RetentaDocuments and media are deceptively difficult agent inputs: a PDF can be visually correct but structurally broken, a spreadsheet can preserve formulas while corrupting meaning, and a transcript can lose speaker boundaries that matter to the task. These skills give an agent format-specific workflows and verification steps instead of treating every file as plain text.
The records separate source review from execution evidence. A pinned workflow can explain how its publisher expects a format to be handled without proving that every parser, model call or generated artifact will behave correctly in your environment.
OpenAI · Codex
A template-first workflow for reproducible experiment and tutorial notebooks, with safe scaffolding, focused cells, validation, and explicit output conventions.
OpenAI · Codex
A render-first process for reading, creating, and reviewing PDFs with layout-aware visual checks and programmatic generation or extraction tools.
OpenAI · Codex
A repeatable CLI workflow for OpenAI speech transcription, optional speaker diarization, known-speaker hints, chunking, and organized output validation.
Anthropic · Claude Code
A detailed production workflow for reading, creating, editing, validating, and visually inspecting PPTX and POTX files through PptxGenJS or direct OOXML operations.
Anthropic · Claude Code
A formula-safe spreadsheet workflow covering XLSX, XLSM, CSV, and TSV creation or editing, recalculation, compatibility constraints, source documentation, and financial-model conventions.
Eligible reviewed snapshots can be added to a Thyme RAG Capsule in one click. Retenta only enables that action after a separate capsule-distribution check; other records link to the publisher's installation path.