A router for choosing the right workflow or skill for a software project. It describes paths from an idea to shipped code, including research, prototypes, specifications, tickets, and implementation.

Use it to choose a project flow, turn ideas into written specifications, split work into tickets, or hand a prototype's findings back to the main work.

It reduces the need to remember which workflow to start with and helps separate conversational questions from questions that need a working prototype. It also explains how to organise work across sessions.

ask-matt-zh — Skill for Claude Code by gongyijie85

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add gongyijie85/mattpocock-skills-dsh-zh --skill ask-matt-zh

Clone the repo

git clone --depth 1 https://github.com/gongyijie85/mattpocock-skills-dsh-zh

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gongyijie85/mattpocock-skills-dsh-zh/ask-matt-zh/github.svg)](https://agentmods.dev/skills/gongyijie85/mattpocock-skills-dsh-zh/ask-matt-zh)

Your own site

<a href="https://agentmods.dev/skills/gongyijie85/mattpocock-skills-dsh-zh/ask-matt-zh"><img src="https://agentmods.dev/badge/skills/gongyijie85/mattpocock-skills-dsh-zh/ask-matt-zh/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gongyijie85/mattpocock-skills-dsh-zh/ask-matt-zh"><img src="https://agentmods.dev/badge/skills/gongyijie85/mattpocock-skills-dsh-zh/ask-matt-zh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,328 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00031	$0.03328
Opus 5	$0.00015	$0.01664
Sonnet 5	$0.00006	$0.00666
Haiku 4.5	$0.00003	$0.00333

Measured yesterday against content hash 791c5ae9a45a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ask-matt-zh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ask-matt-zh/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ask Matt

你不可能记住每一个 skill,所以问吧。

一个 flow(流程) 是贯穿各 skill 的一条路径。大多数路径沿着一条 main flow(主流程) 展开,并有两条 on-ramp(入口) 汇入其中。其他一切都是独立的,或者是运行在底层的一层 vocabulary(词汇)。

主流程:idea → ship

这是大多数工作走的路线。你有一个想法,希望把它构建出来。

grill-with-docs — 通过访谈打磨想法。当你在工作目录中工作时,从这里开始:它是有状态的,会把学到的东西保留在 CONTEXT.md 和 ADR 中。(没有工作目录?使用 grill-me — 见 Standalone。两者运行的是同一个 grilling 原语;grill-with-docs 是会留下书面记录的那个,因此只要有仓库可供留下记录,它就是两者中更好的选择。)
分支 — 所有问题都能在对话中解决吗? 如果某个问题需要一个可运行的答案(state、业务逻辑、你必须亲眼看到的 UI),就绕道经过一个 prototype,由 handoff 双向桥接(prototype 住在自己的目录里,这正是 handoff 的用途 — 见 Phase boundaries):
- handoff 出去,然后针对那个文件开启一个新 session,
- prototype 用一次性代码回答这个问题,
- handoff 把你学到的东西带回来,并在原始的 idea 线程中引用它。
分支 — 这是一个 multi-session(多会话)构建吗?
- 是 → to-spec(把线程变成 spec),然后 to-tickets 把它拆成 tracer-bullet tickets,每个 ticket 声明自己的 blocking edges(阻塞边界)。在本地 tracker 上,每个 ticket 是 .scratch/<feature>/issues/ 下的一个文件,手工按 blockers-first(先处理阻塞项)推进;在真正的 tracker 上,这些边变成原生的 blocking links,因此任何 blockers 已完成的 ticket 都可以被领取 — 每个 ticket 启动一次 implement,并在每两个之间 /clear 上下文。每个 ticket 都是自包含的,所以最后一个 ticket 的上下文可以直接丢弃。
- 否 → 就在当前 context window 里运行 implement。
无论哪种方式,implement 都会在内部驱动 tdd 来构建每个 issue — 一次一个 red-green(红绿)切片 — 然后在提交之前,运行 code-review(对 diff 的双轴审查:Standards + Spec)收尾。当你只是想在没有完整 spec 的情况下以 test-first(测试先行)方式构建一个具体行为时,单独使用 tdd;每当你想针对某个固定点审查分支或 PR 时,单独使用 code-review。

Context 卫生

把第 1–3 步保持在一个不间断的 context window 中 — 在 to-tickets 之前不要 compact 或 clear — 这样 grilling、spec 和 tickets 都建立在同一个思考之上。之后每个 implement 都从 ticket 出发、以全新状态开始。

这其中的限制是 smart zone:模型仍能敏锐推理的窗口(在最先进的模型上约为 150k tokens)。如果 session 在 to-tickets 之前逼近这个窗口,不要在退化的状态下硬撑 — 在最近的 phase boundary 处 /compact,然后继续(见 Phase boundaries)。

On-ramps(入口)

一种产生工作的起始情境,随后汇入主流程。

Bug 和请求堆积 → triage。它让 issues 经过 triage 角色流转,产出 agent-ready(agent 可直接处理)的 issues,之后由 implement 接手。

Read the full file on GitHub · 91 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 91 lines · 31 tokens per session scan A 791c5ae9a45a

Subscribe to this mod's changes

ask-matt-zh is a skill published in the GitHub repository gongyijie85/mattpocock-skills-dsh-zh (5 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 3,328 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-11.

Planning Project management agent-skills chinese deepseek-harness dsh dsh-plugin mattpocock

manage-taskboard

Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…

shengsheng90/DSH-taskboard · 88 tokens

dev-team

Simulate a collaborative dev team session where multiple role-based personas (PM, Architect, Developer, QA) respond to the same problem together in one session. Use when designing a feature, reviewing a proposal, or onboarding a new initiative and you want multi-role perspective without switching agents manually.

gongyijie85/dsh-ecc · 60 tokens

ask-matt-zh