Recording → Structured Artifact
Three skills that turn unstructured recordings and AI-assisted drafts into artifacts you can actually trust, built on the same discipline: never invent what the source didn't show. screencast-to-sop turns a screen recording into a documented procedure without inventing a step you didn't record. video-strategy-extraction does the same for any instructional video or transcript — extracting a structured spec at near-zero tool cost, flagging low-confidence extractions instead of guessing. ai-content-fact-audit closes the loop on anything AI-assisted you're about to publish, grading provenance rather than falsely certifying "true." One discipline, three different input types.
Works with every agent that reads SKILL.md — Claude Code, Cursor, Codex CLI, Gemini CLI, GitHub Copilot, Windsurf, OpenClaw, and more.
One payment, lifetime access. 3 skills unlock instantly in your library.
30-day refund guarantee
Instant unlock in your library
Free updates from the creator
What's included
3 skills
High-precision fact checking that traces claims to primary sources and assigns provenance-strength grades.
Turn instructional videos into structured, schema-validated specs without hallucinating missing details.
Convert instructional videos into machine-readable, schema-validated specs without hallucinations or invented parameters.
See it in action
You say
Audit this claim: "Recent studies show 91.5% of vibe-coded apps have critical security vulnerabilities." Trace it to the primary source and grade the provenance.
Your agent does
Grade: UNCORROBORATED Flag: MIS-SCOPED Trail: Cited 'Security Weekly' blog -> Traced to 'Vendor X Audit Report'. Finding: The 91.5% figure refers only to a sample of 200 apps using Vendor X's tool, not all vibe-coded apps. Action: Re-scope to 'one vendor audit' or cut.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.