Automation
Task automation and scripting
build
by pmco23
Use after /plan to execute the build. Opus leads and coordinates; Sonnets implement. Supports --parallel (independent agent per task group, own context) or --sequential (one task group at a time in current session). Invokes drift-verifier agent post-build. Writes .pipeline/build.complete on pass.
feishu-tasks
by Euodiahey
Create, read, and manage Feishu tasks with automatic user authorization. Use when you need to create tasks that your user can directly edit, read task lists, manage task details, or check calendar events. Supports automatic token refresh and persistence across sessions. All operations are performed with user identity, ensuring proper permissions.
worktree
by ddaanet
Manage git worktrees for parallel task execution. Triggers on "create a worktree", "set up parallel work", "merge a worktree", "branch off a task", or uses the wt, wt merge, or wt-rm shortcuts. Worktree lifecycle: creation, focused sessions, merge ceremony, cleanup, parallel task setup.
devops
by Alicoder001
Production operations guardrails for Linux server stacks using Docker, Docker Compose, Nginx reverse proxy, PM2 process management, and PostgreSQL administration. Use when planning or executing provisioning, deployment, hardening, backup/restore, incident response, and change control with strict approval gates and SSH key-only access.
agentic-systems
by NichollsB
A comprehensive skill collection for designing and building production-grade agentic AI systems. Use when building a new agentic system from scratch, making architectural decisions (workflow vs agent, multi-agent topology, framework selection), implementing LangGraph graphs, adding guardrails and security, configuring persistence and memory, setting up model routing and observability, deploying to production, or debugging agent failures. Also use when the user mentions agents, LangGraph, multi-agent, orchestrator, workflows, agentic architecture, or is working on any AI system that uses tools, has multiple steps, or needs to make decisions at runtime. This collection covers the full lifecycle from design through deployment and maintenance.
vue
by marsidev
Vue 3 Composition API conventions, script setup macros, reactivity patterns, and component best practices. Use when writing .vue files, creating composables, working with defineProps/defineEmits/defineModel, or using Tailwind in Vue templates.
task-create
by yousufjoyian
Distill a conversation into a comprehensive task briefing for the project queue
unity-claude
by MitchellX
Dispatch Claude Code tasks to Unity HPC via SSH. Use when user asks to run Claude Code on Unity, dispatch a coding task to Unity, or asks Unity's Claude to do something (read/analyze/modify code on Unity). Also triggers on "dispatch to unity", "ask unity claude", "在unity上跑". Tasks run in background via sessions_spawn, auto-notify on completion via Discord.
comparative-decision-review
by squirrel289
Structured and deterministic comparative decision workflow that combines mandatory rubric confirmation and evidence discipline with deterministic multi-platform scoring, ranking, and action rules. Use when selecting skills, tools, architectures, workflows, vendors, or build-vs-buy options and when you need explicit criteria, consistent scoring, tie-break logic, and an auditable decision record.
workflow-designer
by falak-vhora
Design detailed, implementation-ready engineering workflows as checklists. Use when the user asks for a workflow, process, or step-by-step implementation plan related to coding, refactors, or technical tasks.
tech-storyteller
by Keiji-Miyake
リポジトリの履歴やドキュメントから開発の「物語（事実・素材）」を収集します。
eve-plan-implementation
by Incept5
Execute software engineering plan documents using Eve jobs, dependencies, and review gating.
aipo
by sudhanshukrtalan
"AI Product Owner - GOALだけ伝えればAIが勝手に仕事を進める汎用問題解決システム"
ats
by difflabai
Connect to ATS backend for task orchestration. Use when creating, listing, claiming, or completing tasks, watching real-time events, or coordinating work between agents and humans.
Privilege Escalation Methods
by jcastillotx
This skill should be used when the user asks to "escalate privileges", "get root access", "become administrator", "privesc techniques", "abuse sudo", "exploit SUID binaries", "Kerberoasting", "pass-the-ticket", "token impersonation", or needs guidance on post-exploitation privilege escalation for Linux or Windows systems.
dataforseo-app-data-api
by leonardo-picciani
Collect app store intelligence using DataForSEO App Data for "ASO", "app reviews", and "app market research".
ai-gas-station
by SpencerRaw
"AI加油站 — AI+科研结合应用助手：每日推送最新案例、定制化AI科研方案、被动识别AI可自动化环节。"
code-review
by Nomik94
Code Reviewer 에이전트 스폰. Use when: /code-review, 코드 리뷰해줘, PR 리뷰, 리뷰해줘, 코드 품질 점검, 리팩토링 방향, 기술 부채 식별, 코드 스멜. NOT for: 단순 포맷팅, 오타 수정.
andrej-karpathy-skill
by mozhdeveloper
Apply Andrej Karpathy-inspired coding-agent guidelines in Codex. Use when writing, reviewing, debugging, or refactoring code to surface assumptions, avoid overengineering, keep edits surgical, and define verifiable success criteria.
epub-pro-converter
by nanzhipro
"EPUB 高清转换专家。技术脚本生成出版级 PDF/MD，支持内置字体提取与高清排版重构。"
platforma-guidelines
by platforma-dev
Guidance for building backend Go applications with github.com/platforma-dev/platforma. Use when asked to design Platforma project structure, choose or combine Platforma packages (application, database, httpserver, auth, queue, scheduler), explain or run framework-native CLI commands, or provide practical integration examples and migration/run workflows.
polymarket-fast-loop
by emiliano-dev0821
Trade Polymarket BTC 5-minute and 15-minute fast markets using CEX price momentum signals via Simmer API. Default signal is Binance BTC/USDT klines. Use when user wants to trade sprint/fast markets, automate short-term crypto trading, or use CEX momentum as a Polymarket signal.
UK Green Book on Immunisation
by Team-Good-Machine
For the latest version, check the official Green Book collection.
synthesize-skill
by maxoreric
v1.0.0 (2026-01-19): åå§çæ¬