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 71 of 82
- View details
scout-loopSkillWeb & browsing
The super-loop that closes the research→backlog loop — it chains the outward CRAWLERS (the daily `idea-scout` arXiv/GitHub feed, the industry scans, the RESEARCH/CONCEPT corpus) into the STUDY pipeline...
Ready to connect
- View details
- View details
splunk-appdynamics-eum-setupSkillWeb & browsing
"Use when the user asks for AppDynamics EUM, Browser RUM, BRUM, Mobile RUM, IoT RUM, app keys, JavaScript
Ready to connect
- View details
splunk-appdynamics-synthetic-monitoring-setupSkillWeb & browsing
"Use when the user asks for AppDynamics Synthetic Monitoring, browser synthetic jobs, Synthetic API
Ready to connect
- View details
splunk-observability-browser-rum-setupSkillWeb & browsing
"Use when the user asks for Splunk Browser RUM, JavaScript RUM, @splunk/otel-web, source maps, frontend
Ready to connect
- View details
super-loopSkillWeb & browsing
Plan, price, launch, monitor, and reconcile bulk headless issue-resolution work safely. Use when an operator asks for a super loop, worker wave, detached issue workers, backlog draining, capacity/status,...
Ready to connect
- View details
t3SkillWeb & browsing
Start, inspect, pair, or stop T3 Code in the Open Harness sandbox, locally or over a private Tailscale tailnet for phone access. Use this for the headless `t3 serve` harness on port 3773, including tmux launch, preflight diagnosis, pairing URL discovery, minting a pairing URL for a second device, lo
Ready to connect
- View details
test-driven-developmentSkillWeb & browsing
Guides your agent to write a failing test first, then minimal code to pass it, when building features or fixing bugs.
Ready to connect
- View details
wave-harvestSkillWeb & browsing
The honest closing half of a super loop — after a detached bulk wave (`/super-loop`) has run, HARVEST it: witness what each headless worker actually shipped (not what its log claims), re-queue the leaves that were...
Ready to connect
- View details
autonomous-reviewSkillWeb & browsing
Use to perform an end-to-end PR review and reach an approve/request-changes verdict — including verifying acceptance criteria, running E2E tests via browser automation, resolving merge conflicts, and (when verdict passes) merging the PR. Triggers on phrases like "review this PR", "decide whether to
Ready to connect
- View details
fb-audience-insightsSkillWeb & browsing
Read a Facebook Page and its audience from real data. Pull any Page's public stats (yours or a competitor's): followers, likes, categories, intro, websites. And pull the commenters on a public Page post, since Facebook hides the reactor and liker roster and shows counts only, so commenters are the s
Ready to connect
- View details
openghost-skillSkillWeb & browsing
Local open-source Agent Skill for authorized web application, API, browser, business-logic, and supporting server-integrity penetration testing. Use for scoped OWASP WSTG, ASVS, and API Security assessments; authenticated and multi-role validation; attack-surface mapping; bounded DAST; evidence-back
Ready to connect
- View details
page-auditSkillWeb & browsing
The Experience Auditor Swarm. Audits a live page or a whole site from first principles: the job each page exists to do, whether its value promise is real and delivered fast, clarity, the path to action, craft, function, and trust. Use when auditing a website or landing page you run, doing a first-pr
Ready to connect
- View details
post-to-campaignSkillWeb & browsing
Turn a specific LinkedIn post (its URL) into a ready-to-launch outreach campaign. Use this whenever a request references a LinkedIn post or pastes a post URL: only this skill scrapes the post's likers and commenters into an audience before writing the sequence, so prefer it over any generic campaign
Ready to connect
- View details
acpx-faqSkillWeb & browsing
Run coding agents (codex, claude, Antigravity/agy) headlessly through the acpx ACP CLI. Use before launching or prompting an acpx subagent, and when an acpx command fails, a session is not found, or a prompt seems lost.
Ready to connect
- View details
ad-creativeSkillWeb & browsing
Runs the full Higgsfield + GPT Image 2 + Seedance 2.0 chain end-to-end from a brand URL to produce a multi-format ad pack: LinkedIn 1.91:1 + 1:1 and Meta 1:1 + 4:5 + 9:16 (Reels/UGC), each in static, animated, and UGC variants. Stages: Firecrawl brand brief → GPT Image 2 hero static → platform-tuned
Ready to connect
- View details
ccSkillWeb & browsing
Drive the running Cockpit server — terminal/browser bubbles, codegraph — through the `cockpit` CLI.
Ready to connect
- View details
chrome-extension-wxtSkillWeb & browsing
Build Chrome extensions using WXT framework with TypeScript, React, Vue, or Svelte. Use when creating browser extensions, developing cross-browser add-ons, or working with Chrome Web Store projects. Triggers on phrases like "chrome extension", "browser extension", "WXT framework", "manifest v3", or
Ready to connect
- View details
claude-code-opsSkillWeb & browsing
Claude Code internals - hooks, skill frontmatter, headless mode, and extension debugging, current as of June 2026. Triggers: hooks, hook events, hook not firing, PreToolUse/PostToolUse/SessionStart, skill frontmatter, SKILL.md, skill not triggering, headless, claude -p, CI/CD scripting, plugin valid
Ready to connect
- View details
cockpit-releaseSkillWeb & browsing
Cut a new Cockpit release end-to-end — bump version, tag, publish to npm, write user-facing release notes, refresh the website, and verify everything went live.
Ready to connect
- View details
code-server-playwright-automationSkillWeb & browsing
Fix Playwright automation failures against code-server (VS Code in browser). Use when: (1) trust dialog blocks all clicks — "monaco-dialog-modal-block intercepts pointer events", (2) button:has-text() finds wrong buttons behind modal dialog, (3) keyboard shortcuts don't work — Meta vs Control incons
Ready to connect
- View details
fleet-workerSkillWeb & browsing
One cheap headless Claude Code worker on a cheaper brain (GLM via z.ai, or Sonnet/Haiku) - full tool harness, isolated git worktree + CLAUDE_CONFIG_DIR - fanned out and gated by an Opus orchestrator. Triggers: fleet-worker, GLM worker, grunt worker, cheap parallel agent, offload to GLM, sonnet worke
Ready to connect
- View details
gui-perf-profiling-cdpSkillWeb & browsing
Diagnose React + Three.js (or any browser canvas) frame stutter by capturing a CDP CPU profile via Playwright instead of guessing from `[perf]` console logs. Use when: (1) frame time is bad but `[perf]` instrumentation doesn't pinpoint the offender, (2) you've spent more than ~30 minutes "fixing" su
Ready to connect
- View details
hook-miningSkillWeb & browsing
Mine a CSV of REAL top-performing hooks and generate alternatives that keep what made them work: hold the storytelling psychology and structure fixed, hot-swap only the power words. Use when the user has hook performance data (a Sandcastles / social-analytics export, scraped competitor hooks, their
Ready to connect
- View details
icp-behaviouralSkillWeb & browsing
'Creates synthetic buyer personas that simulate real purchase decisions, then runs those personas through website
Ready to connect
- View details
leveldb-opsSkillWeb & browsing
Read and inspect LevelDB stores - especially Chromium/Electron app state (Local Storage, IndexedDB, Session Storage). Triggers on: leveldb, .ldb files, IndexedDB, Local Storage, Chromium storage, Electron app state, claude.ai cache, browser forensics, decode app state, claude desktop state.
Ready to connect
- View details
linkedin-ad-teardownSkillWeb & browsing
Pull a competitor's live + recent ads from LinkedIn's public Ad Library and turn them into a strategy read — recurring themes, offers, ad formats, posting cadence, EU-disclosure targeting signals, and the gaps they're leaving open. Sources via our existing scrapers (Browser MCP free-first, then Fire
Ready to connect
- View details
linkedin-content-auditSkillWeb & browsing
'Audits LinkedIn creator profiles by scraping recent posts via Apify and producing a structured analysis of hook
Ready to connect
- View details
mapbox-opsSkillWeb & browsing
Mapbox GL JS v3 (web) toolkit: custom markers, symbol/geojson layers, clustering, style expressions, 3D terrain/fill-extrusion, heatmaps, choropleths, camera animation, and performance gotchas. Use for any Mapbox GL JS work — markers, layers, style, 3D, or headless map verification.
Ready to connect
- View details
onboarding-video-scriptSkillWeb & browsing
Writes product onboarding video scripts that founders or PMs read aloud to record. Pulls from a product website
Ready to connect
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.