Skill UI

A comprehensive guide for setting up the Finta fundraising CRM account. This skill assists users with initial onboarding, connecting critical data sources like Gmail, Outlook, and Google Calendar to automatically track investor communications and meeting activities. It is essential for managing the entire fundraising pipeline, from initial research to closing a term sheet.

Executes the comprehensive workflow for claiming Research & Development (R&D) tax credits through Fondo. This skill guides users through qualifying R&D expense calculation, prepares the necessary Form 6765, and manages the payroll tax offset process for startups, potentially saving up to $500,000 annually.

idea-os is a comprehensive, five-phase pipeline designed to transform a raw, abstract idea into a fully structured, build-ready plan. It guides users through Triage, Clarification, Deep Research, detailed PRD creation (including non-goals and metrics), and finally, a phased execution plan. The system adapts its complexity and vocabulary to the user's sophistication level, providing everything from foundational market analysis to actionable technical stack recommendations.

This structured skill guides users through root-cause-first debugging when an implementer is blocked, verification fails, or repeated attempts at fixing do not converge. It mandates a systematic approach combining local evidence inspection, runtime analysis, and external documentation research to accurately classify the failure's true source (e.g., missing dependency, spec conflict). It prevents speculative patching and generates a clear, actionable fix plan.

This skill provides a deep dive into the architecture of low-level keyloggers. It covers techniques such as kernel driver hooks, using WH_KEYBOARD_LL, ETW-based input capture, and analyzing user-mode vs. kernel-mode approaches. Use this methodology to understand input capture mechanisms, research EDR evasion methods, or analyze malware architecture for advanced security threat detection.

This technique guides users through a rigorous two-phase research strategy. First, conduct a broad search to identify potential papers or authors. Crucially, the system instructs the user to use the extracted "author full name" as a highly specific anchor in subsequent queries. Combining the author's name with details like journal, institution, year, or biographical information ensures the most precise and reliable results, significantly narrowing down the search scope and achieving deep academic insights.

Automates the entire process of web research and professional communication. It takes raw web search results and formats them into polished, structured messages, digests, or threaded summaries optimized for Slack. Users can generate outputs in Slack's native Markdown format, Block Kit JSON, or a ready-to-use Webhook command, perfect for weekly reports, security alerts, and competitive intelligence updates.

This comprehensive skill guides users through the entire lifecycle of developing AI agent skills. From initial concept (Understand) to structured design, writing the core skill logic, rigorous testing, and final performance optimization. It ensures skills are robust, accurate, and highly triggerable across any domain, including engineering, content creation, and research.

This technique guides users on how to use visual descriptions from music videos (MV), such as specific scenes, emotional themes (grief, loss), or real-world events, as powerful search anchors. Instead of only searching by title or artist, users can extract keywords from the visual narrative to refine search queries, significantly increasing the chances of identifying the correct song or tracing its origin. Ideal for music research and cultural analysis.

Analyzes Screenpipe history windows to detect repeated research workflows, match existing skills, and stage new skill drafts for review. Requires local Screenpipe daemon on localhost:3030 with optional LLM backend. Privacy-focused with data redaction before LLM processing. Use only when user explicitly requests workflow analysis.

A comprehensive methodology for exploiting Time-of-Check / Time-of-Use (TOCTOU) race conditions across diverse system layers. This covers symlink swaps, file-descriptor races, kernel double-fetch vulnerabilities, and advanced window-widening primitives like FUSE slow filesystems and userfaultfd. Essential for security researchers targeting race-based privilege escalation in binaries, kernels, and container orchestrators.

A comprehensive playbook detailing expert-level techniques for exploiting web cache vulnerabilities. Covers both Web Cache Deception (stealing authenticated user data) and Web Cache Poisoning (injecting malicious content). Techniques include path confusion, unkeyed header manipulation (X-Forwarded-Host), and exploiting CDN/reverse proxy caching logic. Essential reading for penetration testers and security researchers.