Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Web & browsing
2,453 results · page 63 of 82
- View details
brand-kitSkillWeb & browsing
Extract visual identity from screenshots (primary) or website URL (fallback) and compile into a DESIGN.md-format brand kit — YAML token frontmatter (colors, typography, rounded, spacing, components) + 8 ordered prose sections. The YAML tokens are machine-authoritative; downstream visual skills consu
Ready to connect★ 58
- View details
dev-commandSkillWeb & browsing
Interact with the running VSCode extension via Playwright. Use when automating, testing, or debugging the OpenCode webview UI.
Ready to connect★ 58
- View details
funnel-strategySkillWeb & browsing
Maps your company's GTM motion (PLG, SLG, or Hybrid) to concrete funnel stages with inputs, outputs, and qualification criteria per stage. Detects motion type from website + Exa research, then produces pre-close + post-close stage definitions, the FETE mapping (Fit / Engagement / Tier / Eligibility)
Ready to connect★ 58
- View details
niche-signal-discoverySkillWeb & browsing
Discover niche first-party signals that differentiate Closed Won vs Closed Lost accounts for ICP analysis. Use when the user provides won/lost customer domain lists and wants differential signals (website content, job listings, tech stack, maturity markers) to build account scoring models and prospe
Ready to connect★ 58
- View details
printing-templatesSkillWeb & browsing
Build print formats, email templates, and web page templates using Jinja. Generate PDFs and configure letter heads. Use when creating custom print layouts, email templates, or any Jinja-based rendering in Frappe.
Ready to connect★ 58
- View details
review-frontendSkillWeb & browsing
Use when reviewing, debugging, or improving frontend code in this repo (website/ HTML, CSS, JS, service workers, PWA assets) or when asked to "review frontend", "revisa el html/css", "review JS", or "audita el frontend". Reviews for correctness, browser compatibility, accessibility, performance, sec
Ready to connect★ 58
- View details
review-goSkillWeb & browsing
Use when reviewing, debugging, or giving feedback on Go code in this repo (exercises/part2, website/tools, or any *.go file) or when asked for a "code review", "review this Go", "revisa este código Go", or "crítica de código". Reviews for correctness, idiomatic Go, error handling, resource cleanup,
Ready to connect★ 58
- View details
review-shellSkillWeb & browsing
Use when reviewing, debugging, or hardening Shell/Bash scripts in this repo (.github/workflows/*.yml steps, website build scripts, or any *.sh file) or when asked to "review bash", "revisa el script", "shellcheck", or "revisa el pipeline shell". Reviews for robustness, error handling, quoting, porta
Ready to connect★ 58
- View details
tov-guidelinesSkillWeb & browsing
Extract voice patterns from existing content (website, blog, social, sales-call transcripts) and codify into voice rules. Produces voice analysis + voice guidelines (rules per pattern + violation pattern + fix template). Writes to marketing/brand/brand-voice.md as the canonical voice rules every con
Ready to connect★ 58
- View details
Web AccessSkillWeb & browsing
All networked operations must be handled through this skill, including: search, web scraping, post-login operations, and web interactions. Trigger scenarios: the user asks to search for information, view web page content, access sites requiring login, operate web interfaces, scrape social media cont
Ready to connect★ 58
- View details
Web Content ExtractionSkillWeb & browsing
Extracts main body content from web pages. Supports a three-level fallback strategy: Jina Reader / Scrapling+html2text / web_fetch, automatically returning clean Markdown-formatted body text while preserving headings, links, image URLs, and list structure. Can read WeChat Official Account articles (
Ready to connect★ 58
- View details
browser-harness-authoringSkillWeb & browsing
Use when mapping a repeatable website workflow into a verified Hermes skill so later runs can follow known steps instead of rediscovering the site. Surveys browser compatibility, semantic targets, failure modes, recovery paths, decision gates, and expiry using dummy data and no irreversible submissi
Ready to connect★ 57
- View details
cross-browser-typography-qaSkillWeb & browsing
cross-browser-typography-qa — Diagnose and verify web typography rendering defects across Chromium, WebKit, and native Safari, including clipped glyphs, broken descenders, wrapping, font metrics, gradient text, and live-cache mismatches.
Ready to connect★ 57
- View details
detecting-indirect-prompt-injectionSkillWeb & browsing
Detect and defend against prompt injection hidden in documents, web pages, and images consumed by an agent.
Ready to connect★ 57
- View details
extracting-browser-history-artifactsSkillWeb & browsing
Extract and analyze browser history, cookies, cache, downloads, and bookmarks
Ready to connect★ 57
- View details
meta-business-postingSkillWeb & browsing
meta-business-posting — Publish posts to a Facebook Page through the agent's own logged-in browser session or the Meta Graph API. Account-agnostic; no credentials in the skill.
Ready to connect★ 57
- View details
site-mappingSkillWeb & browsing
site-mapping — Map out a website's full structure — sitemaps, navigation, URL taxonomy, content inventory.
Ready to connect★ 57
- View details
analyzing-browser-forensics-with-hindsightSkillWeb & browsing
Analyze Chromium-based browser artifacts using Hindsight to extract browsing
Ready to connect★ 56
- View details
open-model-workbenchSkillWeb & browsing
Open a ready-to-use local 3D model composition workbench for GLB or GLTF files. Use when the user says "打开模型工作台", asks to place, rotate, scale, arrange, or frame one or more 3D models, or needs a clean composition screenshot before website or Image 2 design. If the user has not supplied a model, req
Ready to connect★ 56
- View details
web-summarizerSkillWeb & browsing
Reads the content of an article or webpage, extracts the main points, and provides a concise, structured summary.
Ready to connect★ 56
- View details
design-elevationSkillWeb & browsing
Comprehensive design elevation system that automatically transforms functional visual outputs into polished, professional designs. Use when creating ANY visual output including presentations (pptx), spreadsheets (xlsx), dashboards, reports, HTML artifacts, PDFs, web pages, or data visualizations. Ap
Ready to connect★ 55
- View details
diagnoseSkillWeb & browsing
Mastery-level diagnostics (Diagnostic R28, FORM.089 §6.1 v5.0) right in VS Code / claude.ai. Up to 6 questions, ~3 min. Saves the cp-profile to the canonical log learning.cp_assessments — via the MCP tool (browser) or directly to Neon (VS Code). Run it when: the pilot says "пройди диагностику",
Ready to connect★ 54
- View details
ever-worksSkillWeb & browsing
Repo-specific guide to the Ever Works monorepo (ever-works/ever-works) — its pnpm + Turborepo layout, the per-workspace test runners (Jest vs Vitest vs Playwright), file-naming and import-alias conventions, the commit/branch model, and the real build/lint/type-check commands. Use this whenever worki
Ready to connect★ 55
- View details
feature-verifySkillWeb & browsing
Cross-verify a just-finished feature with throwaway browser tests driven by chrome-headless-shell — proves the feature actually does what it was supposed to do, and proves the change didn't break the routes and components that depend on it. Reports a verdict with evidence and never edits app code. U
Ready to connect★ 55
- View details
peer-conversationSkillWeb & browsing
Multi-turn dialogue between a writer (Claude) and one or more partners (any set of kimi/codex/hermes/claude-headless) on a pilot task (DP.SC.154). Runs a turn-loop (2 participants) or round-loop (3+, WP-509), detects CONSENSUS/ESCALATE, and after consensus holds a Decision Gate (record vs re
Ready to connect★ 54
- View details
playwright-best-practicesSkillWeb & browsing
Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation,
Ready to connect★ 55
- View details
skill-seekersSkillWeb & browsing
Convert documentation websites, GitHub repositories, PDFs, and reference sets into portable Agent Skills with source traceability and validation.
Ready to connect★ 55
- View details
ux-writingSkillWeb & browsing
Create user-centered, accessible interface copy (microcopy) for digital products including buttons, labels, error messages, notifications, forms, onboarding, empty states, success messages, and help text. Use when writing or editing any text that appears in apps, websites, or software interfaces, de
Ready to connect★ 55
- View details
agent-browser-zhSkillWeb & browsing
A browser automation CLI based on Vercel's agent-browser, designed for AI agents. This is the best tool for AI-driven browser automation—using deterministic refs from the accessibility tree instead of fragile selectors. Optimized for LLMs, with a fast Rust CLI, JSON output, and dedicated AI workflow
Ready to connect★ 54
- View details
brave-search-zhSkillWeb & browsing
Web search and content extraction via the Brave Search API. Use it to search documentation, facts, or any web content. Lightweight, no browser required.
Ready to connect★ 54
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
54,764 of the 55,196 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.