scene-analysis

scene-analysis is a skill for Claude Code from AgenticAIPlan/AgenticAISkills. It costs 58 tokens per session (1,059 once invoked), scanned A, original, MIT.

A Chinese-language guide for deciding how to approach a proposed AI project before building it. It compares agents, fixed workflows, small deep-learning models, ordinary rules, and delaying the project.

In plain words
What is it for?
Use it during requirements reviews to classify a business problem, choose a technical path, assess whether to combine models, and define a first-stage MVP.
Why use it?
It helps teams avoid using AI where normal code would be clearer, or starting work without enough data, a clear process, or a testable first version.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agentic-ai-skills plugin — 54 skills shipped together

Good fit Use it during requirements reviews to classify a business problem, choose a technical path, assess whether to combine models, and define a first-stage MVP.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agenticaiplan/agenticaiskills/scene-analysis
Install

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.

Any agent
npx skills add AgenticAIPlan/AgenticAISkills --skill scene-analysis
Clone the repo
git clone --depth 1 https://github.com/AgenticAIPlan/AgenticAISkills

Made for: Claude Code.

Or install agentic-ai-skills, the plugin that ships this one along with the rest of its 54 skills.

Wrote 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.

agentmods badge for scene-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/scene-analysis.svg)](https://agentmods.dev/skills/agenticaiplan/agenticaiskills/scene-analysis)
Your own site
<a href="https://agentmods.dev/skills/agenticaiplan/agenticaiskills/scene-analysis"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/scene-analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,059 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.01059
Opus 5 $0.00029 $0.00530
Sonnet 5 $0.00012 $0.00212
Haiku 4.5 $0.00006 $0.00106

Measured 8d ago against content hash 3e369121a959, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

scene-analysis 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 8d 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.

skills/scene-analysis/SKILL.md · 104 lines

What it actually says

Scene Analysis

适用场景

当用户需要在 AI 项目正式启动前,快速判断“这个需求该不该做 AI、该走哪条技术路径、第一阶段应该怎么推进”时,使用本 Skill。

典型触发场景:

  • 业务部门提出一个模糊 AI 需求,需要先判断是否值得立项
  • 咨询顾问或产品经理需要给出“Agent / Workflow / DL / 规则代码”的初步路径建议
  • 技术负责人需要在需求评审会上快速识别伪需求、高风险需求或前置条件不足的需求
  • 团队在讨论“要不要大小模型连用”时,需要先根据输入类型和任务特征做判断

输入要求

  • 业务场景描述
  • 目标用户或使用角色
  • 当前人工处理流程
  • 预期产出或希望改善的结果
  • 已知约束:数据、系统接口、合规、成本、时效、风险

如果信息不完整,至少要能回答:

  • 谁在用
  • 现在怎么做
  • 最痛的环节在哪里
  • 为什么现在想做 AI

执行步骤

  1. 先判断需求属于哪一类:
    • A 类:偏语言理解、知识检索、内容生成、多步推理,优先考虑大模型或 Agent
    • B 类:偏固定流程、信息整合、低复杂度自动化,优先考虑 Workflow 助手
    • C 类:偏规则、检索、BI、数据治理,优先考虑规则代码、SQL、BI 或流程治理
    • D 类:条件不具备、边界不清或风险过高,当前不建议推进
  2. 再判断具体路径:
    • 单轮问答或资料检索:知识库问答 / RAG
    • 多步流程编排:Workflow
    • 复杂判断与协同:Agent
    • 图像、票据、时序、语音等非结构化输入为核心:DL 小模型
    • 规则能完整描述:直接写代码,不必强行上 AI
  3. 对优先级做初判,重点看四个维度:
    • 业务价值是否高频且有明确痛点
    • 实施难度是否可控
    • 当前数据和流程基础是否具备
    • 第一阶段是否能做出可验证 MVP
  4. 判断是否需要大小模型连用。只有同时满足以下两个条件,才建议连用:
    • 有图像、音频、扫描件、时序等非结构化输入需要先感知
    • 感知结果还需要进一步理解、分析或生成自然语言
  5. 给出第一阶段建议,明确:
    • 第一版做什么
    • 当前不做什么
    • 下一步应该进入哪个 Skill 或哪个非 AI 方案

输出要求

输出必须使用结构化 Markdown,至少包含以下内容:

## 场景分析报告

**业务场景:** [填入]
**目标用户:** [填入]
**分析日期:** [填入]

### 1. 需求分类
- 类别:A / B / C / D
- 结论理由:
  1. [理由 1]
  2. [理由 2]
  3. [理由 3]

### 2. 推荐技术路径
- 推荐路径:知识库问答 / Workflow / Agent / DL 小模型 / 大小模型连用 / 规则代码 / 暂缓
- 是否需要 DL:是 / 否
- 路径理由:[一句话]
- 当前不推荐的路径:[一句话]

### 3. 优先级判断
- 级别:高 / 中 / 低 / 暂缓
- 业务价值:[评估]
- 实施难度:[评估]
- 当前基础:[评估]

### 4. 第一阶段建议
- 第一版做什么:[一句话]
- 第一版不做什么:[排除项]
- 验证标准:[可测量标准]

### 5. 下一步动作
- [应该进入的下一个 Skill 或替代方案]

输出必须明确指出风险、假设和待确认项,不能只给模糊建议。

参考资料

如果任务中已经有需求文档、会议纪要、现有流程图、业务 SOP 或历史方案,请优先结合这些材料再做判断,不要只根据一句口号式需求下结论。

Changes

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.

  1. 8d ago First seen · 104 lines · 58 tokens per session scan A 3e369121a959

Subscribe to this mod's changes

scene-analysis is a skill published in the GitHub repository AgenticAIPlan/AgenticAISkills (11 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 1,059 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens