๐งฐDeveloper Tools Skills
Browse the best Developer Tools skills for Claude Code, Codex, Cursor and other AI agents.
7,129 skills ยท Page 13 of 298
fine-tuning-with-trl
โ
62Fine-tune LLMs using reinforcement learning with TRL: SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
implementing-llms-litgpt
โ
62Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
product-design
โ
46Automates design review, token extraction, component mapping, and implementation planning. Reduces design handoff from 6-10 hours to 5 minutes via direct Figma MCP integration. Auto-invoke when user mentions design review, Figma mockup, or design handoff.
nav-skill-creator
โ
46Analyze codebase patterns and create custom skills for repetitive workflows. Use when project needs automation or pattern enforcement. Auto-invoke when user says "create a skill for...", "automate this workflow", or "we keep doing X manually".
lean4-theorem-proving
โ
37Use when developing Lean 4 proofs, facing type class synthesis errors, managing sorries/axioms, or searching mathlib - provides build-first workflow, instance management patterns (haveI/letI), and domain-specific tactics
mcp-builder
โ
36Create high-quality MCP servers that enable LLMs to effectively interact with external services. Use when building MCP integrations for APIs or services in Python (FastMCP) or Node/TypeScript (MCP SDK).
imp
โ
30Unified shipping + TRACE self-review protocol (beads, proof, PR). Explicit-only.
development-guidelines
โ
30Use this task to ensure you follow development best practices during development and implementation.
unity-editor-toolkit
โ
29Unity Editor control and automation, WebSocket-based real-time communication. ์ ๋ํฐ์๋ํฐ์ ์ด๋ฐ์๋ํ, WebSocket๊ธฐ๋ฐ์ค์๊ฐํต์ .Features/๊ธฐ๋ฅ: GameObject control ๊ฒ์์ค๋ธ์ ํธ์ ์ด, Transform manipulation ํธ๋์คํผ์กฐ์, Component management ์ปดํฌ๋ํธ๊ด๋ฆฌ, Scene management ์ฌ๊ด๋ฆฌ, SQLite database integration SQLite๋ฐ์ดํฐ๋ฒ ์ด์คํตํฉ, GUID-based persistence GUID๊ธฐ๋ฐ์๊ตฌ์๋ณ, Multi-scene synchronization ๋ฉํฐ์ฌ๋๊ธฐํ, Command Pattern with Undo/Redo ๋ช ๋ นํจํด์คํ์ทจ์์ฌ์คํ, Menu execution ๋ฉ๋ด์คํ, ScriptableObject management ์คํฌ๋ฆฝํฐ๋ธ์ค๋ธ์ ํธ๊ด๋ฆฌ, Array/List manipulation ๋ฐฐ์ด๋ฆฌ์คํธ์กฐ์, All field types support ๋ชจ๋ ํ๋ํ์ ์ง์, Material/Rendering ๋จธํฐ๋ฆฌ์ผ/๋ ๋๋ง, Prefab system ํ๋ฆฌํน์์คํ , Asset Database ์ ์ ๋ฐ์ดํฐ๋ฒ ์ด์ค, Animation ์ ๋๋ฉ์ด์ , Physics ๋ฌผ๋ฆฌ, Console logging ์ฝ์๋ก๊น , EditorPrefs management ์๋ํฐํ๋ฆฌํผ๋ฐ์ค๊ด๋ฆฌ, Editor automation ์๋ํฐ์๋ํ, Build pipeline ๋น๋ํ์ดํ๋ผ์ธ, Lighting ๋ผ์ดํ , Camera ์นด๋ฉ๋ผ, Audio ์ค๋์ค, Navigation ๋ค๋น๊ฒ์ด์ , Particles ํํฐํด, Timeline ํ์๋ผ์ธ, UI Toolkit, Profiler ํ๋กํ์ผ๋ฌ, Test Runner ํ ์คํธ๋ฌ๋.Protocol ํ๋กํ ์ฝ: JSON-RPC 2.0 over WebSocket (port 9500-9600). 500+ commands ๋ช ๋ น์ด, 25 categories ์นดํ ๊ณ ๋ฆฌ. Real-time bidirectional communication ์ค์๊ฐ์๋ฐฉํฅํต์ .Securit
ln-700-project-bootstrap
โ
25Orchestrates full project bootstrap from Replit export to production-ready structure
dagster-development
โ
25Expert guidance for Dagster data orchestration including assets, resources, schedules, sensors, partitions, testing, and ETL patterns. Use when building or extending Dagster projects, writing assets, configuring automation, or integrating with dbt/dlt/Sling.
configuration-management
โ
25Manage application configuration including environment variables, settings management, configuration hierarchies, secret management, feature flags, and 12-factor app principles. Use for config, environment setup, or settings management.
ide-diagnostics
โ
23Expert knowledge of IDE/LSP tools for code navigation, diagnostics, and refactoring. Use when working with TypeScript errors, linting issues, code navigation, or IDE operations.
pyhealth
โ
22Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).
dependency-manager
โ
21Expert dependency manager specializing in package management, security auditing, and version conflict resolution across multiple ecosystems. Masters dependency optimization, supply chain security, and automated updates with focus on maintaining stable, secure, and efficient dependency trees.
nlp-engineer
โ
21Expert NLP engineer specializing in natural language processing, understanding, and generation. Masters transformer models, text processing pipelines, and production NLP systems with focus on multilingual support and real-time performance.
creating-mcp-servers
โ
21Creates production-ready MCP servers using FastMCP v2. Use when building MCP servers, optimizing tool descriptions for context efficiency, implementing progressive disclosure for multiple capabilities, or packaging servers for distribution.
codex-cli
โ
19OpenAI Codex CLI orchestration for AI-assisted development using gpt-5.2-codex model. Capabilities: code generation, refactoring, automated editing, parallel task execution, session management, code review, architecture analysis, and MCP integration. Actions: analyze, implement, review, fix, refactor with Codex. Keywords: Codex CLI, gpt-5.2-codex, codex exec, code generation, refactoring, parallel execution, session resume, code review, second opinion, independent review, architecture validation, Context7 MCP. Use when: delegating complex code tasks to Codex, running multi-agent workflows, executing automated reviews, implementing features with AI assistance, resuming previous sessions, querying OpenAI documentation. Triggers: 'use codex', 'codex exec', 'run with codex', 'codex resume', 'implement with codex', 'review with codex', 'codex docs'.
standup
โ
18Analyze git history, codebase structure, PRs, and issues to brief you on project state and next objectives. Use when returning to a project after any time awayโ1 day or 30 days. Produces current state, recent changes, and recommended next steps.
agentic-jujutsu
โ
18Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination
github-explorer
โ
18Explores, analyses, and works with GitHub repositories and git history. Includes searching public repos, comparing repositories, setting up GitHub Actions, debugging workflows, and investigating git history to trace code changes. Use when working with GitHub or git history.
react-native-setup
โ
17Expert in React Native 0.83+ and Expo SDK 54+ environment setup. Helps with Node.js 20+, Xcode 16.1+, Android Studio, watchman, CocoaPods, EAS Build, simulators, emulators, and troubleshooting. Activates for environment setup, installation issues, xcode setup, android studio, simulators, emulators, react-native init, expo init, development environment, SDK configuration, EAS Build, development builds.
obsidian
โ
16Comprehensive guidelines for Obsidian.md plugin development including all 27 ESLint rules, TypeScript best practices, memory management, API usage (requestUrl vs fetch), UI/UX standards, and submission requirements. Use when working with Obsidian plugins, main.ts files, manifest.json, Plugin class, MarkdownView, TFile, vault operations, or any Obsidian API development.
gemini-cli
โ
16Use Gemini CLI as a complementary AI tool for tasks requiring massive context windows (1M tokens). Invoke when analyzing large codebases, requesting deep analysis with extended thinking, getting second opinions on complex problems, or when Claude's context limits are insufficient. Triggers include phrases like "use gemini", "analyze with gemini", "get second opinion", "deep analysis of codebase", or when processing files exceeding Claude's context capacity.