All skills

Turns Claude into a Feynman-style thinking advisor that uses 5 mental models and 8 heuristics to test whether you truly understand something or just memorized its name.

Official skill for reading, merging, splitting, table extraction, creation, OCR and form filling of PDFs.

The official Anthropic skill for building slide decks with pptxgenjs, editing .pptx/.potx templates at the XML level, extracting content, and running required file and visual QA.

Official skill for creating, reading, and editing Word (.docx/.dotx) files, including tracked changes and comments.

A prompt-engineering skill that identifies the target AI tool and returns one paste-ready, tool-optimized prompt.

Turns complex answers into a single visual HTML explainer page with diagrams, tables and charts.

An output-style skill that reshapes Claude's answers for an ADHD reader: next action first, numbered steps, concrete time estimates, and progress restated every turn.

An output-style skill that reshapes Claude's answers to lead with the next action, number every multi-step task, restate progress each turn, and cut all filler.

A meta-skill that logs friction and user corrections during real work and converts them into skill updates or new-skill proposals at a weekly review.

Pull YouTube transcripts (multi-language, translated, SRT), chapters, speaker labels and cover images from just a URL or video ID.

Turns any article or document into a professional slide-image deck using 17 style presets, then merges it into PPTX and PDF.

A three-mode (quick/normal/refined) translation pipeline for Claude Code with glossary merging, chunking, and parallel subagent drafting.

Fetch any webpage through Chrome and save it as a clean Markdown file.

Inspects a GitHub PR, GitLab MR, or Perforce changelist for review comments, failing checks and description gaps, then helps fix them.

A Scrum toolkit for writing user stories, acceptance criteria, splitting epics, planning sprint capacity, and prioritizing the backlog.

Analyzes every open GitHub issue and PR in parallel and writes permalink-backed triage reports without ever mutating the repository.

x

Install, authenticate and operate Gemini Notebook (NotebookLM) end-to-end through the notebooklm-py CLI or its typed async Python API, with ID-pinned, authorization-aware workflows.

Keeps watching a pull request — CI, comments, and unresolved review threads — until it's genuinely ready to merge.

Runs a long-horizon experiment loop that improves a code/model/prompt artifact against an evaluator, using a persistent hypothesis tree and a held-out test merge gate to avoid overfitting.