write-planning-doc
Creates structured planning documents for projects and initiatives, breaking down complex work into stages with clear actions and validation points.
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。
菜单
Creates structured planning documents for projects and initiatives, breaking down complex work into stages with clear actions and validation points.
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
Helps users connect and use a service in Rebel when it isn't already in the built-in connector catalog. Acts as an expert advisor — runs the full build-vs-buy check (catalog, MCP Registry, community) before scaffolding a custom MCP server and guiding research, implementation, security review, and contribution.
Guides users through adding new tools or capabilities to an existing connector (MCP server). Handles eligibility, workspace setup, connector research, implementation via Software Engineer workflow, local testing, and PR submission with an extension-specific template.
Capture citable sources (meetings, documents, files, media, web content) as structured files in memory/sources/ with provenance metadata for traceability.
Help users celebrate impactful wins and surface important learnings by analyzing their recent communications and activities.
Guidelines for maintaining single sources of truth and using signposting to connect documentation without duplication
Evaluate a finalised meeting transcript and distribute relevant content to other spaces, deciding per space whether to copy the full transcript, write a sanitised summary, or skip.
| name | write-planning-doc |
| description | Creates structured planning documents for projects and initiatives, breaking down complex work into stages with clear actions and validation points. |
| last_updated | "2025-10-26T00:00:00.000Z" |
| agent_type | main_agent |
| output_shape | {"default_surface":"file_artifact","chat_contract":"decision_brief","artifact_expected":true,"max_chat_words":200,"source_policy":"artifact_sources"} |
This is a guide for writing planning/project management .md files for any type of project or initiative. These are for thinking through & documenting decisions, breaking down complex projects into multiple stages, and tracking progress.
Store planning docs in the relevant space’s memory/planning/ folder (for example personal/memory/planning/, work/[COMPANY-NAME]/solo/memory/planning/, or Chief-of-Staff/memory/planning/ for cross-space/meta planning).
Aim to keep these concise, but emphasise & clearly capture all the decisions, responses, and requirements from the user.
If you're starting the doc from scratch:
date +"%y%m%d" to get the current date for naming the fileSee also: write-help-evergreen-doc for instructions on writing evergreen docs
Planning docs should follow this naming format: yyMMdd[letter]_description_in_normal_case.md
yyMMdd format (e.g., 250526 for 26 May 2025)ab, and so onToC (Table of Contents)250526a_customer_onboarding_workflow.mdUpdate this doc regularly to keep the actions up-to-date. When you change it, make minimal, focused changes, based on new user input.
Don't include a Date section at the top since it's implicit from the filename.
memory/), other planning docs (from this space’s memory/planning/), files, links, stakeholders, or anything else that could provide contextOverall approach:
[ ] and [x] checkboxes to indicate todo/doneUpfront preparatory actions:
Early stages:
After creating the initial planning doc:
At the end of stage (where appropriate):
In later stages:
As final actions:
memory/planning/finished/)Example stages & action (no need to include the words TODO or DONE explicitly, since the [ ] todo-checkboxes capture that):
### Stage: High-level description of this stage
- [ ] This is a top-level action
- [ ] It can have sub-actions that get ticked off
- You can add bulletpoint notes with extra detail/context to help plan & shape future actions
### ✅ This stage has already been completed
- ✅ This action has already been completed
- 📔 You could journal about useful/unexpected discoveries when you update progress on completed tasks
- ❌ This action has failed/been skipped
Add any other important context here, e.g.