Automation
Task automation and scripting
laravel-api
by JustSteveKing
Build production-grade Laravel REST APIs using opinionated architecture patterns with Laravel best practices. Use when building, scaffoling, or reviewing Laravel APIs with specifications for stateless design, versioned endpoints, invokable controllers, Form Request DTOs, Action classes, JWT authentication, and PSR-12 code quality standards. Triggers on "build a Laravel API", "create Laravel endpoints", "add API authentication", "review Laravel API code", "refactor Laravel API", or "improve Laravel code quality".
planning-with-files
by zhaono1
Uses persistent markdown files for general planning, progress tracking, and knowledge storage (Manus-style workflow). Use for multi-step tasks, research projects, or general organization WITHOUT mentioning PRD. For PRD-specific work, use prd-planner skill instead.
bug-finder
by osdlc
Sweep an entire codebase for real bugs and fix them. Partitions the tree into module-boundary territories, then runs three chained agent workflows — scan (three altitudes: in-function, in-module, in-library) → adversarial validate → fix → verify-fix → land — so a fresh agent performs every step and the orchestrating session never reads source itself. Opens one PR per module boundary, then surveys the open PRs, computes the conflict matrix deterministically with git merge-tree, and merges the overlapping bugfix branches into each affected PR in a single aggregated push so CI runs once per PR, not once per fix. Pass --bomb for maximum parallelization.
api-enhancement-scan
by osdlc
Given a library or module name, survey every call site of it across the codebase — fanning out subagents over independent codebase sections — and surface recurring caller-side patterns (repeated boilerplate, copy-pasted wrappers, awkward argument plumbing, repeated post-processing) that a new or enhanced API on the called module would absorb. Returns ranked enhancement opportunities, each backed by real call-site citations. Use when asked to find API improvement or enhancement opportunities for a module, library, or package, to spot missing affordances, or to understand how a module is actually used by its callers. Pass --in to survey only named packages or directories instead of the whole project, and --workflow to have it propose a reusable Workflow script for the survey instead of running it ad hoc.
brewcode:teardown
by kochetkov-ma
Removes brewcode project files (templates, configs, logs).
zju-literature-downloader
by baihe26
Use this skill whenever the user wants to use their own logged-in Zhejiang University Library, WebVPN, 求是学术搜索, Summon, publisher, or Chrome session to legally search, download, organize, and read academic PDFs and supporting information. Trigger on requests like “用浙大图书馆下载文献”, “WebVPN 下载 PDF”, “自动下载补充材料”, “读取全文和 supporting information”, “批量整理文献到项目文件夹”, or “导入 Zotero 后帮我读全文”.
trigger-setup
by triggerdotdev
Set up Trigger.dev in your project. Use when adding Trigger.dev for the first time, creating trigger.config.ts, or initializing the trigger directory.
accelerate
by wundercorp
Run PyTorch training across GPUs with minimal changes.
simpo
by wundercorp
Reference-free preference alignment, simpler than DPO.
kanban-video-orchestrator
by wundercorp
Plan and run multi-agent video production pipelines.
slime
by wundercorp
RL post-training for LLMs with Megatron and SGLang.
evaluating-llms-harness
by wundercorp
"lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.)."
archify
by wundercorp
Validated interactive HTML diagrams, upstream-maintained.
peft
by wundercorp
Fine-tune large LLMs with LoRA on limited GPU memory.
audiocraft-audio-generation
by wundercorp
"AudioCraft: MusicGen text-to-music, AudioGen text-to-sound."
pytorch-lightning
by wundercorp
Clean training loops with built-in distributed support.
torchtitan
by wundercorp
Pretrain LLMs at scale with PyTorch 4D parallelism.
serving-llms-vllm
by wundercorp
"vLLM: high-throughput LLM serving, OpenAI API, quantization."
saelens
by wundercorp
Train sparse autoencoders to interpret model features.
watchers
by wundercorp
Poll RSS, JSON APIs, and GitHub with watermark dedup.
modal
by wundercorp
Serverless GPU cloud for ML jobs and model APIs.
flash-attention
by wundercorp
Speed up long-sequence transformer training and inference.
book-writing-workspace
by aktsmm
Set up a complete book writing workspace with AI agents, instructions, prompts, and scripts. Use when users want to create a new book/technical writing project with Markdown + Re:VIEW + PDF output workflow. Triggers on "book writing workspace", "technical book project", "執筆ワークスペース", or similar project setup requests.
release
by Automattic
Version management and release processes using Jetpack Changelogger. Use when creating releases, managing changelogs, bumping versions, or preparing patch releases.