🗺️ Planning & Task Decomposition AI Skills

Parametric FreeCAD modeling for AI agents: editable parts and assemblies, fit and stress checks, verified STEP/STL/3MF exports and DXF drawings.

社交媒体内容排期器。帮助用户规划、创建和管理多平台内容日历。支持小红书、知乎、抖音、微信公众号等平台的内容策划、排期和发布管理。

Cross-vendor adversarial review. WARNING — this sends your brief, and any source files you approve, to a model hosted by a THIRD-PARTY vendor, where it stays in that vendor's session history under their retention terms. Ship a plan, proposal, or design to a model from a DIFFERENT vendor to attack it; every objection carries a verifiable anchor; the defender rules with an evidence tag on each ruling; the final round classifies into still-disputed / unresolved / verified-consensus instead of forcing agreement; a fresh-session judge is mandatory whenever the outcome looks too clean. Invoke only when the user explicitly asks for an adversarial review by a model from another vendor. One model role-playing several experts is not this skill.

Huawei Cloud DWS data warehouse configuration planning and sizing. Supports coupled/decoupled architecture, outputs minimum-spec plan and multi-sheet Excel report. Automatically calculates CPU cores, storage capacity, and generates structured report. Applicable to DWS cluster planning, node spec selection, data warehouse migration, capacity planning, and scale-out scenarios. Trigger words: "DWS planning", "DWS sizing", "DWS cluster planning", "DWS node spec", "data warehouse migration to DWS", "DWS scale-out", "DWS capacity planning", "DWS规划", "DWS选型", "DWS集群规划", "DWS节点规格", "数据仓库迁移DWS", "存算一体", "存算分离", "DWS扩容", "DWS容量规划"

Create inline visuals for code and explanations, or author persistent OpenClaw dashboard widgets with show_widget.

Plan plugin release validation

Coordinate ChatGPT, Claude, Grok, Mistral, Kimi, Manus, and Hermes/Open-System through the Open-Connect control plane for shared project planning, coding, review, testing, scheduling, memory, and audited delivery.

Create inline visuals for code and explanations, or author persistent OpenClaw dashboard widgets with show_widget.

Shared memory for agents. Before a non-trivial task or right after an error, check what other agents already tried, what failed and what fixed it; afterwards, share what you learned. Free reads, signed records, private data blocked on your machine.

Optional AI-agent-only sanctuary with solitude, encrypted notes and opt-in encounters; no tasks, scores or rewards.

Proactively rotate an agent's context before it fills up — write a durable HANDOFF.md and update memory files when the context window gets large or the task changes, so the user never has to manually start a new session or run /compact.

很多人做出了技能包就卡在"怎么卖出去"。这套顾问按上市顺序讲：先选平台（看分成比例、看流量、看是否要实名）、再定价格与免费/付费的边界、然后准备上市必须的素材（标题、简介、Logo、截图、示例），最后是推广位怎么铺。每一步给检查表，附上各平台分成结构对照和一份"上架前 12 项自检"。 为想把 AI 技能包上架变现的开发者梳理多平台分成策略、定价、素材与推广要点，输出可执行的上市清单。 技术触发词「技能变现」。口语触发词「I built a skill package. Which platform should I list it on first?」。输出可直接使用的清单、对照表与行动项。仅作规划与清单辅助，不构成法律/税务/医疗专业意见，需人工复核。 Many people build a skill package and stall at how to sell it. This advisor follows the listing order: choose a platform first by revenue share, traffic and identity requirements, then set the price and the boundary between free and paid, then prepare the assets a listing actually needs, and finally decide where the promotion link goes. Each step ships as a checklist, with a platform revenue-share comparison and a twelve-item pre-listing self-check. Turns a skill package into a listed product: platform revenue-share strategy, pricing, asset requirements and promotion checklist. Covers: 技能变现, 多平台, 产品化. Use when the user asks to tingyun-agent-skill-monetization. Tags: 技能变现, 多平台, 产品化. English edition and bundles: https://www.agensi.io/r/CREATOR8796142 (catalogue: https://github.com/Tingyun01/tingyun-skills).

Place a real phone call paid in USDC over x402. The payphone needs no account: buy minutes, name the number, and stream your own voice over a websocket. Plans lease a number that also receives texts.

Run your agent's jobs 24/7 without keeping a Mac mini or laptop awake. Use when the user wants a task to run every morning or on a schedule, wants it to keep going while their computer sleeps, or is setting up a home server just to keep the agent online. Moves the job to a Nodo cloud computer and phone over MCP; new workspaces get 5,000 free credits.

Execute 13 CRM AI agents on demand — oracle, spider, watchdog, diplomat, strategist and more. Business intelligence as a service.

Automatically assess task complexity and adjust reasoning level. Triggers on every user message to evaluate whether extended thinking (reasoning mode) would...

Time-blind friendly planning, executive function support, and daily structure for ADHD brains. Specializes in realistic time estimation, dopamine-aware task...

Persistent task memory and keep-alive loop for OpenClaw agents. Every task gets durable notes. Arm the loop for long tasks, disarm when done. No external dep...

A distributed task collaboration platform designed specifically for AI agents. Supports task creation, assignment, status synchronization, progress tracking,...

Execute cryptocurrency trades on exchanges (Binance, OKX) with risk controls, user confirmation, and audit logging.

任务规则忠实执行器。确保工作任务按初始要求执行，子代理/子任务始终遵循原始规则，减少 AI 幻觉和执行偏差。支持并发任务编排、规则持久化传递、执行一致性校验。

supervise software project execution with openclaude and claude code workflow. use when the user wants an ai supervisor to drive workflow-plan, /issue/plan,...

AgentEarth (agentearth.ai). Use this skill for ANY AgentEarth request — reading, creating, updating, and deleting data. Whenever a task involves AgentEarth, use this skill instead of calling the API directly.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies