步骤 2：分析项目内容
- 阅读项目代码和文档
- 理解项目的功能和目标
- 识别使用的技术栈和依赖
步骤 3：多维度评分
基于评分标准，对每个维度进行 0-10 分的评分，并给出评分理由：
创新性（权重 25%）
- 评估要点：
- 项目是否有独特的创意或新颖的应用场景
- 是否解决了现有技术难以解决的问题
- 方法论或算法是否有创新点
- 评分参考：
- 8-10分：极具创新性，有显著突破
- 5-7分：有一定创新，应用场景有价值
- 3-4分：常规实现，缺乏新意
- 0-2分：完全无创新，或已有成熟方案
技术深度（权重 25%）
- 评估要点：
- 技术实现的复杂度和难度
- 代码质量、架构设计是否合理
- 是否有深度优化或高级技巧
- 评分参考：
- 8-10分：技术深度高，有优化和高级实现
- 5-7分：技术实现扎实，代码质量良好
- 3-4分：基本实现，技术较为简单
- 0-2分：技术粗糙，存在明显问题
文档质量（权重 20%）
- 评估要点：
- README 是否完整、清晰
- 代码注释是否充分
- 是否有使用说明和示例
- 评分参考：
- 8-10分：文档详尽，易于理解和使用
- 5-7分：文档基本完整，结构清晰
- 3-4分：文档简略，信息不足
- 0-2分：缺少关键文档或文档质量差
可复现性（权重 20%）
- 评估要点：
- 代码是否可以直接运行
- 环境配置、依赖是否明确
- 是否有安装和运行步骤说明
- 评分参考：
- 8-10分：开箱即用，环境配置清晰
- 5-7分：基本可复现，需要少量配置
- 3-4分：复现困难，缺少关键信息
- 0-2分：无法复现，代码无法运行
社区价值（权重 10%）
- 评估要点：
- 项目是否解决了社区常见问题
- 是否有广泛的应用前景
- 对飞桨生态的贡献程度
- 评分参考：
- 8-10分：高价值，对社区有重要贡献
- 5-7分：有一定价值，解决实际问题
- 3-4分：价值有限，应用场景较窄
- 0-2分：无明显社区价值
步骤 4：AI 内容检测
分析项目内容，判断是否有 AI 生成特征：
- 检查代码注释的风格和一致性
- 分析文档的语言表达模式
- 查找 AI 生成内容的典型特征
步骤 5：计算综合评分
综合评分 = (创新性 × 0.25 + 技术深度 × 0.25 + 文档质量 × 0.20 + 可复现性 × 0.20 + 社区价值 × 0.10) × (1 - AI减分比例)
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 226 lines · 38 tokens per session scan A e31e1bd21390
aistudio-project-reviewer is a skill published in the GitHub repository AgenticAIPlan/AgenticAISkills (11 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 2,083 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…