Loading...
Loading...
Found 982 Skills
Verify contact details for a prospect list — email status, phone validity, LinkedIn match, name check. Use when the user wants to validate or clean a prospect contact list.
Automated auditor designed to verify Android applications against Google Play Policy domains. It cross-references static code analysis with Play Store declarations to generate deterministic compliance reports, identifying undeclared data collection, architectural risks, and missing disclosures across Permissions and APIs Hygiene, User Account and Identity, and Data Safety and Privacy domains.
Reuse one manually established Playwright login state across multiple isolated automation instances running in parallel, with routed Setup, Login, and Launch subflows. Use when a user asks to install or configure Playwright Chromium, manually establish or refresh a site's shared login state, open or automate a site with persisted authentication, verify shared authentication, take authenticated screenshots, or run concurrent authenticated browser work. On first use, automatically run Setup; prefer the read-only Launch subflow for normal daily automation.
Operate and verify queues with or without Horizon; safe worker flags, failure handling, and test strategies
Apply RED-GREEN-REFACTOR with Pest or PHPUnit; use factories, feature tests for HTTP, and parallel test runners; verify failures before implementation
The full lifecycle for agentic loops — recurring, scheduled AI agents packaged as a portable LOOP.md (the agenticloops.dev standard: a trigger + skills + a prompt in one file any harness can install and run on a schedule). Use this whenever the user wants to FIND, INSTALL, RUN, or BUILD a loop: "find a loop for X", "is there a loop that…", "install a recurring agent that does X", "run this loop", as well as "create a loop", "make an agentic loop", "write a LOOP.md", "turn this into a recurring agent", "schedule an agent", "set up a cron job for an agent", or any description of a repeating job they want an agent to do on a timer (a daily digest, a competitor watcher, a triage sweep, a report pipeline, "email me X every morning", "check Y every hour") — even if they never say the word "loop". Always search the directory first and install an existing loop when one fits; author a new LOOP.md only when nothing does. This is the loop-level analogue of skill-creator + find-skills combined. For an ad-hoc in-session multi-agent run (spawn, verify, panel, fan-out) use the `loops` skill instead; for authoring a reusable SKILL.md use skill-creator.
End-to-end testing and click-verification of web apps with Playwright — install, write specs, drive authenticated pages, take screenshots, and run in CI. Use when verifying a web change actually works in a real browser, testing user flows, debugging a UI bug live, or confirming an authed/gated page before shipping. Keywords Playwright, e2e, browser test, click test, screenshot, headless.
CodeRabbit CLI local code reviews and .coderabbit.yaml configuration. Run AI reviews on uncommitted/committed changes before pushing or opening a PR, parse --agent findings, iterate fix-and-verify loops within hourly rate limits, and tune repo config for low-noise high-signal reviews. Use when reviewing local changes pre-push/pre-PR, installing or driving the coderabbit/cr CLI, creating or tuning .coderabbit.yaml, or reducing CodeRabbit review noise. Not for PR-side review loops and thread handling (git-pr), commits (git-commit), or CI status (git-ci)
Running structured, multi-source research that produces a trustworthy, cited synthesized answer. Use when a question needs more than a single lookup — comparing options, validating a claim, surveying a market or technology, or briefing a decision where being wrong is costly. Covers scoping (and narrowing) the question, fanning out across sources, judging source quality, adversarially verifying each key claim, separating fact from inference, and reporting with explicit confidence. Keywords deep research, multi-source, fact-check, verify, synthesize, cited report, source credibility, due diligence.
Coming from Firecrawl? Switch to fastCRW in one line. Use when the user has existing Firecrawl SDK code (firecrawl-py, firecrawl-js, REST calls, or an MCP config) and wants to point it at fastCRW — managed or self-hosted. Covers the exact base_url swap, which endpoints are drop-in, which have gaps, and how to verify the switch worked.