Pesquisa e Web

Trigger on "weekly podcast", "timeln podcast", "podcast from my saves", "turn my saves into audio", "listen to my saves". Produces one Timeln Podcast MP3 from Timeln saves (default: last 7 days). Full pipeline: pull, connect, TTS script, local render. NOT for text-only search (timeln-find) or action plans (timeln-plan).

Verifies canon status, naming compliance, frontmatter completeness, writing standards, and cross-reference validity across worldbuilding files. Use when checking naming consistency, verifying frontmatter, auditing prose standards, or when user says "canon audit", "check names", "verify frontmatter", "writing standards check", or "naming audit". Does NOT check physics equations — use /auditing-phys

Full-spectrum web application VAPT skill for Claude Code, OpenCode, Codex CLI & Gemini CLI — from reconnaissance to exploitation to remediation reporting

Profile ML training performance to identify bottlenecks (data loading, compute, memory usage) and optimize GPU utilization. Use when training is slow, GPU utilization is low, or experiencing memory issues.

Generate images with transparent backgrounds using difference matting technique. Use when creating assets with transparency, extracting alpha channels, batch generating transparent images via Vertex AI, or working with PNG transparency.

Full-spectrum web application VAPT skill for Claude Code, OpenCode, Codex CLI & Gemini CLI — from reconnaissance to exploitation to remediation reporting

Stress-test and improve implementation plans before execution. Researches alternatives, challenges complexity, checks modularity and feasibility, then delivers a full revised plan. Use whenever the user has a plan — any format (PLAN.md, inline, pasted, attached) — and wants it reviewed before starting. Trigger on 'review this plan', 'challenge this plan', 'stress test', 'is this plan good', 'befor

Audit a project's Claude Code setup against official Anthropic documentation. Evaluates 9 areas: CLAUDE.md, Rules, Skills, Sub-agents, Hooks, Permissions, Settings, MCP servers, and Feature Selection. Produces a scored AUDIT-REPORT.md with findings that cite documentation sources fetched during the session. Use this skill when the user says 'audit', 'audit my setup', 'review my Claude Code config'

Use when you need to investigate an unfamiliar library, framework, architectural question, or technical decision — spawns the researcher agent which explores the codebase and searches external sources in parallel. Invoke before making technology choices or when the right approach is unclear.

[PM Twin] Generate user research plan and interview script from PRD — discovery, usability, or feedback studies.

Use Google's Deep Research API (Gemini) to conduct comprehensive, multi-source research that runs for 5-20 minutes server-side and produces detailed research reports. Use when the user asks for "deep research", thorough investigation of complex topics, market analysis, competitive landscaping, or any research requiring multiple web sources synthesized into comprehensive reports. This skill uses th

Distill raw observations and research data into meaningful, actionable product insights. Use this skill when a team has research data and needs to move from observations to insights that can drive decisions.