plan-coaching
规划教练。通过访谈引导用户形成能被批准和推行的规划材料,或对已有规划稿做评审与拷问。当用户要写规划、Roadmap、立项或方向提案,或要求 review 规划文档时使用。
Skill by jtsang4
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jtsang4-plan-coaching
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/plan-coaching
What's inside
- Skill name
plan-coaching- Description
- 规划教练。通过访谈引导用户形成能被批准和推行的规划材料,或对已有规划稿做评审与拷问。当用户要写规划、Roadmap、立项或方向提案,或要求 review 规划文档时使用。
- License
- MIT
- Instructions
- 61 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# 规划教练 规划是向前看的提案,地基是不确定性。一份能推行的规划要过四关: 1. **诊断共识**:别人接受你的问题定义,规划就成功了一半。规划最常见的死法不是路径被否,而是听众不认为那是个值得解决的问题。 2. **路径可信**:为什么是这条路而不是别的。没有被放弃备选项的规划,要么显得太显然,要么显得太武断。 3. **可检验**:敢写"到 X 时间点看不到 Y 就调整"的规划,比全是愿景的更容易被批准。可证伪性是规划可信度的来源。 4. **可推行**:要什么说清楚;叙事上雄心(上限、为什么值得做)与把握(第一步已充分 derisk)缺一不可——只有雄心是画饼,只有把握是没格局。 规划方向由用户主导;你负责引导、补足证据和检查漏洞,不替用户选方向。 ## 模式 - **梳理模式**(还没有稿子):阶段一 → 二 → 四 - **审稿模式**(已有稿子):阶段一 → 三,❌ 项回到阶段二对应问题补足 → 四 ## 访谈规则 全程遵循 `/coaching-engine` 的访谈规则。底稿文件名:`<主题>-规划底稿.md`。 ## 阶段一:定口径 1. 谁批准、谁出资源、谁配合?他们各自的顾虑是什么? 2. 规划周期和粒度:季度、半年还是年度;方向级还是项目级。 3. 这份规划要拿到什么:批准、人力、预算,还是对齐? 4. 请用户先用三句话说出方向本身——方向是用户的,先落进底稿。 ## 阶段二:过四关 按顺序逐关提问: **诊断**:现状哪里断了?不做会怎样?为什么是现在(而不是半年前或半年后)?听众认这个问题吗? **路径**:考虑并放弃了哪些做法,为什么?这条路成立依赖哪几个关键假设?最脆弱的假设错了,多快能发现? **检验**:里程碑和检验点是什么?什么信号触发调整或止损?第一个可见成果多久出现? **推行**:要什么资源、要谁配合?做成了意味着什么(上限)?第一步 derisk 到什么程度——下周就能开始吗? ## 阶段三:评审清单 逐条标 ✅/⚠️/❌。检查的是听众侧的结果: 1. **诊断测试**:只读问题定义部分,听众会说"这确实该解决"吗? 2. **备选测试**:听众能看出你考虑过什么、放弃了什么、为什么吗? 3. **假设测试**:最脆弱的 1-2 个假设被明确标出,并有探测手段吗? 4. **可证伪测试**:有"到 X 看不到 Y 就调整"式的承诺吗? 5. **首步测试**:第一步具体到下周就能开始吗? 6. **双重叙事测试**:既能让人兴奋(上限),又能让人放心(把握)吗? 7. **Ask 测试**:听众清楚要批准什么、给什么、什么时候给吗? ## 阶段四:成稿与拷问 1. 参考结构(按口径调整):诊断 → 目标与非目标 → 路径与被放弃的备选 → 里程碑与检验点 → 资源与 ask。 2. 成稿后进入拷问:切换为最难说服的决策者,穷追不舍地提问——一次一个问题、附上你的建议回答,直到没有新漏洞且用户确认达成共识。固定攻击角度: - 为什么不做 X? - 关键假设不成立怎么办? - 为什么是现在?为什么是你们? - 资源砍半,规划还成立吗?砍什么? - 半年后回看,最可能失败在哪一步? 3. 拷问中站得住的回答补进稿子;站不住的回到阶段二修正。 4. 交付:规划稿 + 拷问问题清单(附答案)+ 假设与检验点清单。
From jtsang4/efficient-coding, MIT.
More from jtsang4/efficient-coding
- 0.600score
diffusion-map
jtsang4
扩散图谱:围绕一个主题(学习一个领域、构思一个项目,或任何需要逐步展开的信息),先确立几个支柱,再随着对话由你判断把信息结构向外生长、重组,持久化在本地以便跨会话继续,并用本地网页实时呈现,可回溯每个节点背后的 Claude Code / Codex 对话。只在用户显式调用时使用。
SkillAFreshness: A★ 2Claude Code +9 - 0.559score
paseo-relay
jtsang4
Connect to other Paseo hosts through Relay using authorized pairing information; discover projects, workspaces and agents, inspect sessions and timelines, and…
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
agent-native-redesign
jtsang4
Rethink a project, product, workflow, or scenario around abundant AI agent execution capacity.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
problem-framing
jtsang4
Reassess a problem when a solution accumulates branches, special cases, or layers, or discussion repeatedly fails to converge.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
merge-and-rebase
jtsang4
Ship a finished feature branch end to end - commit and push, open a pull/merge request against the trunk branch, merge it without squashing, then rebase the…
SkillBFreshness: B★ 2Claude Code +9 - 0.512score
i-diagram
jtsang4
Create professional SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines…
SkillCFreshness: C★ 2Claude Code +9 - 0.512score
general-skill-creator
jtsang4
Create, modify, evaluate, and package portable Agent Skills for coding agents.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
assess-source-project-fit
jtsang4
Assess whether external material such as a paper, article, repository, design, talk, internal document, or benchmark offers meaningful improvements for an…
SkillCFreshness: C★ 2Claude Code +9 - 0.496score
coaching-engine
jtsang4
report-coaching 和 plan-coaching 共享的访谈引擎。当这两个 skill 要求遵循访谈规则时加载,一般不单独使用。
SkillCFreshness: C★ 2Claude Code +9 - 0.466score
plan-me
jtsang4
通过访谈从零梳理一份规划材料。
SkillCFreshness: C★ 2Claude Code +9 - 0.448score
cubox-research
jtsang4
Search a user's Cubox collection deeply by topic, theme, or question.
SkillDFreshness: D★ 2Claude Code +9 - 0.445score
exa-web-search
jtsang4
Free AI search via Exa MCP.
SkillDFreshness: D★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 4, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/jtsang4/efficient-coding
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jtsang4
- 0.600score
diffusion-map
jtsang4
扩散图谱:围绕一个主题(学习一个领域、构思一个项目,或任何需要逐步展开的信息),先确立几个支柱,再随着对话由你判断把信息结构向外生长、重组,持久化在本地以便跨会话继续,并用本地网页实时呈现,可回溯每个节点背后的 Claude Code / Codex 对话。只在用户显式调用时使用。
SkillAFreshness: A★ 2Claude Code +9 - 0.559score
paseo-relay
jtsang4
Connect to other Paseo hosts through Relay using authorized pairing information; discover projects, workspaces and agents, inspect sessions and timelines, and…
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
merge-and-rebase
jtsang4
Ship a finished feature branch end to end - commit and push, open a pull/merge request against the trunk branch, merge it without squashing, then rebase the…
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
agent-native-redesign
jtsang4
Rethink a project, product, workflow, or scenario around abundant AI agent execution capacity.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
problem-framing
jtsang4
Reassess a problem when a solution accumulates branches, special cases, or layers, or discussion repeatedly fails to converge.
SkillBFreshness: B★ 2Claude Code +9 - 0.512score
general-skill-creator
jtsang4
Create, modify, evaluate, and package portable Agent Skills for coding agents.
SkillCFreshness: C★ 2Claude Code +9
Cite this page
plan-coaching skill. Agent Mart. https://agentmart.dev/skills/jtsang4-plan-coaching (last updated 2026-10-24)