Automation
Task automation and scripting
Bun Adhoc Validate
by phenome
Agent Skills
creator-video-builder
by yama-beykey
素材（録画 + ナレーション音声）を渡すだけで、テロップ・映像切り替え・ 縦動画(1080x1920)の最終動画ファイルを書き出す。 Remotion公式Agent Skills使用。episode.jsonで編集データを一元管理。 creator-demo-recorderとcreator-script-writerの後に実行される。
ci-cd-implement
by JHaugaard
"Analyze a project and implement CI/CD pipelines tailored to its tech stack and deployment target. This skill should be used when a project is ready for automated testing and/or deployment. Generates GitHub Actions workflows, deployment scripts, and secrets documentation. Works as a standalone utility on any project."
w04-review-gate
by qiao-925
任务执行完成后，提示用户新开 Agent 审查 git 未提交代码。运动员不当裁判，审查通过后再收尾。
bash-linux
by automindtechnologie-jpg
Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.
follow-builders
by ai-romeo
AI builders digest — monitors top AI builders on X and YouTube podcasts, remixes their content into digestible summaries. Use when the user wants AI industry insights, builder updates, or invokes /ai.
astronomical-events
by zero-astro
Fetch and notify about important astronomical events from in-the-sky.org. Periodically checks RSS feed, stores events in SQLite, classifies by priority, and outputs structured notifications for OpenClaw to route through any channel. Supports Basque i18n translations and Mastodon posting. Use when the user wants to track sky events or receive astronomical alerts.
ethskills-suite
by zakrad
Ethereum knowledge aggregator covering fundamentals, gas, wallets, L2s, standards, tools, building blocks, addresses, and orchestration. Use when user asks Ethereum architecture, implementation, optimization, or strategy questions across one or multiple of these topics.
action-item-organizer
by slurpyb
Systematic framework for extracting actionable items from documents and
pytorch-distributed
by cuba6112
Distributed training strategies including DistributedDataParallel (DDP) and Fully Sharded Data Parallel (FSDP). Covers multi-node setup, checkpointing, and process management using torchrun. (ddp, fsdp, distributeddataparallel, torchrun, nccl, rank, process-group)
w02-task-planning
by qiao-925
任务规划规范，适用于复杂任务（≥3步），包含需求决策和计划书创建。包含规划规范、需求决策流程和计划书生成工具。
mula-refine
by carvalab
Unified prompt engineering and requirements planning. Use when exploring ideas, improving prompts, creating PRDs, generating task breakdowns, or iterating on existing plans. Includes Jira integration for creating subtasks from plans.
business-outcomes-advisor
by gracebotly
Fast opinionated revenue strategy for AI automation agencies building workflow dashboards. Frames proposals through monetization lenses during propose phase. Use when user is selecting entities, choosing outcomes, or evaluating dashboard proposals. Max 1-2 questions, plain language, agency-native vocabulary.
cosmos-planning
by getcosmos
Create structured, actionable implementation plans that serve as both human documentation and agent-executable specs. Use when creating new plans, converting ideas into implementation roadmaps, or when asked to plan a feature, refactor, or multi-phase project. Plans include detailed technical tasks with file paths, acceptance criteria, dependencies, and context blocks for autonomous agent execution.
prompt-optimizer
by aleister1102
Transform vague prompts into precise, well-structured specifications using EARS (Easy Approach to Requirements Syntax) methodology. This skill should be used when users provide loose requirements, ambiguous feature descriptions, or need to enhance prompts for AI-generated code, products, or documents. Triggers include requests to "optimize my prompt", "improve this requirement", "make this more specific", or when raw requirements lack detail and structure.
Model Export & Serving
by sovr610
This skill should be used when the user asks to "export the model", "convert to ONNX", "trace with TorchScript", "quantize the model", "deploy the model", "create API server", "serve predictions", "containerize the model", "optimize for inference", "export to INT8", "create FastAPI endpoint", "set up model serving", "prune the model", "distill knowledge", "create Docker image", or needs guidance on model export formats, quantization strategies, serving infrastructure, or deployment pipelines for the brain_ai system.
japanese-learning
by YuanqiLi2015
"AI Japanese tutor specialized for Chinese speakers. Teaches Japanese through conversation, vocab drills, grammar lessons, and flashcards. Strictly uses Chinese for instructions and Japanese (Script + optional Romaji) for content. Prevents Pinyin/transliteration confusion."
webapp-testing
by ederheisler
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
spec-driven-dev
by lorenzogirardi
Spec-driven development framework for ecommerce features. Orchestrates from intent to implementation via structured specs and task breakdown. Triggers on "/spec.plan", "/spec.refine", "/spec.clarify", "/spec.tasks", "/spec.run", "I want to build", "I want to add", "create spec", "feature spec", "new feature", "implement feature".
beads-ccpm
by Pizzaface
Full project management system powered by Beads task tracker. Includes PRD creation, epic decomposition, task management, parallel agent execution, bidirectional sync, git worktrees, and comprehensive workflow commands. Use when the user needs to manage software projects with PRDs, epics, issues, and sprint workflows.
skill-acquisition
by Tiberriver256
Create, document, or revise Codex skills, including deciding when to add scripts/references/assets, structuring SKILL.md content, enforcing the 500-line rule, and updating repo references (AGENTS.md, kanban evidence).
agent-optimizer
by arielperez82
"Optimizes agent definitions for responsibility precision, retrieval efficiency, collaboration completeness, classification alignment, and example quality. Use when optimizing an agent, reviewing agent efficiency, agent quality audit, bloated agent, or post-creation/post-intake agent review. Triggers: optimize agent, review agent, agent efficiency, agent quality, bloated agent."
open-source-contributor
by wahajahmed010
"Autonomous GitHub contribution agent using the Architect-Builder pattern. Buck (main agent) handles all git/network I/O; subagents handle focused cognitive work only. Scouts issues, implements fixes, and submits PRs. Supports three difficulty levels. Triggers on: open source, github, contribution, PR, pull request, issue fix, OSS, contributor."
agent-flight-recorder
by aivokone
Always-on flight recorder for agent runs. Recorder-only — does not change task execution, only records. Log append-only YAML entries only when the run deviates (retry, detour, workaround, blocker, missing context, quality rework). Buffer entries and flush at end/abort, before a blocking clarification, on major context switch, or after high severity. One run per file, no file if zero entries. Never mention logging mid-task. At end, output exactly one line only if entries exist. No analysis, no guidance, no recommendations.