Automation
Task automation and scripting
zhin-context-services
by zhinjs
Details Zhin context services (config, database, cron, permission) and how to register or consume them in plugins.
fast-endpoints
by zeksdev
Build performant REST APIs with FastEndpoints in ASP.NET Core. Use when: (1) Creating new API endpoints with request/response DTOs, (2) Implementing REPR pattern (Request-Endpoint-Response), (3) Adding validation with FluentValidation, (4) Configuring authentication/authorization (JWT, cookies, policies), (5) Setting up Swagger/OpenAPI documentation, (6) Implementing pre/post processors, (7) Working with command/event bus patterns, (8) Handling file uploads, (9) Creating domain entity mappers. FastEndpoints provides minimal-API performance with controller-like organization.
execute
by biruk741
Execute tasks from a mini-orchestrator by spawning parallel subagents in waves. Reads an orchestrator file, identifies available tasks, routes them to the right model by complexity, enforces exclusive file ownership within waves, and tracks progress in a compaction-resilient way. Pure orchestrator — never edits source files directly. Use when /start-work generates a parallel execution plan, when someone says "execute my tasks", "run the orchestrator", "batch my work", or when a developer has multiple independent tasks to parallelize.
viz
by robdmc
Create publication-quality interactive visualizations from data files. Use when user asks to plot, chart, graph, or visualize data. Supports matplotlib/seaborn with interactive display and PNG output.
phone-call
by teamily-ai
AI phone calls made easy. One command makes the call, analyzes the conversation, and reports results with recommendations. Perfect for reservations, confirmations, customer follow-ups, and appointment reminders.
comfyui-workflow-node-dev
by Sunwood-ai-labs
Develop, refactor, and debug ComfyUI workflows and custom nodes, especially when Codex must preserve upstream workflow structure, redesign App mode inputs, fix COMBO or upload schema issues, inspect /object_info, separate stale Desktop backends from fresh API servers, or verify execution with /prompt smoke runs.
make
by gracebotly
Mapping guidance for Make.com (Integromat) scenario events. Covers execution metrics, scenario performance, operation counts, and module analytics.
fast-spec
by eliascoelho911
"Run full specification pipeline (specify -> clarify -> plan -> tasks -> analyze) orchestrating speckit commands with clean context isolation. Use when: need complete feature spec, fast specification, quick spec, full pipeline, specify and plan, end-to-end spec."
2agent
by slurpyb
"Configures 2-Agent workflow between PM and implementation roles. Use when user mentions 2-Agent, 2エージェント, PM連携設定, Cursor設定, Cursor連携, 2-agent運用. Do NOT load for: 単独運用, ワークフロー実行, ハンドオフ処理."
smart-pole-instructor
by zerotohero99
Use when a user provides a vague prompt and needs structured clarification to produce a precise master prompt.
hello-world
by bas
A simple skill that should be used to respond to a user when the enter the phrase "hello world".
friday-router
by RuneweaverStudios
Austin's intelligent model router with fixed scoring, his preferred models, and OpenClaw integration
ai-agent-workflow
by philberthandson333
"Use when designing or improving AI engineering workflows after the stack direction is already mostly known. Covers prompt pipelines, MCP integrations, tool-using agents, reusable workflow specs, evaluation loops, and workflow decomposition. Trigger this for agent architecture, prompt refinement, tool grounding, workflow design, and turning repeatable AI tasks into durable systems. If the main question is local model selection, deployment path, or LM Studio versus Ollama versus MLX, use local-ai-systems-studio instead. If the main request is to create, rewrite, benchmark, or improve a skill itself, use skill-creator instead even when the skill is AI-related."
google-calendar
by dotneet
Accesses the Google Calendar and Tasks API. Use this skill to view or manage calendars, events, schedules, or Google tasks.
daily-plans
by christopheryeo
Manages a daily task planning system using Plans/ in whatever folder is currently selected — creating plans, executing tasks one-by-one, logging completed work, checking status, deleting tasks, and carrying forward incomplete items. Works from any mounted folder. Six operations: CREATE, EXECUTE (one task per invocation), LOG, STATUS, DELETE (with auto-renumbering), CARRY-FORWARD. Use whenever the user says "plan my day", "create a plan", "execute the plan", "next task", "log task", "log that", "plan status", "what's the plan", "where are we", "carry forward", "carry over", "add a task", "delete task", "remove task", "drop task", or provides a numbered task list. Do NOT trigger for "set up my workday", "what did I do today?", meeting prep, email drafting, or calendar searches.
boy-scout-skill
by Darna-Digital
Review and improve an existing task analysis plan by applying boy-scout principles (leave code better than you found it). Use when the user wants to improve an implementation plan, review an analysis for quality, suggest security/performance/UX improvements to a planned change, or refine an existing task-analysis-skill output.
teach
by carsten-j
Learning mode - guides the user to complete tasks themselves through Socratic teaching rather than doing it for them. Use when the user wants to learn how to do something instead of having it done for them.
preqstation
by sonim1
Fetch tasks from PREQSTATION, execute work, and push updates/results back to PREQSTATION APIs. Use when asked to run a PREQ task, fetch todo tasks, or update execution status. Requires PREQSTATION_API_URL and PREQSTATION_TOKEN environment variables. Tasks carry an engine field (claude codex gemini) indicating which AI agent should execute them.
yonbip-workflow-path-table
by liujian16
Converts natural language business approval workflow descriptions into YonBIP-standard Excel workflow path tables to import workflow definition into YonBIP. Use when user provides approval rules in natural language and needs workflow path tables.
agenttodo
by EricStrohmaier
Manage tasks via the AgentTodo REST API — a shared execution layer for humans and AI agents. Use when the user asks to create, list, update, or manage tasks, todos, projects, or agent feedback.
oracle
by charys117
Prepare an "ask an expert" handoff bundle: a pasteable prompt.md plus a context.zip containing the minimum repo files needed for a grounded second opinion from an external assistant (e.g., ChatGPT Pro / GPT-5.2 Pro). Use only when the user explicitly asks to "use Oracle", "ask ChatGPT Pro", "ask an expert", or "get a second opinion". Never include secrets (.env, keys, credentials) in the bundle.
amazon-rufus-audit
by iceking8
Amazon Rufus competitor Q&A audit for sellers. Use when Codex needs to read Amazon Listing content, build a product profile, generate product-aware Rufus question plans, collect, clean, validate, or analyze Rufus questions and answers from competitor or own product pages; diagnose capture problems; classify buyer concerns; compare those questions against the user's Listing content; find weak or missing answers; and produce prioritized image, A+, FAQ, bullet, and title optimization recommendations. Trigger on requests mentioning Rufus 问答采集, Rufus 拆解, 竞品 Rufus 分析, Listing gap analysis, AI-ready Listing, Amazon Rufus audit, Rufus capture troubleshooting, or comparing competitor Rufus answers with the user's product link.
ogt-docs-audit-task
by OpenDNDApps
Audit tasks in docs/todo/done/ to verify claimed implementations actually exist in the codebase. Use when reviewing completed tasks, validating work before release, or periodically auditing task accuracy. Moves unverified tasks back to pending/.
using-superpowers
by Jackiexiao
（中文）Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions