Agent skills for Claude Desktop

Automates complex PDF operations including text extraction, table parsing, document generation, and form filling using top-tier Python and…

Use this skill whenever PDF files are created, read, merged, split, transformed, OCR-processed, or data-extracted.

Automate Pdf4me tasks via Rube MCP (Composio).

Display and manipulate PDF documents using PDFKit.

Automate Pdfless tasks via Rube MCP (Composio).

Automate Pdfmonkey tasks via Rube MCP (Composio).

Extract TikZ diagrams from Beamer `.tex` source, compile each to a standalone PDF, and convert to SVG with 0-based indexing.

Comprehensive manuscript review with three modes: single-pass (default), --adversarial critic-fixer loop, and --peer [journal] simulated…

Read-only proofreading pass over lecture `.tex` or `.qmd` files.

Consult with a peer engineer for plan review, code review, implementation discussions, or problem-solving brainstorming.

Help someone give peer feedback for a colleague using the Non-Violent Communication framework

Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments.

Add Apple Pencil drawing with PKCanvasView, PKToolPicker, PKDrawing serialization/export, stroke inspection, and PencilKit/PaperKit…

Fetch and summarize all posts pending approval across one or more Planable workspaces.

Foundation for the Pennylane Company API v2 in a multi-company setup: where tokens live, how to call the API, cursor pagination, filters…

PennyLane integration skill for hybrid quantum-classical machine learning and variational algorithms

People HR integration via Apideck's HRIS unified API — same methods work across every connector in HRIS, switch by changing `serviceId`.

Generate headcount, attrition, diversity, or org health reports.

People research using Exa search. Finds LinkedIn profiles, professional backgrounds, experts, team members, and public bios across the web.

Run a focused interview with the operator about one specific brick (a feature, a module, a cross-cutting concern, a structural…

Per-category/per-family models can produce WORSE leaderboard scores than a single global model, even when per-category CV is better.