AI

Browse AI and ML workflow skills for model integration, prompt engineering, evaluations, and LLM automation across major IDEs.

This directory brings installable AI Agent skills into one place so you can filter by search, category, topic, and official source, then install them directly into Claude Code, Cursor, Windsurf, and other supported environments.

906 利用可能なスキル

niko-plan

Logo of Texarkanine
Texarkanine

Niko Memory Bank System - Plan Phase - Implementation Planning

0
0
AI

tr-dashboard-autopilot

Logo of macho715
macho715

End-to-end autopilot for TR 이동 대시보드. Use to generate a plan from AGENTS.md, implement in small steps, and run lint/typecheck/test/build with SSOT(option_c.json) guardrails via subagents.

0
0
開発者

class-refactoring

Logo of pekral
pekral

Refactors PHP classes following Laravel best practices and SOLID principles. Ensures code quality, maintains functionality, improves testability, and achieves 100% code coverage. Focuses on single responsibility, DRY principle, and clean code structure.

0
0
開発者

ai-module-dev

Logo of akihiro4321
akihiro4321

FaveFitのAIモジュール(Agent, Function, Workflow)の新規作成・修正・デバッグを行うスキル。server/ai/ 配下のコードを扱うときは必ず使うこと。

0
0
開発者

oris-maintainer

Logo of Colin4k1024
Colin4k1024

Maintain the Oris Rust agent runtime with an issue-driven GitHub workflow. Use when Codex is working in the Oris repository and needs to pick up a GitHub issue, turn the issue into scoped code changes, run Rust validation such as cargo fmt and cargo test, publish the oris-runtime crate to crates.io, close the completed issue, and continue to the next iteration.

0
0
開発者

kb-orchestrator-workflow

Logo of kvcop
kvcop

Orchestrator-first workflow for building and shipping changes via KB Orchestrator (orchestrator/): setup target repo/workdir, run validation jobs with artifacts + safety, then run structured code review and apply fixes (requesting-code-review/receiving-code-review), and verify web UI behavior via Playwright MCP. Use when the user asks “через оркестратор”, wants repeatable stages + audit trail (commands/prompt), or needs phone/VPN-accessible web demo checks.

0
0
開発者

sub-agent-decompose-worker-review

Logo of bagrinsergiu
bagrinsergiu

Describes the sub-agent pipeline: task-decomposer breaks a task into subtasks, task-worker implements them, work-reviewer checks the result; on issues feedback goes back to the worker. Use when orchestrating multi-step work with task-decomposer, task-worker, and work-reviewer agents, or when the user asks how these agents work together.

0
0
開発者

workflow-to-skill

Logo of PHMbench
PHMbench

将用户的手工SOP/工作流抽取为可复用的Agent Skill规格与SKILL.md草案。适用于“把这个流程封装成skill/把步骤做成skill/从手工步骤生成SOP+分支+质量门禁+技能文件/元prompt做成skill”等请求。Use when the user describes a manual workflow and wants to turn it into a reusable Skill.

0
0
開発者

archunit-enforcement

Logo of ctimmerman-prog
ctimmerman-prog

OpenCode-first AI configuration template — canonical skills, commands, and agents for all AI tools

0
0
開発者

curate

Logo of ductai199x
ductai199x

agentic-data-curation for detecting AI-generated imagery

0
0
開発者

set-reminder

Logo of Will-Barnard-WB
Will-Barnard-WB

Multi-modal WhatsApp AI assistant that turns voice notes, images, links, and text into structured knowledge articles using a Claude agent.

0
0
開発者

flowai-skill-manage-github-tickets

Logo of korchasa
korchasa

FoxCode — Firefox sidebar for Claude Code: real-time chat, browser automation, page context injection

0
0
開発者