build-tables
Combine saved Stata estimates into publication-ready tables via esttab. Produces both .tex (for paper) and .csv (for audit) with consistent formatting.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Combine saved Stata estimates into publication-ready tables via esttab. Produces both .tex (for paper) and .csv (for audit) with consistent formatting.
Generate images from text prompts and edit existing images using OpenRouter's dedicated Image API. Use when the user asks to create, generate, or make an image, picture, or illustration from a description, or wants to edit, modify, transform, or alter an existing image with a text prompt.
Transcribe speech to text using OpenRouter's speech-to-text API. Use when the user asks to transcribe audio, convert speech to text, extract a transcript from a recording or meeting, caption a video's audio, or mentions STT, speech-to-text, ASR, or transcription.
Generate speech audio from text using OpenRouter's text-to-speech API. Use when the user asks to synthesize speech, narrate text, create a voiceover, generate an audiobook clip, read text aloud, convert text to an audio file, or mentions TTS, text-to-speech, or voice synthesis.
Run a holistic narrative review on a Quarto report or Markdown document. Checks reader prerequisites, worked examples, notation clarity, structural arc, and pacing.
Decide where in `wiki/` to place a new or existing Wiki page, picking a topical subfolder rather than dumping it at the root. Use this skill whenever the user creates a Wiki note, asks where a topic should live, wants to relocate an existing Wiki page, or says anything like "place wiki", "organize wiki", "where should this wiki go", "move this wiki page", "find a home for X", "this should probably live somewhere else". Also invoked automatically by the `create-page` skill for Wiki type. Reads existing `wiki/` subfolders to ground placement, proposes 1-2 candidate homes, pushes back against kitchen-drawer root dumping, and executes the move/create via Obsidian CLI so the link index stays intact.
Render a Quarto report (Stata engine) to HTML / PDF / DOCX. Performs freshness check on included tables/figures, verifies the Stata Quarto engine, and validates numerical claims before rendering.
Use this skill when working with TabFM, Google's zero-shot tabular foundation model, running classification or regression on a CSV or DataFrame without training, benchmarking TabFM against XGBoost or TabICL, or debugging TabFM installation and weight loading. Covers the tabfm Python package, TabFMClassifier and TabFMRegressor, Hugging Face weight download, the PyPI loader bug, CPU dtype performance, hard model limits, and the weight license.
Fetch transcripts from YouTube videos and save as structured Markdown files to ~/yt_transcripts/. Use this skill whenever the user shares a YouTube URL or video ID and wants the transcript, captions, or subtitles extracted. Also triggers when the user wants to take notes on a YouTube video, summarize video content, analyze what was said in a video, or reference YouTube content in their notes — even if they don't explicitly say "transcript." If the user pastes a YouTube link with no other context, default to fetching the transcript.
Swedish SIE4 file format: parsing, validation, generation, troubleshooting. All record types (#VER, #TRANS, #IB, #UB, #RES, #KONTO, #RAR, #FLAGGA, #KSUMMA, #SRU, etc.), SIE types 1-4, encoding detection (CP437/UTF-8/Latin-1), mojibake diagnosis, verification balance integrity, IB/UB continuity, multi-year migration, diffing, audit trail under BFL, BAS account classes, SRU tax codes, and error patterns. Trigger on ANY SIE question: import, export, parsing, validation, encoding issues, garbled å/ä/ö, unbalanced verifications, IB/UB mismatch, #FLAGGA, SIE migration between Fortnox/Visma/BL/SpeedLedger/Bokio, .SE/.SI files, verification series, or code reading/writing SIE data. Always use over training data.