Loading...
Loading...
Found 765 Skills
Professional-level refinement and verification for Chinese SRT subtitles for launch. Used to clean ASR-based raw subtitles into a publishable version, only performing subtitle-level cleaning and correction without formal rewriting, summarization, or expansion; meanwhile, strictly maintaining synchronization with the original audio, splitting entries only within the original subtitle time range when necessary, outputting a complete clean SRT, and then using the accompanying verification script for final rule checks and timeline review. Suitable for tasks such as documentaries, interviews, oral broadcasts, screen recordings that require correcting recognition errors, deleting meaningless filler words, adding pause spaces, limiting single-entry word count, and avoiding accidental deletion of meaningful subtitles.
Source code security audit using backward taint analysis, slot type classification, render context verification, and 3-phase parallel review producing an exploitation queue.
oh-my-agent project setup verification and configuration
Identifies and exploits SQL injection vulnerabilities in web applications during authorized penetration tests using manual techniques and automated tools like sqlmap. The tester detects injection points through error-based, union-based, blind boolean, and time-based blind techniques across all major database engines (MySQL, PostgreSQL, MSSQL, Oracle) to demonstrate data extraction, authentication bypass, and potential remote code execution. Activates for requests involving SQL injection testing, SQLi exploitation, database security assessment, or injection vulnerability verification.
Build with Mailgun Validate API for email verification and list hygiene. Use when validating email addresses, checking email deliverability, running bulk validation jobs, previewing list health, or cleaning an email list.
Solve CAPTCHAs in automated browser sessions using third-party solving services. Use this skill whenever you need to: bypass a CAPTCHA while automating a website, integrate CAPTCHA solving into a Playwright or Puppeteer script, solve reCAPTCHA v2 or v3, hCaptcha, Cloudflare Turnstile, or image-based CAPTCHAs, automate a login or form submission that's blocked by a CAPTCHA, test a page that has CAPTCHA challenges, or write a script that needs to pass a CAPTCHA programmatically. Also triggers for: "recaptcha", "hcaptcha", "turnstile", "captcha solving", "bypass captcha", "solve captcha", "pass captcha challenge", "automate past captcha", "get past robot check", "bot verification". Always use this skill for any CAPTCHA-related automation — even simple cases benefit from correct token injection patterns.
Comprehensive guide to why and how AI agents should use email. Use when evaluating whether an agent needs email, comparing email infrastructure options (AgentMail vs Gmail API vs Resend vs SendGrid vs SES), understanding security risks like prompt injection via email and OAuth credential exposure, or exploring common agent email use cases such as customer support agents, sales outreach, verification flows, and browser automation.
Architecture patterns and best practices for giving AI agents email capabilities. Use when designing how agents send, receive, and manage email conversations, building two-way communication loops, implementing human-in-the-loop approval with drafts, choosing between WebSockets and webhooks, setting up multi-agent email topologies, handling OTP and verification flows, or securing agent email against prompt injection.
Primary Playwright governance skill for sandbox browser verification and deterministic end-to-end authoring or rewrite work.
create git commits and push code to GitHub safely. use when the user asks to commit, create branch, push changes, or prepare a pull request-ready commit with clear scope and verification.
Create a pull request with Conventional Commits formatting, a templated body, and local verification. Use when the user asks to create a PR, open a PR, submit changes for review, or put code up for review.
Launch multiple sub-agents in parallel to execute tasks across files or targets with intelligent model selection, quality-focused prompting, and meta-judge → LLM-as-a-judge verification