Development plugins

Build in-game UIs with JSUI: React Native components on QuickJS + Yoga + Skia, embedded in Godot, the web or C/C++.

1 skill

Teach your agent to optimize, resize, convert, and strip metadata from images with the crustyimg CLI.

1 skill

Finds the smallest safe change that improves software performance, simplicity, cleanliness, and organization.

1 skill

Build and audit polished mobile-first daily browser puzzle games.

1 skill

Claude scrive in Tokyn i programmi che usano Claude (agenti, chatbot, estrazione e classificazione di testi) con meno token del Python, li controlla e li prova con il compilatore incluso (prima con risposte finte, poi con il tuo Claude Code o una chiave API) e, se vuoi Python, ti dà il file generato dal compilatore. Messaggi in italiano.

1 skill

Claude writes programs that use Claude (agents, chatbots, text extraction and classification) in Tokyn with fewer tokens than Python, checks and runs them with the bundled compiler (first with fake answers, then through your Claude Code or an API key) and, if you want Python, hands you the file the compiler generates. Messages in English.

1 skill

Adversarial, diagnosis-only review of implementation plans before autonomous execution.

1 skill

Python language server (ty) for type checking and code intelligence.

LSP

Two-axis code review (Standards and Spec) in parallel sub-agents, from mattpocock/skills

1 skill

Standard README badges: what to include, Shields.io URLs, order, wording, colors and links, and which badges to delete.

1 skill

Teaches the agent to share a running server with `npx wurmhol <port>` and send the user the URL

1 skill

Structural code map for Roblox/Luau projects: module summaries, definitions, callers, remotes, attributes and tags in a few lines instead of whole files.

1 skill

Find Open Mercato modules before you build: the om-find-module skill searches the registry, checks what is verified on your Open Mercato version and shows the install plan. The MCP server is not deployed yet.

1 skill

Teaches Claude to write idiomatic, correct and fast keel code: models and keel gen, typed queries, relation loads, keyset pages, batches, writes, transactions, tenancy, hooks, migrations, seeds and tests.

1 skill

Laravel streamlines: skinny controllers, organized models, dumb views, config/routes/container/macros/exceptions/events done the Laravel way.

1 skill

Consulta el RPO de un AppServer Protheus sin VS Code: inspector de objetos y funciones, validacion de servidor y metadatos del RPO, hablando LSP con advpls.exe y reutilizando los tokens de servers.json (sin pedir contrasena).

1 skill

Coding agent skills for writing and reviewing user interfaces that follow the Nethesis design systems: Nebula and Carbon

1 skill

File ordering, architecture, errors, testing, review and prose rules for Go, TypeScript, Rust, Python and PHP.

1 skill

AI mob programming toolkit. Two engineers, two Claude Code instances, one shared brain. Collaborative coding via git and markdown — no external services required.

Plan and file goals and feature issues through conversation

Lean 4 language server for theorem proving

Comprehensive neural network training coach for Transformers - training, tuning, debugging, and scaling guidance

End-to-end dev workflow: /prflow:implement, /prflow:review + /prflow:review-and-fix, the /prflow:docs suite, /prflow:spec, plus the retrospective loop.

Elixir Language Server Protocol support for Claude Code

Drive a persistent headless Ghidra JVM from Claude Code: 19 reverse-engineering tools over MCP — decompile, navigate and search a program, plus durable rename/comment/set-datatype/set-prototype/set-local writes saved to the project.

Claude Code integration for rtk (Rust Token Killer): a PreToolUse hook that transparently rewrites Bash/PowerShell commands through rtk for 60-90% token savings, plus rtk analytics as MCP tools.

Sutra Native v1.5.0 — the production-grade founder workflow engine for Claude Code. v1.5.0 (2026-05-08) ships Verifier Engine v1: profile-driven utterance generator + 4-tier verifier (schema / artifact / behavior / rubric) + multi-axis assertion report (Outcome-Fidelity, Constraint-Honor, Cross-Stage-Drift, Acceptance-Coverage). SPEC §6 capture-lifecycle invariant enforced at extractor (auto-corrects clarification_required when ambiguity_flags non-empty OR confidence < 0.6) AND tier-1 verifier (new tier-1/ambiguity-coherence assertion). First scenario: pets-site (happy + broken-fixture variants). 1503 tests passing. + v1.4.0 (2026-05-06, D49) made Native fully standalone — no core@sutra dependency at runtime. Native ships its own H-Sutra producer hook + vendored classifier + shared lib. + v1.3.0 (2026-05-04) shipped 6-wave Native v1.x final ship: W1 per-step timeout_ms + CLI invoke_host_llm/--host-N + create-trigger CLI; W2 step-level approval gate; W3 cron daemon scheduler tick + workflow status/cancel CLI; W4 on_failure machinery; W5 PNC predicate adapter + commitment_broken; W6 cutover-validator + telemetry-sink. Backward-compatible with v1.2.2 user-kits.

Zig language server (zls) for code intelligence and analysis

Fortran language server (fortls) for code intelligence and analysis

R language server (languageserver) for statistics and data science