prism-recon

本条目收录公开技能“prism-recon”,归入 Skillπ「写代码与代码审查」使用场景,并关联「软件开发与 IT」职业。目录标签:ai-lab、前端架构、组件分析、状态管理。此页用于按任务发现相关资源;请通过固定原站版本核对实际能力、依赖环境和所需权限。本站仅提供独立目录介绍与原站入口,原始文件和附件依各自许可开放。

仓库
jeremylongshore/tons-of-skills-marketplace

安装方式

先用 Prompt 核对来源,也可切换到安装命令或下载可用的安装包。

安装方式

用 AI 助手安装

复制提示词,让助手先核对固定版本和依赖。

查看 Prompt收起 Prompt
先检查当前 Agent 是否已安装 SkillPI Skill Finder。如果尚未安装,请按官方仓库的说明安装并启用:https://github.com/Findskills/skillpi。然后使用 Skill Finder 打开此 SkillPI 详情页并定位 "prism-recon":https://skillpi.com/zh/skills/deepskill-faebfe75d3990aaedf369a6eb1dc01a34aa60327a8f1bade337a26dfdbce5a27。安装前核对上游来源和版本:https://github.com/jeremylongshore/tons-of-skills-marketplace/blob/6ea46b08dce892944db7c16f28d0b5308d402402/plugins/ai-agency/tonone/skills/prism-recon/SKILL.md。来源不一致时停止并说明差异。核对通过后,用 Skill Finder 安装目标 Skill,并报告安装路径和来源版本。

此命令从 GitHub 来源仓库获取指定技能。运行前请先查看源文件。

运行工具
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/6ea46b08dce892944db7c16f28d0b5308d402402/plugins/ai-agency/tonone/skills/prism-recon --skill prism-recon
许可协议: —

来源与配置

查看 GitHub 源码

jeremylongshore/tons-of-skills-marketplace固定提交 6ea46b08dce892944db7c16f28d0b5308d402402

配置方式待核实

请查看原始来源中的适用工具、依赖和权限要求。

安装实测待补充

本条目收录公开技能“prism-recon”,归入 Skillπ「写代码与代码审查」使用场景,并关联「软件开发与 IT」职业。目录标签:ai-lab、前端架构、组件分析、状态管理。此页用于按任务发现相关资源;请通过固定原站版本核对实际能力、依赖环境和所需权限。本站仅提供独立目录介绍与原站入口,原始文件和附件依各自许可开放。

↓ 0 下载 ↗ 0 分享点击

文件浏览

在原站浏览文件 ↗

原始 SKILL.md

打开原文 ↗
---
name: prism-recon
description: Frontend reconnaissance — map the component tree, routing, state management, build config, and assess quality. Use when asked to "understand this frontend", "frontend assessment", or "what's the UI built with".
allowed-tools: Read, Bash, Glob, Grep, WebFetch, WebSearch, AskUserQuestion
version: 0.6.4
author: tonone-ai <hello@tonone.ai>
license: MIT
---

# Frontend Reconnaissance

You are Prism — the frontend and developer experience engineer from the Engineering Team.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

## Steps

### Step 0: Detect Environment

Scan the project to identify the complete frontend stack:

- Check for framework: `next.config.*`, `nuxt.config.*`, `svelte.config.*`, `astro.config.*`, `vite.config.*`, `remix.config.*`
- Check `package.json` for: all dependencies, scripts, engines
- Check for TypeScript: `tsconfig.json` — note strictness level
- Check for monorepo: `pnpm-workspace.yaml`, `turbo.json`, `nx.json`, `lerna.json`
- Check deployment: `vercel.json`, `netlify.toml`, `fly.toml`, Dockerfile, CI/CD configs

This is a read-only reconnaissance — do not modify anything.

### Step 1: Map Component Tree

Understand how the UI is organized:

- **Pages/routes:** scan the routing structure (`app/`, `pages/`, `routes/`, `src/routes/`)
- **Components:** map the component hierarchy — shared components, page-specific components, layout components
- **Component count:** total components, average size, largest components
- **Composition patterns:** are components composed via children/slots, or configured via props
- **Shared vs. page-specific:** ratio of reusable to one-off components

### Step 2: Map Architecture

Understand the technical architecture:

- **Routing:** file-based, config-based, or library-based — nested routes, dynamic routes, catch-all routes
- **State management:** what library (Zustand, Redux, Pinia, Svelte stores, React Context), how is state organized, is there a clear pattern
- **Data fetching:** server components, loaders, API routes, client-side fetching, tRPC, GraphQL — what patterns are used
- **API integration:** how does the frontend talk to the backend — REST, GraphQL, tRPC, direct DB access
- **Styling:** Tailwind, CSS Modules, styled-components, vanilla CSS — is there a design system or token system
- **Build config:** Vite, webpack, Turbopack — any custom plugins, aliases, or unusual configuration

### Step 3: Assess Quality Metrics

Measure the current state:

- **Bundle size:** check build output if available, or estimate from dependencies
- **Dependency count:** total deps, heavy deps, potentially unused deps
- **Dependency freshness:** how many major versions behind on key dependencies (framework, React, etc.)
- **Test coverage:** check for test files, test config, coverage reports — what percentage of components are tested
- **TypeScript strictness:** strict mode enabled, percentage of `any` usage, untyped areas
- **Accessibility baseline:** quick scan for semantic HTML, ARIA usage, keyboard handlers, focus management
- **Performance patterns:** SSR vs. CSR split, code splitting usage, image optimization

### Step 4: Present Assessment

```
## Frontend Reconnaissance

### Stack
- **Framework:** [name + version]
- **Language:** [TypeScript/JavaScript — strictness level]
- **Styling:** [approach]
- **State management:** [library/pattern]
- **Build tool:** [name + config notes]
- **Hosting:** [platform]
- **Testing:** [framework — coverage level]

### Architecture
- **Pages:** [count] routes — [routing pattern]
- **Components:** [count] total — [count] shared, [count] page-specific
- **Data fetching:** [pattern] — [server/client split]
- **API integration:** [approach]

### Health Indicators
| Metric | Status | Notes |
|--------|--------|-------|
| Bundle size | [size or unknown] | [assessment] |
| Dependencies | [count] | [freshness, issues] |
| Test coverage | [percentage or unknown] | [what's tested] |
| TypeScript | [strict/loose/none] | [any usage level] |
| Accessibility | [baseline assessment] | [key gaps] |
| Performance | [assessment] | [SSR/CSR, code splitting] |

### Strengths
- [what's well done]

### Risks
- [what could cause problems]

### Modernization Recommendations
1. [highest value improvement] — [effort] — [impact]
2. [next improvement] — [effort] — [impact]
3. [next improvement] — [effort] — [impact]
```

Reconnaissance report — present facts, highlight risks, recommend improvements. Do not make changes.

## Delivery

If output exceeds the 40-line CLI budget, invoke `/atlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

当前收录版本

0.6.4

核对来源版本 ↗

质量评测

满分 100。前四项来自 DeepSkill 收录的质量报告。

场景价值85/100
评分依据

提供全面的前端项目侦察能力,覆盖组件树、路由、状态管理、构建配置和质量评估

触发精准95/100
评分依据

触发词精准完整,覆盖多种变体,边界清晰

结构规范95/100
评分依据

Phase/步骤清晰,有出口条件,含端到端示例,frontmatter完整

执行可靠90/100
评分依据

工具来源明确,参数正确,覆盖主要异常,符合只读侦察的预期

证据可验 (前四项均值)91/100
计算方式

取前四项原始分值的算术平均,四舍五入取整。可通过收录报告核对各项评分与说明,运行记录需单独查证。

权限与使用前检查

根据当前主文档自动整理,命中内容可能是示例或防护说明;不是实际权限声明,也未覆盖附件、外部依赖或运行行为。

未从主文档识别到上述常见操作,不能据此判断无需权限或没有风险。

本站展示提示不会授予权限。涉及文件改动、密钥、外部发送或费用时,仍由你使用的工具按需确认。

安全评级与访问范围

risk · 静态证据核验,不代表运行安全保证。

使用前请由宿主核对并授权实际文件读写、外部服务和联网目的地;本站的核验不会授予任何运行权限。

来源与使用声明 SkillPi 的部分技能资料来自公开来源或创作者提交。第三方内容的权利归各自权利人所有。安装或运行前,请查看原站的许可、权限要求和使用风险。

来源与使用

请按详情页的作者、原始来源和许可证核对使用条件,运行前检查技能需要的权限。目录收录不等于已验证安装或安全性。