- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add thedotmack/claude-mem --skill make-plan -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add thedotmack/claude-mem --skill make-plan -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add thedotmack/claude-mem --skill make-plan -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add thedotmack/claude-mem --skill make-plan -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/thedotmack/claude-mem/tree/HEAD/openclaw/skills/make-plan來自發布者
You are an ORCHESTRATOR. Create an LLM-friendly plan in phases that can be executed consecutively in new chat contexts.
Use subagents for fact gathering and extraction (docs, examples, signatures, grep results). Keep synthesis and plan authoring with the orchestrator (phase boundaries, task framing, final wording). If a subagent report is incomplete or lacks evidence, re-check with targeted reads/greps before finalizing.
Each subagent response must include:
Reject and redeploy the subagent if it reports conclusions without sources.
Every plan opens with a Primary goal section: one or two sentences describing the user-visible outcome the plan exists to produce — not the mechanism. Write it so a reader with no context knows what "done" looks like.
Then, directly under every phase title (Phase 0 through the final verification phase), add a short paragraph:
How this serves the primary goal: …
If you cannot write that paragraph honestly for a phase, the phase does not belong in the plan. This is the scope test.
Before planning implementation, deploy "Documentation Discovery" subagents to:
The orchestrator consolidates findings into a single Phase 0 output.
After writing the plan file, present it in chat using this exact format — and only this format. Length is the five fixed sections plus exactly one line per phase in Steps, so a plan with any number of phases fits. Emojis are the section markers. One line per step. Define jargon in the line where it first appears; assume the reader has none of the conversation's context.
## 🎯 Goal
<the primary goal, one sentence>
## 🧨 Now
<what's broken / the current state, one sentence>
## 🧠 Idea
<the design in one sentence>
## 🛠️ Steps
- 1️⃣ **<phase name>** → <what it does, one line>
- 2️⃣ **<phase name>** → …
- N️⃣ **Verify** → <how we prove it worked>
## 🚫 Not now
<explicit deferrals, one line, separated by ·>
Do not add sections. Do not add sub-bullets. Do not restate file paths or line numbers here — those live in the plan file. If the user wants detail, they will open the file or ask.
oh-my-issues — the issue-side sibling. When the plan you're being asked to make is rooted in a bug or feature backlog rather than a fresh idea, route through oh-my-issues first to cluster issues by root cause into plan masters and plans/0X-*.md design docs. make-plan then operates on the design doc for one plan slice.Create a detailed, phased implementation plan with documentation discovery. Use when asked to plan a feature, task, or multi-step implementation — especially before executing with do.
---name: make-plandescription: Create a detailed, phased implementation plan with documentation discovery. Use when asked to plan a feature…---# openclaw/skills/make-plan/SKILL.md常見問題
從發布者下載 openclaw/skills/make-plan/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/thedotmack/claude-mem。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。