AI Dev Impact Lab JA
← Rankings · AI-RELATED REPO

wan-huiyan/skill-portfolio-existence-review

Existence/strategy audit for a portfolio of published Claude Code skills/repos — should each exist at all? Per-artifact KEEP/CONSOLIDATE/KILL/PIVOT verdicts with web-verified differentiation.

JavaScript MIT GitHub ↗
★ 0
stars
70
AI relevance
50
solo dev
0
tool sigs

SUMMARY AI summary by gpt-5-mini

A tool to answer one question other audits skip: should each published Claude Code skill, plugin bundle, or adjacent repo exist at all. Intended for maintainers, authors, and portfolio/product owners who need strategic decisions across multiple published artifacts. Key features: - Per-artifact verdicts: KEEP / CONSOLIDATE / KILL / PIVOT. - Concrete "Recommended Fix" for non-KEEP items: ordered steps, executor, blast radius, effort estimate, and verification checks. - Multi-agent adversarial review panel (Product Strategist, Devil’s Advocate, Competitive Analyst, etc.) built on agent-review-panel. - Web-verified competitive differentiation and reconciliation of published vs local state. - Consolidation sequencing across a portfolio and preserved dissent; read-only recommendations (no auto-deletes). - Notes limitations: judgment-based, model-shared blind spots, freshness of web checks, and higher runtime cost. Installation via Claude plugin or git clone.

DETECTED Detected AI stack

AI-related keywords found in this repo's description, topics, or README summary — grouped by category. Each badge links to the corresponding ranking detail page.

🤖 LLM models (1)
Claude

GitHub Topics

#claude-code #claude-code-skill #adversarial-panel #existence-review #redundancy-audit #skill-portfolio

Language breakdown (by bytes)

JavaScript
100%

Owner

Account
wan-huiyan
Type
User
Followers
7
Company
@MightyHive

Dates

Created on GitHub 2026-06-01
Last push 2026-06-01
First seen here 2026-06-01
Last fetched 2026-06-01 16:10

Similar repos (same language)

yinsang0910-star/collab-cli

Universal collaboration protocol + CLI for multi-agent LLM teams — Claude Code, Reasonix, Codex, WorkBuddy, Cursor

JavaScript 3 AI 70
littlejin7/AIMON1

AI 코딩 학습툴

JavaScript 2 AI 55
luguan1998/loguanzhong

一个精神分裂但代码靠谱的 Claude Code 输出风格。AI 随机附体诸葛亮、关羽、董卓,审代码时是谋臣,改 bug 时是武将。

JavaScript 2 AI 45
TheTianQiong/OCS_AI_API

基于 OCS 题库配置规范开发的本地 HTTP 服务,支持接入 OpenAI、Claude、Gemini、DeepSeek 等主流 AI API 进行解题。注意:该项目由AI开发,仅供学习,请勿进行任何商业行为!

JavaScript 1 AI 65
guorunjie/agentic-workflow-guard

Static analysis for AI automation workflows. Find prompt-injection paths, overpowered tools, and write-capable agent jobs before they run.

JavaScript 1 AI 70
CodesEasy/codexgrill

Let Codex review and validate your Claude Code actions

JavaScript 1 AI 45
toge-lang/Calcul

Calcul is a simple programming language made for familliarizing myself with programming language making all alone instead of just relying on claude for "whats the next part?". As the name implies, its used for calculating stuff

JavaScript 1 AI 45
ajayjoy-1/crud-ai-app

A production-ready, full-stack web application that combines traditional data management (CRUD) with advanced Artificial Intelligence. This project features a React frontend, a Django REST Framework backend, and a seamless integration with Google's cutting-edge Gemini 2.5 Flash Large Language Model.

JavaScript 1 AI 65