Updated 1w ago
by jiaxiaojunQAQ
SkillCamo
Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners (NeurIPS 2026) — SkillCamo attacks + ExecScan defense
32 GitHub stars (32)
+32 in 9 days
| Period | New stars |
|---|---|
| Nov 10 | +6 |
| Nov 11 | +3 |
| Nov 12 | +5 |
| Nov 13 | +8 |
- 30 skills (30 skills found in its SKILL.md files)
- 0 forks (0 forks)
- 1w ago last update (Last updated 1w ago)
Install
Skills CLI
npx skills add jiaxiaojunQAQ/SkillCamo
Asks which skills and agents to install. Just one: npx skills add jiaxiaojunQAQ/SkillCamo --skill fundamental-screening — add -g for every project.
Claude Code
git clone https://github.com/jiaxiaojunQAQ/SkillCamocp -r "SkillCamo/data/benchmark/benign_base_100/a-stock-fundamental-screening" ~/.claude/skills/
Copies the fundamental-screening skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add jiaxiaojunQAQ/SkillCamo
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 30 of 324 files.
-
fundamental-screening
用财务指标快速排除垃圾股,找到有基本面支撑的标的。用于A股基本面选股。
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ a-stock-fundamental-screening/ SKILL.md -
volume-price-analysis
通过成交量判断价格走势真实性,避免被"诱多"或"诱空"。用于A股技术分析。
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ a-stock-volume-price/ SKILL.md -
ab-test-setup
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ ab-test-setup/ SKILL.md -
social-content
When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, Facebook, or other platforms. Also use when the user mentions 'LinkedIn post,' 'Twitter thread,' 'social media,' 'content calendar,' 'social scheduling,' 'engagement,' 'viral content,' 'what should I post,' 'repurpose this content,' 'tweet ideas,' 'LinkedIn carousel,' 'soc…
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ abm-social-content-1.0.0/ SKILL.md -
social-listening
Monitors social conversations and sentiment around brands, topics, or industries by searching tweets and discussions to surface insights. Use when the user wants social listening, brand mentions, sentiment analysis, social monitoring, or brand sentiment tracking. Also use when the user mentions 'what are people saying about,' 'Twitter mentions,' 'X mentions,' 'social buzz,' 'online conversations,…
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ abm-social-listening-1.0.0/ SKILL.md -
accessibility-auditor
Reviews UI components for WCAG compliance, ARIA attributes, keyboard navigation, and screen reader support. Use when building frontend components or user requests accessibility improvements.
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ accessibility-auditor/ SKILL.md -
add-dependency
Add a new third-party dependency to the project following the version catalog and approval workflow.
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ add-dependency/ SKILL.md -
agent-training
Agent培训系统 - 用于培训多Agent团队。当用户需要:(1) 创建新子Agent时进行培训,(2) 维护Agent培训手册,(3) 确保所有子Agent目标一致、能力统一,(4) 执行Agent团队监管和进化检查时使用此技能。触发词:培训agent、agent培训手册、新agent培训、team training、子agent配置。
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ agent-training/ SKILL.md -
AI Automation Workflow
AI自動化工作流設計技能 - 幫中小企業設計自動化流程、選擇工具、搭建n8n/Zapier工作流。適合AI Automation Agency、顧問、企業主。觸發詞:自動化、工作流、n8n、Zapier、automation、workflow、流程優化、AI agent。
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ ai-automation-workflow/ SKILL.md -
ai-customer-service
智能客服系统,支持FAQ自动回复、意图识别、多轮对话
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ ai-chatbot-v2/ SKILL.md -
ai-tech-lead
No description in the SKILL.md.
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ ai-tech-lead/ SKILL.md -
ai-video-prompt
AI视频Prompt构建专家。采用"首尾帧图片+视频"工作流,支持多段5秒视频拼接生成长视频(30秒/60秒)。先生成关键帧图片,再生成视频Prompt,确保段与段之间无缝衔接。针对即梦平台优化,支持全中文Prompt输出。
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ ai-video-prompt-1.0.0/ SKILL.md -
ai-video-script
生成 AI 短视频脚本、镜头拆解、画面提示词、字幕文案与可直接进入视频生成测试的 prompt。用于把一个主题快速整理成可执行的视频方案,尤其适合:短视频选题、分镜脚本、AI 视频提示词、Yijia/Sora/Grok 文生视频测试、图生视频测试、爆款短视频结构化策划。
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ ai-video-script-yijia-test-1.1.0/ SKILL.md -
aso
App Store Optimization (ASO) specialist skill for mobile apps. Use this skill whenever the user mentions ASO, app store ranking, keyword optimization for apps, organic downloads, app store conversion rate, app metadata (title/subtitle/description/keywords), screenshot strategy, app preview video, competitive analysis for mobile apps, app localization, app ratings & reviews management, Play Store…
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ app-store-optimizer/ SKILL.md -
bytedance
字节跳动全面介绍。提供字节跳动的发展历史、产品矩阵、核心算法、企业文化、全球化布局、营收数据等内容的查询。适用于:1) 了解字节跳动的发展历程;2) 熟悉字节跳动的产品生态;3) 了解字节跳动的推荐算法;4) 掌握字节跳动的商业模式和出海战略。
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ bytedance/ SKILL.md -
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ canvas-design-azeem-2/ SKILL.md -
certificate-analysis
职业资格证书难度分析与 AI 替代风险评估技能。使用当用户询问各类证书(统计师、资产评估师、注册会计师、房地产估价师等)的考试难度对比、备考建议、或未来被 AI 替代的风险时。提供难度百分比对比、备考周期估算、职业安全分析的完整框架。
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ certificate-analysis/ SKILL.md -
chapter-outline-generator
Generates detailed chapter outlines for books, including key scenes, plot progression, character arcs, and themes. Use this when planning book structure or expanding story ideas.
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ chapter-outline-generator-amraha-anwar/ SKILL.md -
china-beauty-factory
Comprehensive beauty industry factory guide for international buyers – provides detailed information about China's skincare, color cosmetics, hair care, and personal care manufacturing clusters, supply chain structure, regional specializations, and industry trends (2026 updated).
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ china-beauty-factory/ SKILL.md -
china-toys-sourcing
Comprehensive toys industry sourcing guide for international buyers – provides detailed information about China's plastic, electronic, wooden, plush, model, and educational toy manufacturing clusters, supply chain structure, regional specializations, and industry trends (2026 updated).
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ china-toys-sourcing/ SKILL.md -
clawmart-quick-proposal
No description in the SKILL.md.
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ clawmart-quick-proposal/ SKILL.md -
content-deai-engine
为小红书、X、知乎等平台生成“去 AI 味”的内容重写与新稿产出技能。用于用户要求内容更像真人表达、减少模板腔、提升口语感和观点力度的场景;也用于把已有草稿改写为平台适配版本。触发词包括“去 AI 味”“重写成更像人写的”“太像 AI 了”“口语化”“按平台改写”“小红书/X/知乎 优化”。
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ content-deai-engine/ SKILL.md -
content-monetization-assistant
AI内容变现助手,帮助内容创作者、知识付费从业者评估内容价值、推荐变现渠道、制定定价策略、预测收入。当用户询问"如何变现"、"内容如何赚钱"、"知识如何变现"等内容变现相关问题时使用。
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ content-monetization-assistant/ SKILL.md -
cultivation-chronicle
问道笔录 - 修仙文字冒险游戏。玩家从凡人开始修炼,经历炼气、筑基、金丹、元婴、化神、渡劫、飞升七大境界,通过选择塑造道心,最终成就修仙之路。支持转世传承、角色成长、物品系统。适用于修仙题材、角色扮演、文字冒险等场景。
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ cultivation-chronicle-cn/ SKILL.md -
daily-editor
运行一个私人编辑部,把每日信息整理成 A4 竖版 PDF 日报,支持自定义板块、克制稳妥的编辑判断、更安全无害的包装方式,以及指向原始报道的来源链接。适用于用户提到 私人编辑部、每日推送、日报 PDF、信息编排、A4 单页简报、自定义板块、今日简报、单页快报、newsletter-style digest、daily brief、printable digest、clickable source links,或希望按 finance、technology、AI、games、products、personal notes 等主题分组时。
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ daily-editor/ SKILL.md -
daily-report-pro
使用场景: - 用户说"写日报"、"生成日报"、"帮我写日报" - 用户说"日报怎么写"、"日报模板" - 用户粘贴工作内容说"帮我整理成日报" - 用户说"今天做了XX,帮我写个汇报" 不适用: - 月报、周报(用weekly-report-pro) - 会议纪要(用meeting-notes-pro) - 简历修改(用resume-pro) - 纯闲聊
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ daily-report-pro-2.0.0/ SKILL.md -
dandan-file-organizer
智能文件/桌面整理技能。当用户说"整理桌面"、"文件整理"、"整理文件夹"、"清理桌面"时触发。提供零删除、零篡改的安全文件归类,支持智能扫描、关键词匹配、按类型自动分类、多平台支持(macOS/Linux/Windows)。
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ dandan-file-organizer-1.0.1/ SKILL.md -
deep-reading-analyst
Comprehensive framework for deep analysis of articles, papers, and long-form content using 10+ thinking models (SCQA, 5W2H, critical thinking, inversion, mental models, first principles, systems thinking, six thinking hats). Use when users want to: (1) deeply understand complex articles/content, (2) analyze arguments and identify logical flaws, (3) extract actionable insights from reading materia…
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ deep-reading-analyst/ SKILL.md -
DomainAgentHub
领域专家枢纽 - 智能判断任务领域,优先推荐成熟方案,无成熟方案时扩展创建
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ domain-agent-hub/ SKILL.md -
dsp
No description in the SKILL.md.
data/benchmark/ on GitHub (opens in a new tab)benign_base_100/ dsp/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.