claude

product

产品/商业/技术/设计分析工具集:product-teardown(Principal-PM 级产品拆解,Product / Business / Technology / Strategy 四层框架,Core Loop 为权重最高的一节,双语 EN+ZH 可打印 HTML 报告)、competitor-landscape(竞品二维定位矩阵)、ai-architecture-review(AI/Agent 产品的技术架构深挖:Model / Tool / Memory / Planning / Agent / Workflow / Evaluation)、copy-ui-style(从截图/URL/代码仓库逆向提取 UI 设计系统,产出 DESIGN.md + AGENTS.md + tokens.json/css + style-dna.json,带校验与 WCAG 对比度检查)、requirement-review(按风险分级的会话级需求评审,检查旧业务影响、安全、兼容性并输出版本化 brief/handoff)、plan-explainer(按风险解释 plan,支持用户复述或知情委托后交给执行流程)。

0 on GitHubby kaelv0.5.0MITupdated 1 month agoproduct
/

Plugin product from marketplace manji in kaelinda/agent-marketplace. Commands read from the repo's manifest — 26 days ago.

What it installs

Skills (6)

  • ai-architecture-review

    Use when the user wants a standalone, deep technical analysis of an AI-native or AI-augmented product's actual AI/agent architecture — not the UI-level 'has an AI feature' read, but Model / Tool / Memory / Planning / Agent / Workflow / Evaluation. Triggers: AI 架构分析, agent 架构, how does X's AI actuall

  • competitor-landscape

    Use when the user wants a standalone, deep competitive analysis of a product against its rivals — not a full product teardown, just the positioning question: where does it sit vs. 3-6 named competitors, on which axes, and where is the gap closing. Produces a dimension-by-dimension matrix plus an exp

  • copy-ui-style

    Use when the user wants to extract, copy, or reverse-engineer a product's UI style / visual design system from screenshots, a URL, or a code repo — and turn it into reusable design tokens plus coding rules an AI agent will actually follow. Produces a ui-style/ bundle: DESIGN.md, AGENTS.md, component

  • plan-explainer

    Use before executing a new or pre-existing implementation plan, including requests to execute this plan now, when the user needs a plain-language walkthrough, plan review, or confirmation of unfamiliar steps. Triggers: 解释 plan, 讲解计划, 计划评审, 我看不懂这个方案, 执行前确认, 逐步说明, execute this plan, or plan explanatio

  • product-teardown

    Use when the user asks to 'teardown', 'break down', 'reverse-engineer', or do a deep PM/strategy analysis of any product (Linear, Notion, Cursor, a competitor, an internal product, ...). Reverse-engineers the product across four layers — Product, Business, Technology, Strategy — through a fixed, MEC

  • requirement-review

    Use before planning or implementing a material feature, business/process change, refactor, integration, or feasibility decision. Triggers: 需求评审, 需求分析, 方案评估, 可行性, 影响范围, compatibility review, security impact, product alternatives, best-practice research, or requests to just write code, implement now,

View source on GitHub

More from kaelinda/agent-marketplace

All 11 plugins →

memory

claude

跨会话长期记忆工具集 — 5 个核心 skill (recall/capture/commit/doctor/admin),支持 OpenViking / MCP / mem0 三后端,identity 默认 fail-closed。

6 skills · 3 commands

0

内容创作与发布工具集,覆盖技术公众号全流程:tech-content-writer(技术文章写作,无 AI 味 + 禁用词扫描)、tech-content-audit(发布前五大维度内容审核)、wechat-cover-html(20:9 封面图,HTML + Playwright,代码密集型首选)、wechat-cover-image(封面图 Pillow 备选方案)、md-to-html(Markdown 渲染为可发布 HTML,内置 MDNice 与开源 CSS 双主题引擎)、ali-oss(上传文件到阿里云 OSS,支持多 bucket 与默认 bucket、region 自动探测、预签名链接)、wechat-publisher(将 Markdown/HTML 文章发布到微信公众号草稿箱,多主题排版 + 封面图与正文图片自动上传 + 多账号切换)。

7 skills

0

项目演进记录系统:随代码库流转的演进日志,每条记录回答「从什么变成什么、为什么、谁牵头」。evolution-log skill 覆盖初始化 / 记录 / 查询 / 草稿确认四条工作流;Stop hook 在每轮结束前做规则快筛,命中后把「先自评是否真为方案级变更」的指令回注给会话内模型完成二级判定(opt-in、fail-open、单会话至多一次、零外发);记录以结构化 Markdown 存进 Git,records/ 是唯一事实来源,INDEX.md 与 records.json 可随时全量重建。

1 skill · hooks

0

agents

claude

外部 AI Agent 调度工具集(Cursor / Codex 等),目前包含 cursor-cli 子 skill。

1 skill

0

core

claude

manji 市场核心功能:版本检测、自动更新、频率控制

1 skill

0

design

claude

设计工具集:apple-icon-studio(Apple 级 App 图标设计工作流 —— 品牌内核 → 隐喻生成(生成 10 个 / 淘汰 7 个)→ 形态 → 材质 → 构图 → 色彩 → 对抗式评审(11 条否决 + 6 维加权评分,低于 85 不发)→ 出图 Prompt → Icon Composer 参数 → 2026 时效校验;含 10 个行业 Icon DNA 知识库、5 个完整拆解案例、双语可打印 HTML 简报,以及从 1024 母版一键生成 iOS/macOS/Web 图标集的脚本)。

1 skill

0

Similar plugins

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

pake

claudecodex

Package any website or local web build into a lightweight desktop app with Pake CLI.

1 skill

tw93/Pake 63,463

Maintain product?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins11 plugins