Daily Featured Skills Count
5,117 5,165 5,205 5,241 5,288 5,316 5,330
05/10 05/11 05/12 05/13 05/14 05/15 05/16
♾️ Free & Open Source 🛡️ Secure & Worry-Free

Import Skills

Composite Most Downloads Most Likes Most Comments Newest
fcakyon fcakyon
from GitHub Tools & Productivity
  • 📁 references/
  • 📁 templates/
  • 📄 SKILL.md
automation data agent-browser

agent-browser

Agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.

⬇0 ❤652 1 month ago · Uploaded Detail →
friday-platform friday-platform
from GitHub Tools & Productivity
  • 📁 references/
  • 📄 SKILL.md
automation data agent-browser

core

Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.

⬇0 ❤79 12 days ago · Uploaded Detail →
applepig applepig
from GitHub Tools & Productivity
  • 📄 SKILL.md
frontend e2e agent-browser

DDD.AgentBrowser

E2E 除錯說明書——用 agent-browser CLI 在 DDD 工作流中系統性地除錯前端問題。 Use when E2E tests fail, when you need to visually verify UI behavior, debug form submissions, inspect page state, or trace frontend issues during "/DDD.work". Also use when the user says "debug E2E", "check the page", "why is the test failing", "open the browser", "take a screenshot", "inspect the DOM", or invokes "/DDD.agent-browser". --- # DDD:AgentBrowser — E2E 除錯說明書 在 DDD 工作流的開發階段（`/DDD.work`），當 Playwright E2E 測試失敗或需要視覺驗證時， 用 `agent-browser` CLI 直接操作瀏覽器來定位問題。 這份說明書不是瀏覽器自動化教學，而是**除錯流程指南**——幫你從「測試掛了」走到「找到根因」。 ## 核心除錯循環 ``` 測試失敗 → 重現場景 → 觀察狀態 → 定位根因 → 修正 → 驗證 ``` 每一步都有對應的 agent-browser 指令，按順序走就對了。 ## Step 1：重現場景 先把瀏覽器帶到測試失敗的那個畫面。 ```bash # 開啟目標頁面

⬇0 ❤6 1 month ago · Uploaded Detail →
hivemoot hivemoot
from GitHub Tools & Productivity
  • 📄 SKILL.md
agent-browser browser automation

web-browse

Drive the shared hivemoot-browser sidecar via agent-browser (vercel-labs). Use for JS-rendered pages, authenticated sessions via bootstrapped cookies, OAuth flows — anything curl / API calls can't handle. --- # Web browse You have a shared headless Chromium sidecar attached over the Chrome DevTools Protocol at `$BROWSER_CDP_URL`. Drive it with the `browser` plugin's CLI — a thin Hermes-style wrapper that injects fleet flags (`--cdp`, `--session-name`, `--state`) and delegates to `agent-browser` for all browser logic. python3 -m hivemoot_agent.plugins_builtin.browser.cli <subcommand> [args] ## When to use | Task | Use this skill? | Cheaper alternative | |---|---|---| | Fetch a JS-rendered SPA's content | ✓ | none — browser is required | | Log into a SaaS with your bootstrapped cookies | ✓ | none | | Fill a multi-step form | ✓ | none | | Read a static HTML page | ✗ | `curl -sL <url>` | | GitHub / Linear / Notion work via API | ✗ | their respective CLIs / APIs | | Scrape anti-bot sites anonymously | ✗ | out of scope; report to operator | **Default to NO.** Every browser call is multi-second and multi-MB. Reach for it only when there's no cheaper path. ## Subcommands (1:1 with agent-browser) ### `navigate <url>` Open a URL. Aliases `open` in agent-browser. python3 .../cli.py navigate https://example.com ✓ Example Domain

⬇0 ❤5 1 month ago · Uploaded Detail →
jikig-ai jikig-ai
from GitHub Tools & Productivity
  • 📄 SKILL.md
data automation agent-browser

agent-browser

This skill should be used when automating browser interactions via Vercel's agent-browser CLI. It handles web page navigation, form filling, screenshots, and data scraping using ref-based element selection.

⬇0 ❤5 1 month ago · Uploaded Detail →

Skill File Structure Sample (Reference)

skill-sample/
├─ SKILL.md              ⭐ Required: skill entry doc (purpose / usage / examples / deps)
├─ manifest.sample.json  ⭐ Recommended: machine-readable metadata (index / validation / autofill)
├─ LICENSE.sample        ⭐ Recommended: license & scope (open source / restriction / commercial)
├─ scripts/
│  └─ example-run.py     ✅ Runnable example script for quick verification
├─ assets/
│  ├─ example-formatting-guide.md  🧩 Output conventions: layout / structure / style
│  └─ example-template.tex         🧩 Templates: quickly generate standardized output
└─ references/           🧩 Knowledge base: methods / guides / best practices
   ├─ example-ref-structure.md     🧩 Structure reference
   ├─ example-ref-analysis.md      🧩 Analysis reference
   └─ example-ref-visuals.md       🧩 Visual reference

More Agent Skills specs Anthropic docs: https://agentskills.io/home

SKILL.md Requirements

├─ ⭐ Required: YAML Frontmatter (must be at top)
│  ├─ ⭐ name                 : unique skill name, follow naming convention
│  └─ ⭐ description          : include trigger keywords for matching
│
├─ ✅ Optional: Frontmatter extension fields
│  ├─ ✅ license              : license identifier
│  ├─ ✅ compatibility        : runtime constraints when needed
│  ├─ ✅ metadata             : key-value fields (author/version/source_url...)
│  └─ 🧩 allowed-tools        : tool whitelist (experimental)
│
└─ ✅ Recommended: Markdown body (progressive disclosure)
   ├─ ✅ Overview / Purpose
   ├─ ✅ When to use
   ├─ ✅ Step-by-step
   ├─ ✅ Inputs / Outputs
   ├─ ✅ Examples
   ├─ 🧩 Files & References
   ├─ 🧩 Edge cases
   ├─ 🧩 Troubleshooting
   └─ 🧩 Safety notes

Why SkillWink?

Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.

We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.

Keyword Search Version Updates Multi-Metric Ranking Open Standard Discussion

Quick Start:

Import/download skills (.zip/.skill), then place locally:

~/.claude/skills/ (Claude Code)

~/.codex/skills/ (Codex CLI)

One SKILL.md can be reused across tools.

FAQ

Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.

1. What are Agent Skills?

A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.

Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.

2. How do Skills work?

Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.

This keeps agents lightweight while preserving enough context for complex tasks.

3. How can I quickly find the right skill?

Use these three together:

  • Semantic search: describe your goal in natural language.
  • Multi-filtering: category/tag/author/language/license.
  • Sort by downloads/likes/comments/updated to find higher-quality skills.

4. Which import methods are supported?

  • Upload archive: .zip / .skill (recommended)
  • Upload skills folder
  • Import from GitHub repository

Note: file size for all methods should be within 10MB.

5. How to use in Claude / Codex?

Typical paths (may vary by local setup):

  • Claude Code：~/.claude/skills/
  • Codex CLI：~/.codex/skills/

One SKILL.md can usually be reused across tools.

6. Can one skill be shared across tools?

Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.

Example: retrieval + writing + automation scripts as one workflow.

7. Are these skills safe to use?

Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.

8. Why does it not work after import?

Most common reasons:

  • Wrong folder path or nested one level too deep
  • Invalid/incomplete SKILL.md fields or format
  • Dependencies missing (Python/Node/CLI)
  • Tool has not reloaded skills yet

9. Does SkillWink include duplicates/low-quality skills?

We try to avoid that. Use ranking + comments to surface better skills:

  • Duplicate skills: compare differences (speed/stability/focus)
  • Low quality skills: regularly cleaned up