路由技能:不知道该用哪个技能/流程时先问这个。把非开发人员用大白话提出的需求,映射到对应的技能流程(改编自 mattpocock/skills 的 ask-matt 路由)。Router: maps a plain-language request to the right skill flow.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add xiehuan123/coding-coach --skill ask-matt --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Ask Matt?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/xiehuan123-ask-matt)More formats (shields.io, HTML) on the badges page.
---
name: ask-matt
description: 路由技能:不知道该用哪个技能/流程时先问这个。把非开发人员用大白话提出的需求,映射到对应的技能流程(改编自 mattpocock/skills 的 ask-matt 路由)。Router: maps a plain-language request to the right skill flow.
---
# 该用哪个流程?(Ask Coach)
用户大多用大白话描述需求,不熟悉技能名。收到请求后先按下面的地图判断该走哪个流程,再调用对应技能。**对用户的所有沟通都用中文大白话,出现技术名词时用一句话解释。**
## 主流程:从想法到做出来
大部分工作走这条主线,按顺序判断:
1. **想法还很模糊?** → `grill-me`(一轮轮追问澄清:要做什么、给谁用、怎样算成功)。先问清楚再动手是铁律。
2. **想先看看/试试靠不靠谱?** → `prototype`(做一个一次性的可运行原型,让用户先看到、玩到)。
3. **需要把需求正式写下来?** → `to-spec`(把对话整理成需求规格文档)。
4. **事情比较大,需要拆步骤?** → `to-tickets`(拆成可一步步完成的小任务,标注依赖)。
5. **开始动手做?** → `implement`(按规格实现;内部走 `tdd` 小步测试;完成用 `code-review` 评审后提交)。
## 岔路:遇到问题 / 别的诉求
- **东西坏了 / 报错 / 很慢 / 行为不对** → `diagnosing-bugs`(先建立能复现问题的反馈循环,再系统排查修复)。
- **缺信息,答案在别人脑子里** → `to-questionnaire`(写一份问卷给别人填);或者先用 `grill-me` 把用户自己的意图问清楚。
- **要查证资料、收集事实** → `research`(派后台子代理查一手资料,产出带引用的报告)。
- **想学会一个东西** → `teach`(在当前目录系统化教学,多轮可累积)。
- **要交接给另一个 AI 或同事** → `handoff`(生成交接文档)。
- **用户没听懂 / 让我重讲** → `wait-what`(用大白话重讲一遍)。
- **术语混乱,同一个词有多个意思** → `domain-modeling`(当场厘清并记入术语表)。
## 贯穿底层
- `grilling` — 追问引擎,`grill-me` 的底层;一般不需要单独调用。
- `codebase-design` — 设计模块形状时的「深模块」词汇,其他技能会引用它。
- `tdd` — 测试优先的小步开发循环,`implement` 内部使用。
## 铁律
- **先问清楚,再动手。** 模糊的需求先 `grill-me`,不要替用户脑补需求。
- 用户可见的文字用中文、大白话;技术名词第一次出现给一句解释。
- 每完成一步,用大白话告诉用户:这一步做了什么、为什么、下一步是什么、用户怎么验证。
- 不要让用户接触底层复杂度:技能内部的流程由你执行,用户只需要做决定和验收。
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.