Explorar skills

Speech-to-text transcription and animated subtitle generation using Whisper and FFmpeg. Creates word-by-word animated captions (karaoke-style), SRT/ASS/VTT subtitles, burns subtitles into video, extracts existing subtitles, converts between formats, and styles captions with custom fonts, colors, and animations. Use when user says "caption", "subtitle", "transcribe", "whisper", "SRT", "ASS", "VTT",

Write and optimize complex SQL queries — JOINs, CTEs, window functions, query plans, and dialect-specific syntax.

Data-driven performance optimization through profiling and infrastructure tuning

Language coaching for every prompt. Use when the user runs /language-coach with any sub-command (setup, native, target, style, response, goal, mode, focus, band, level, status, off, on). Routes to the correct action based on the argument provided.

Identify security vulnerabilities in code and configurations — CVE lookup, SAST findings, and remediation guides.

Write high-converting copy — landing pages, ads, product descriptions, taglines, and brand narratives.

Good-faith divergent brainstorming for achieving a goal. Validates assumptions, then spawns brainstormers running different techniques (first-principles, working-backwards, lateral, analogical, constraints-shift, etc.) in isolation, and synthesizes the pool into a report of standouts, reasonable ideas, and hybrid combinations. Produces feedback only — no code, no tickets, no artifacts.

Run agile sprints — backlog refinement, story pointing, sprint planning, daily standups, and retrospective formats.

Run a structured retrospective on a shipped commit range, release, deployment, PR, commit, or session. Per-fix validation enforcement, active evidence-sourcing pass (autonomous lookups + targeted user-asks for anything that could become objective), simpler-alternative discipline, re-diagnosis, action verdicts, and a growing failure-mode pattern library. Triggers: '/retrospect' (auto-range), '/retr

Reflective pass over your memory files — merge duplicates, fix stale facts, prune the index.

A trust layer between AI agents and your codebase. 🚀 Enterprise AI Agent Ecosystem - 40 Claude Code subagents for strategic leadership, tech architecture & organizational transformation. Built with ❤️ in Milano 🇮🇹

Facilitate cohort-based learning — weekly prompts, peer challenges, group projects, and community engagement.