Coding & Development

npx skills add 1natsu-vacation/agent-skills

My personal SDLC toolbelt for AI coding agents — PRD to ship.

Helping the Agents Compose the Things

Turn an agent-authored YAML podcast script into a finished MP3 with OpenAI text-to-speech.

A Pharos Agent Skill — deploy ERC-20 tokens, verify contracts, and run batch airdrops on Pharos Atlantic Testnet and Pacific Mainnet. Full token lifecycle in one natural language command.

Agent skill repository: nishalpattan/capture-screenshot

Self-improving knowledge wiki as a coding-agent skill. Project-aware curation: drop sources in, run curate, occasionally archive. Companion skill curiosity-merge to merge in another wiki.

Retro game cover downloader as an AI Agent Skill. Batch download covers/logos from Libretro for Pegasus, ES-DE, RetroArch frontends. Compatible with Claude Code, Codex CLI, OpenClaw & CodeBuddy.

OpenClaw-specific Discord server backup skill with V3 cursor state, backlog queue, deterministic workers, and audit probes.

비공식 토스증권 API / TossInvest API Agent Skill: 공개 주식·시장 데이터를 Codex와 Claude Code에서 안전하게 재조회

DeployHQ CLI — deploy from your terminal, for humans and agents

music-control-skill，暂时支持spotify

唯一公开库：book-learn-distill Skill + 知识图谱 demo · 本月运营门面

Unit testing framework for LLM applications. Gives developers automated tools to test regression patterns in agent workflows.

Code search engine powered by AI agents capable of explaining large legacy codebases across multiple programming languages.

Text sequence indexing utilities translating structural model tracking parameters cleanly across distinct infrastructure targets.

Secure access token management layers safeguarding target model credentials across distributed production applications.

Boilerplate setup to deploy multi-agent streaming JSON interfaces over asynchronous WebSockets securely.

A battery-packed toolkit for building AI-native applications, giving agents straightforward structured entity-extraction skills.

Lightweight graph routing engine enabling localized model structures to hand off tasks upon failure.

Self-hosted AI coding assistant backend featuring low-latency code completion agent skills over internal corporate repos.

Open-source autopilot for VS Code and JetBrains. Connect any model to build unique architectural review agents inside your IDE.

aider is AI pair programming in your terminal. It lets you edit code in your local git repository directly through command-line chat.

Config routines giving specialized agents the ability to submit custom LoRA fine-tuning runs based on failed interactions.