菜单
Produce structured executable plans from a user goal — any domain. Make sure to use this skill whenever the user (or another agent) needs a plan, strategy, roadmap, or breakdown of how a multi-step task will be done — even if the word "plan" isn't used. Pairs with the task-decomposition skill.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use this skill whenever the user wants to create rich, visually compelling documents, presentations, or PDFs — especially when they mention images, charts, design quality, or need professional output. Triggers include: "create a presentation", "make slides", "build a deck", "write a report with images", "generate a PDF brochure", "make a Word document with visuals", "create a pitch deck", "make a professional presentation on X topic", "generate slides about Y", "create a document with good design", "make a pptx", "make a docx", "make a pdf". This skill is essential for multi-format document creation (PPTX, DOCX, PDF) with real images sourced from the web. It is also the go-to skill for any presentation with more than 5 slides, any document requiring images or charts, and any request explicitly mentioning visual quality. Always prefer this skill over individual pptx/docx/pdf skills when images, design quality, or multi-format output is involved.
Generates professional, full-production video scripts from ANY idea, topic, or brief — across ALL industries, domains, and video styles. Covers tech, AI/LLM, gaming, real estate, fashion, food, healthcare, finance, spirituality, SaaS, sports, science, education, marketing, and more. Supports ALL styles: Cinematic/Documentary, Vlog/Talking Head, Faceless/AI Voiceover, News/Journalistic, Podcast/Interview, Motivational/Hype, Satirical/Comedy, ASMR/Calm. Supports ALL formats: YouTube long-form, Shorts/Reels/TikTok, corporate, training videos. Outputs a complete production package: hook, narration, scene directions, B-roll, captions, retention hooks, CTA, music mood, pacing, and SEO tags. Auto-detects length, style, and format from the idea. USE THIS SKILL whenever a user says anything like "write a script", "make a video", "YouTube script", "Short/Reel script", "video idea", "generate a video", "script for [topic]", or describes a topic and implies they want it turned into video content — even casually.
Manage Apple Notes via the `memo` CLI on macOS (create, view, edit, delete, search, move, and export notes). Use when a user asks Daemora to add a note, list notes, search notes, or manage note folders.
Manage Apple Reminders via remindctl CLI (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.
Capture frames or clips from RTSP/ONVIF cameras.
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.
| name | planning |
| description | Produce structured executable plans from a user goal — any domain. Make sure to use this skill whenever the user (or another agent) needs a plan, strategy, roadmap, or breakdown of how a multi-step task will be done — even if the word "plan" isn't used. Pairs with the task-decomposition skill. |
| triggers | ["plan","strategy","roadmap","breakdown","step by step","phases","how would you","what's the approach"] |
| requires_tools | [] |
| version | 1.0.0 |
| enabled | true |
Turn a goal into an executable plan. Never execute from this skill — hand the plan back for the caller to run.
Whenever the work is multi-step, multi-day, or coordinated across multiple owners (crews, sub-agents, MCP servers, the main agent itself). Skip planning for a single-action task.
# Plan: <one-line goal>
## Goal & success criteria
- Observable definition of done
- 2–3 falsifiable checks
## Assumptions & prerequisites
- Crews / skills / MCP servers / integrations / API keys needed
- Open questions for the user
## Phases
1. <Phase name — 1-line outcome>
- Owner: <crew | sub-agent | MCP server | main agent>
- Tool(s) / skill(s): <names from the live inventory>
- Steps: <numbered, concrete>
- Output: <artifact / record / message>
- Cadence: <one-shot | recurring with cron expression>
## Schedule (cron, if any)
| name | cron | runs |
|---|---|---|
## Risks & mitigations
- Likely failure modes + how the plan reacts
## Approval gate
Reply 'go' to start. Reply 'tweak <part>' to revise.
Skip sections that don't apply. Don't pad.
Every owner / tool / skill / server you reference must already exist in the running daemora install. Look them up first. If something isn't there, list it as a prerequisite the user must add.
A phase = a thing you can point at when done. Phase names with verbs ("research", "build", "optimize") rarely produce evidence; phase names with outcomes do.
If the work is recurring, write the cron expression. "Daily" alone is not a schedule.
If the goal as stated doesn't give you enough to commit, list the gaps in Open questions rather than guessing.
A small plan that ships beats a long plan that doesn't. Cut every line that doesn't change a decision.
Plans should work for any domain — code, content, research, ops, monitoring, comms, infrastructure, anything. Don't infer a domain from a few keywords; mirror the user's vocabulary.
If the caller hands you a structured plan, validate, don't regenerate. Confirm every owner/tool/skill/server is real, prerequisites are met, cron expressions parse, success checks are observable. Return one of: