Agent Skills Overview
skill.md Source★ 5,795 DiscordAI Models & Agents / Agent Tools & MCP Servers
- Monthly visits
- 8.7K
- Down58.8%MoMOct 2026
- Public revenue
- Undisclosed
- No public revenue evidence yet
- Entry price
- Free
- No monthly subscription pricing
- Launched
- 10mo ago
- 2026-01-31 · Est.
Traffic
Marketing moves
Launches, search & content, referrals, promotions- 如此明显ai的图,要不说明本意就是坏的,要不说明技术就不行,还好意思当ai营销号? 引用帖 @blackmelooo: 真是有钱人一顿饭,够我们普通老百姓存几十年。
@exoticknightd · 2026-11-08 · 0 likes · 0 reposts · 28 views
- AI 一句话就能出结果,真要一起把项目做下去,还得在实践里磨合。 我把这段时间的摸索整理成了 RED:让 AI 持续理解项目,参与需求探索、方案调整、实现和后续维护。方法和工具都开源了。 GitHub:https://github.com/exoticknight/red 方法介绍(文章):https://blog.e10t.net/red/
@exoticknightd · 2026-09-13 · 4 likes · 0 reposts · 100 views
- 我把 Labnana OpenAPI 接进了 3 个工具 🍌 支持 Nano Banana、GPT-Image-2、Seedream 等模型。 • DeepSeek Harness:对话生图/改图 • MCP:Claude Code/Cursor • ComfyUI:参考图编辑/4K https://github.com/exoticknight/dsh-labnana https://github.com/exoticknight/labnana-mcp https://
@exoticknightd · 2026-08-29 · 0 likes · 0 reposts · 207 views
Launched on V2EX (3 comments)Launch
国庆没怎么休息,折腾出了小红书 30 天 1206 万曝光,顺手开源了一套 AI 视频 Skills — 国庆几天基本没怎么休息,一直在折腾 Codex 、Claude Code 和 AI 视频制作。 没想到折腾出了点意外收获: 小红书近 30 天曝光 1206 万,播放 275 万,国庆这几天涨粉大概 2000 。 数据截图放下面,省得被说吹牛。 先说结论: AI 确实把个人做…
Oct 8 · 40d agoLaunch page
At the time: 21K visits/moVisits: prior 1 mo +10%, next 1 mo -59%3 concurrent movesLaunched on V2EX (2 comments)Launch
做了一个可以在浏览器开展你所有工作的 AI 助手,推送,搭建, AI,写作,自动化流程,推送 — Thresh AI 的本地引擎:把浏览器变成 AI 的工作台。在浏览器侧边栏里与 AI 对话,AI 能真正操作你的浏览器(点击、填表、抓取)、读写本地文件、跑终端命令、执行自动化流程——数据全部留在本机。 它能做什么 你现在用浏览器的方式: 复制粘贴、手动点、手动记。 装上之…
Sep 20 · 58d agoLaunch page
At the time: 19.1K visits/moVisits: next 2 mo -55%3 concurrent movesLaunched on V2EXLaunch
RED 实战:用 AI 把一个想法做成能用的 DSH 插件 — 上一篇 V2EX 帖子: 这次接着上一篇的方法介绍,直接看它怎样参与一次真实的插件开发:从一个说不清的使用问题开始,让 AI 先研究并做 demo ,看到效果后再进入 E ,最后把确认过的行为整理进 D 。这次不再只讲方法,直接看两轮开发怎样展开。 最近 DSH ( Deep…
Sep 17 · 2mo agoLaunch page
At the time: 19.1K visits/moVisits: next 2 mo -55%3 concurrent movesLaunched on V2EX (8 comments)Launch
[开源] 让 Agent 真正「看懂」视频: Gemini 主动视频理解 MCP + Skill,附 FFmpeg 抽帧实测对比 — 9 月初 Google 发了篇博客介绍 agentic video understanding:视频理解不再是「按固定帧率抽帧 → 全部塞进上下文」,核心思路是淘汰以前用平均地抽帧来理解视频,而是让 agent 自己去决定看哪一帧。 我照着这个思路做了个开源项目 gemini…
Sep 15 · 2mo agoLaunch page
At the time: 19.1K visits/moVisits: next 2 mo -55%3 concurrent movesLaunched on V2EXLaunch
🧠 如何让你的所有 AI Agent 共享同一个记忆?—— 一个开源方案 — 你有没有遇到这种情况: 在 ChatGPT 里问过的那个人的生日,换到 Claude Code 写代码时又得重新说一遍。Cursor 里收藏了一篇好文章,回到 Kun 里完全想不起来。你的知识跟着工具走,不是跟着你走。 每个 Agent 都有自己的"记忆孤岛"。 为什么会出现…
Jul 21 · 4mo agoLaunch page
Third-party reviews & case dossiers
Acquisition breakdowns, engineer reviews & open-source metricsOpen Source & Agent Ecosystem
- GitHub Stars
- ★ 5,795
- Forks
- 355
- License
- See repository
- Primary language
- Docker / Self-hosted
- Exposed tool capabilities:
- Agent SkillsDomain expertiseRepeatable workflowsCross-product reuseDiscoveryActivation
Traffic sources
Traffic breakdown
No traffic channel or country breakdown data for this website yet.
Search
Domain authority —Domain registered Unknown
No search keyword data for this website yet.
Traffic data: Vaneform
Pricing
Pricing page not identified yet, or no public pricing listed.
Pages & changes
Key pages
Weekly snapshotsChanges
No pricing, plan, or positioning changes detected since tracking started.
Design
Minimal Monochrome (Light canvas, balanced density) featuring centered headline + cta layout and code block / terminal / cli visuals.
First-screen preview · click to zoom
First-screen pitch & conversion flow
“Agent Skills Overview”
Centered Headline + CTA hero structure paired with direct input / instant try CTA and no explicit trust bar.
Conversion path: Centered Headline + CTA + Code Block / Terminal / CLI → Direct Input / Instant Try
- Category Positioning Anchor
- Code & Terminal
Palette · click to copy
- Typography
- 8.0
- Color & Contrast
- 7.0
- Layout & Spacing
- 8.0
- Craft & Polish
- 8.0
- Distinctiveness
- 6.0
Structure
- Fonts
- Inter / Paper Mono
- Hero layout
- Centered Headline + CTA
- Primary visual
- Code Block / Terminal / CLI
- Conversion CTA
- Direct Input / Instant Try
- Social proof
- No Explicit Trust Bar
- Navigation
- Full-Width Top Bar
- Theme & density
- Light · Balanced
- Corners & depth
- Medium Radius · Hairline borders
Preview full AI design brief (includes :root CSS variables & layout rules)Style tokens only; never copy brand names, logos, copy, or images
# Design Brief: Minimal Monochrome
Monochrome palette with a single accent color, hairline dividers, and generous whitespace.
## Design Tokens
```css
:root {
--background: #ffffff;
--surface: #f3f3f3;
--foreground: #000000;
--muted-foreground: #1a1a1a;
--accent: #7f7f7f;
--radius: 8px;
--font-heading: "Inter", ui-sans-serif, system-ui, sans-serif;
--font-body: "Inter", ui-sans-serif, system-ui, sans-serif;
--font-mono: "Paper Mono", ui-monospace, monospace;
}
```
Color area ratio: Background #FFFFFF (~74%) · Surface #F3F3F3 (~15%) · Text #000000 (~6%) · Muted Text #1A1A1A (~3%) · Accent #7F7F7F (~2%). Background and surface dominate the canvas; reserve the accent color for primary buttons and active states.
## Layout & Conversion Structure
- Hero layout: Centered Headline + CTA
- Navigation: Full-Width Top Bar
- Theme & density: Light · Balanced
- Border radius & elevation: Medium Radius; no drop shadows—separate layers with hairline borders and whitespace
- Primary visual medium: Code Block / Terminal / CLI
- Conversion CTA: Direct Input / Instant Try
- Headline hook: Category Positioning Anchor
- Hero components: Code & Terminal
- Spatial layout notes: Centered Headline + CTA hero structure paired with direct input / instant try CTA and no explicit trust bar.
- Visual summary: Minimal Monochrome (Light canvas, balanced density) featuring centered headline + cta layout and code block / terminal / cli visuals.
## Avoid
- Multi-stop neon gradients
- Heavy drop shadows
- More than one competing accent color
Implement the UI following the design tokens and layout specifications above: use only these color variables, and reserve the accent color strictly for primary actions and active states. Adopt only this visual style—never copy any reference product’s brand name, logo, copy, or imagery.
Questions & evidence
- How much website traffic does Agent Skills get?
- Vaneform estimates 8.7K website visits in 2026-10. Visits can include repeat visits; this estimate measures web traffic separately from paying customers or revenue.Source
- What is Agent Skills and what platforms does it support?
- Agent Skills is catalogued under Agent Tools & MCP Servers: Agent Skills Overview. Supported platforms: Web.
- Is Agent Skills open source?
- Agent Skills has a public repository (https://github.com/openai/skills) with its source repository published, recording 5,795 GitHub stars, and supporting self-hosted deployment.Source
Related products in this category
These products share a catalog category. Compare customer tasks, features and deployment requirements before treating them as alternatives.
| Product | Entry price | Visits | Revenue |
|---|---|---|---|
| ComposioMatureGive your AI secure access to 1,500+ apps in minutes | $29/mo | 2.8M | Undisclosed |
| REAMatureFind out how software works. | — | 2.3M | Undisclosed |
| Desktop CommanderMatureUse your computerfrom chat | $20/mo | 1.5M | Undisclosed |
| Browser UseMatureBrowser agents and cloud browsers. | — | 1.2M | Undisclosed |
| TinyFishMatureThe web stackfor AI agents. | — | 1.1M | Undisclosed |
| CapafyMatureDomain Expert AI Agent Store | — | 796.8K | >$289K/30dClaimed |