Rabbit-Ivan/Ivan-skills

agents

Ivan Skills 仓库级入口说明与维护规范

Source text: Chinese

clean-code-reviewer

Produces a severity-rated (高/中/低) Clean Code findings report across 7 dimensions (naming, function size/SRP, duplication/DRY, over-engineering/YAGNI, magic numbers, structural clarity, project conventions), each with a location and a behavior-preserving…

create-visual-card

Generate a magazine-quality visual card as a single self-contained HTML file (embedded CSS, Swiss-grid + bold-type design system), then screenshot it to a shareable PNG and hand back both files. Use this whenever the user wants content turned into a visually…

entity-model-auditor

Audit and design entity data models into a field-by-field markdown report: a target-vs-current audit table per entity, a classification of every field (table column / config blob / runtime-computed / remove), a grouped migration change list, and…

geju

Produces a bold, high-altitude direction judgment (格局判断): a sharp thesis on the right target model, a kill-list of what to delete / merge / split / reframe, a Conservative-vs-Clean-vs-Staged options table, a verification path (first proof point + falsifier)…

goudi

Pressure-tests an ambitious proposal and returns a grounded landing judgment (go / shrink / pause / reject / validate-first) with one minimum-viable first move, an explicit cut list, success/failure signals, and a stop rule. Use whenever a discussion has more…

hai-architecture

Produce an evidence-grounded architecture review or design-decision critique — an architecture map, the painful complexity center, 3-6 chosen review lenses, ranked findings with file:line evidence, why-not alternatives, and a red/blue adversarial check —…

hai-ast-grep

Produces a ready-to-run ast-grep pattern or YAML rule that structurally searches, lints, or auto-rewrites code via tree-sitter AST matching, validated against positive + negative fixtures. Trigger on ast-grep, sg scan, sgconfig, tree-sitter, AST matching,…

hai-audit-docs-against-code

Audits documentation against the actual code, config, schemas, and API contracts and produces a severity-ranked (P0-P3 + needs-evidence) report of every stale or mismatched claim, each with a doc location, a code/contract reference, the impact, and a minimal…

hai-audit-docs-internally

Audits a document or doc set from the inside and produces a prioritized findings report (P0-P3) of internal conflicts, stale content, terminology drift, duplication, and misplaced or unsupported claims, plus update/move/merge/remove/split decisions and a…

hai-goal

Produces a written goal document before execution starts — a verifiable target, boundary, current state, phased route, per-phase rules, todos with proof, a dry-run, and a Go / No-Go judgment — instead of coding while watching to see if it works. Use whenever…

hai-idea

Evaluates whether an idea deserves attention and returns a clear verdict — Do / Validate first / Reframe / Defer / Kill — with a dimension-by-dimension scorecard, the strongest objection, a stronger reframe, and the cheapest validation test. Use whenever the…

hai-naming

Produces 3-5 candidate names with one recommended final name, the three-stage reasoning trail behind it (research-stage / top-of-head / final-after-reading), and — for reviews — a priority-ordered rename list with old->new and migration scope. Use when the…

hai-prd

Produces a PRD recommendation, draft, or document-level diagnosis: decides whether a PRD is even needed (vs a goal, design doc, or task), drafts one from a product problem, audits/repairs an existing PRD for drift and unverifiable acceptance, or judges…

hai-razor

Audits whether each requirement, workflow step, role, field, state, module, layer, abstraction, or rule deserves to exist and returns a razor verdict: a Keep/Merge/Defer/Delete/Replace/Prove-first classification of every concept, the strongest survival…

hai-rewrite-doc

Verifies a drifted, patched-over document block by block — against the current conclusions, the codebase, and anything else checkable — then rewrites it around the evidence: blocks that survive verification keep their original wording, blocks that fail are…

hai-ssot

Diagnoses single-source-of-truth (SSOT) violations and produces a numbered findings report — file:line evidence, honest adjudication (real violation vs idiomatic false positive), severity, and disposition per finding, plus a treatment-recipe table. Covers ten…

hai-tdd

Drives implementation through a strict red-green-refactor loop and produces a filled-in test-evidence report (target behavior, the failing RED test + why it failed for the right reason, the minimal GREEN implementation, the refactor decision, and verification…

hai-visual-report

Generates a complete, self-contained multi-section HTML report — header + one-line verdict, Mermaid structure map, decision matrix, risk/proof table, and next-move block — from an idea, requirement, PRD, goal, review, architecture topic, plan, or proposal,…

react-component-diagnosis

Produces a structured diagnosis report on one React component's design: a 7-dimension scorecard (consumer API, data flow, testability, extensibility, performance, mental model, boundaries & contracts — each scored 1-5 with code evidence), design highlights,…

readme-beautifier

Produces a restructured, consistently formatted, professional-looking README (or similar markdown project doc such as CONTRIBUTING.md, docs/index.md, 项目说明.md) plus a short change summary — content untouched: nothing added, nothing removed, only structure and…

goalpro

当用户要写出高质量 goal 提示词，把模糊、战略性、多步骤、证据不足或容易跑偏的请求整理成可执行、可验证、可暂停的 Goal Contract 时使用。适用于写 goal、优化任务提示词、明确 done/success criteria、deep research 后定战略、大改前 inventory、修复跑偏计划、为 Codex 或 Claude Code 准备执行任务；默认只生成 goal，不执行 goal。

Source text: Chinese

ai-reimbursement

AI 工具订阅报销材料一键生成。当用户提到报销、续费、订阅费用、采购申请、AI 工具费用报销、生成报销材料等关键词时触发。即使用户只说"帮我报销 ChatGPT"或"Claude 续费 200 刀"或"Cursor 要到期了帮我生成报销单"，也应触发此 skill。覆盖 ChatGPT、Claude、Cursor、Lovart、Copilot 等 AI 工具订阅费用的报销材料自动生成，包括审批文案和暗黑玻璃态 HTML 可视化信息图。

Source text: Chinese

cli-upgrade

通用版本升级对比助手。用于查询任意 CLI 或 App 的最新稳定版本，并与前 3 个稳定版本做更新对比，输出小白可读的大白话总结。适用于用户提到版本升级、release notes、changelog、更新亮点、对比前几个版本等场景；当数据源不明确时，要求用户补充官网或 GitHub 仓库 URL。

Source text: Chinese

flowus-to-feishu

将 FlowUs 文章迁移到飞书云文档/知识库。当用户提供 FlowUs 链接并要求迁移到飞书时使用。 也适用于用户提到 FlowUs 迁移、FlowUs 转飞书、文章搬运到飞书、FlowUs 文档导入飞书等场景。 即使用户只说“帮我把这篇 FlowUs 迁移过来”，也应触发此 skill。

Source text: Chinese

vps-build

VPS 面板自动化安装与管理工具。通过 SSH 远程连接用户的 VPS，自动完成面板安装（3X-UI、S-UI）、SSL 证书配置、系统加固（BBR/UFW/Fail2ban）等全套流程。当用户提到 VPS 搭建、面板安装、3X-UI、S-UI、重装面板、VPS 初始化、节点搭建等关键词时触发。即使用户只是说"帮我装个面板"或"新买了台 VPS"，也应该触发此 skill。

Source text: Chinese

n8n-gen

Generate n8n workflows by researching official templates. This skill: (1) Searches and downloads reference workflows from n8n.io using Playwright, (2) Designs a new custom workflow based on 'n8n AI Agent' guidelines, (3) Generates the final JSON file, and (4)…

static-residential-ip-assessor

用于判定单个 IP 或 IP 段是否属于静态家宽住宅，并输出带证据链、冲突分析与置信度评分的风险报告。用户提供 IP，或提供 ASN、Hostname、Range 三元信息时使用；适用于账号风控前审、代理池质量筛查、住宅 IP 真实性核验、报告复核与复查场景。

Source text: Chinese

benzenith-frontend-design

BenZenith 品牌专用前端设计与UI实现规范。用于生成或优化 BenZenith 官网/落地页/活动页/电商页面/组件（React/Next.js/HTML/CSS/Tailwind 等），或根据设计稿/截图进行高还原实现；要求输出可直接落地的 production-grade 代码与清晰的设计决策，并强制遵循 BenZenith 的品牌调性（东方极简、珠宝级质感、水/墨肌理、黑金与温润中性色体系），避免通用模板化“AI slop”界面。

Source text: Chinese

benzenith-frontend-design2

BenZenith 官网“设计稿范式复刻”专用前端设计 skill。强制遵循 BenZenith 的东方极简 + 珠宝展陈质感 + 水墨结构性视觉 + 黑金点睛；并固化 PC 端尺寸规范、页面模板（首页/系列页/单品页/品牌故事/展览页）、CTA 默认形态（editorial link）、超大品牌签名 footer 等，输出 production-grade 代码（Next.js/React/Tailwind/HTML/CSS）与可执行的设计决策清单，避免通用模板化“AI slop”。

Source text: Chinese

kie-ai-generation

在开发需要调用 Kie.ai（kie.ai）生成视频/图片的 API 服务时使用。本 Skill 提供统一的“创建任务→查询结果/回调”工作流、模型参数对照、后端封装最佳实践（鉴权、重试、轮询、回调验签/防重、解析 resultJson）、以及可直接复制的 curl/TypeScript/Python 示例代码。适用于 Next.js/Node/Flask 等服务端集成。

Source text: Chinese

product-manager

面向产品需求整合与 PRD 产出。当用户提供多份需求文档/口述记录/图片/思维导图/录音转写，需要抽取关键信息并按 PRD 模板生成需求文档时使用。本技能覆盖多格式输入整合、缺口澄清与 PRD 输出。

Source text: Chinese

wechat-article-writer

公众号文章自动化写作流程。支持资料搜索、文章撰写、爆款标题生成、排版优化。当用户提到写公众号、微信文章、自媒体写作、爆款文章、内容创作时使用此 skill。

Source text: Chinese

yt-dlp-downloader

使用 yt-dlp 下载视频。当用户发送视频链接（YouTube、Bilibili、Twitter、抖音等）或请求下载视频时触发。支持单个/批量下载，默认优先 4K（2160p），fallback 到 1080p。支持三种编码模式：H.264（默认，最广泛兼容）、HEVC/H.265（4K 高效编码，文件更小）、原始格式（不转码，保留 webm/mkv 等）。自动嵌入中文字幕（优先中文，英文兜底）。触发词：下载视频、yt-dlp、视频链接、HEVC、H.265。

Source text: Chinese