Dev & Coding

A four-language engineering constitution that forces reference reading before coding, then enforces strict types, TDD, and file-size discipline.

Scans a repository and auto-generates a hierarchical set of AGENTS.md files at the root and in complexity-scored subdirectories.

Search and refactor code by syntax structure (AST) instead of text across 25 languages, with dry-run-first codemods.

A planning-only skill that grounds in your codebase, asks just the decisions you must own, and writes one decision-complete work plan after your explicit approval.

Token-efficient codebase navigation that uses tree-sitter AST parsing to map structure first and only unfold the symbols you actually need.

Analyzes a repo in parallel and generates AGENTS.md at the root plus in complexity-scored subdirectories.

Detects the languages in your project, installs and configures the right language server, then verifies it with a real diagnostics roundtrip.

A language-agnostic debugging workflow that forces runtime evidence, three hypotheses, a failing test, real manual QA, and full artifact cleanup.

Searches and reads local session transcripts across 20+ coding agents (Codex, Claude Code, OpenCode, and more) so you can recall past work with evidence.

Explores and scores your repo in parallel, then generates hierarchical AGENTS.md docs at the root and in high-complexity subdirectories.

A frontend discipline skill that forbids saying "done" until the site builds, passes checks, and is visually verified in a real browser.

Guides Claude through Hugging Face Transformers work: Hub model loading, pipeline inference, text generation, and Trainer fine-tuning on transformers 5.x.

Guides Claude in using Datamol, the Pythonic RDKit wrapper, for SMILES parsing, standardization, fingerprints, clustering, and 3D conformers.

Guides Claude to do exact symbolic math in Python with SymPy — algebra, calculus, solvers, matrices — and export results as code or LaTeX.

Organizes PyTorch code into LightningModules, Trainers and DataModules, with multi-GPU strategies and experiment logging.

Helps Claude write and deploy Python to Modal's serverless cloud with on-demand GPUs, volumes, web endpoints and cron jobs.

Guides Claude to read, write, and process DICOM files with pydicom 3.0.2 while enforcing PHI-safe output and a bounded de-identification preflight.

A version-pinned guide for building, simulating, transpiling, and running quantum circuits with Qiskit 2.x and IBM Quantum Runtime.

A practical guide for training, evaluating and customizing reinforcement learning agents with Stable Baselines3.

Design, review, and migrate MATLAB or Octave code with strict license gating, static-only safety checks, and reproducibility reporting.