mattpocock-skills-zh-CN is a Simplified Chinese localization of a collection of reusable instructions for coding agents. Chinese-speaking developers use the translated skills to support engineering workflows while keeping their original commands, paths, identifiers, and behavior. The catalogue contains the localized skills, instructions, and plugin components.
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.
npx skills add vinvcn/mattpocock-skills-zh-CN --skill retrogit clone --depth 1 https://github.com/vinvcn/mattpocock-skills-zh-CNWrote 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.
[](https://agentmods.dev/skills/vinvcn/mattpocock-skills-zh-cn/retro)<a href="https://agentmods.dev/skills/vinvcn/mattpocock-skills-zh-cn/retro"><img src="https://agentmods.dev/badge/skills/vinvcn/mattpocock-skills-zh-cn/retro/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.
<a href="https://agentmods.dev/skills/vinvcn/mattpocock-skills-zh-cn/retro"><img src="https://agentmods.dev/badge/skills/vinvcn/mattpocock-skills-zh-cn/retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00009 | $0.00991 |
| Opus 5.5 | $0.00004 | $0.00396 |
| Sonnet 5.5 | $0.00002 | $0.00198 |
| Haiku 4.5 | $0.00001 | $0.00099 |
Grade A, and why
retro 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 19d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用户要求做一次 retrospective。你要针对 coding agent 的 environment 提出改进建议,以改善未来的运行结果。
步骤
-
调用 Skill 工具并指定
writing-for-agents,获取写作风格指南。 -
阅读用户指定 session 的 primary sources。这可能意味着在本机搜索 session logs。如果用户没有指定 session,默认使用当前 session。
-
在以下类别中寻找改进候选项。
- Navigation:agent 找到正确 files 有多容易?files 之间是否存在隐藏依赖?navigation pointer 能否让定位更容易?当 agent 花了很长时间才找到某段信息时使用。
- Automated checks:是否有 automated checks 可以捕获 agent 犯的错误?例如 linting、typing、tests 或 filesystem linters?先阅读 repo 自己的检查命令(
package.json/build-tool 中的lint/checkscripts 以及 CI workflow),这样,如果某个检查已经存在但没有接入流程或悄悄失效,真正的发现就是这个问题,而不是重新发明一套检查。若 repo 完全没有 guardrail(没有 pre-commit hook,也没有运行 lint/typecheck/test command 的 CI job),这本身就是一项发现:未纳入 lint 的 repo 是长期存在的改进缺口,而不是理所当然的默认状态。当 agent 犯了本来可以被 automated check 捕获的错误,或 repo 完全没有 guardrail 时使用。 - Coding standards:是否应该给 reviewer agent 一条新规则来执行?是否应该删除或澄清现有规则?先对违规分类:mechanical 违规(固定的语法模式、被禁用的 API、import 形式、文件位置规则)必须交给 deterministic check 处理;根据 repo 使用的语言和现有 guardrail,选择成本最低的方式:在 repo 自己的 linter 中添加自定义规则、新增 pre-commit hook,或新增 CI job。默认优先构建检查,而不是编写规则。
CODING_STANDARDS.md只用于真正的 judgement calls(跨文件一致性、"matches the surrounding style",以及任何 guardrail 都无法替代的判断)。当 reviewer agent 没有发现一个错误时使用。 - Global AGENTS.md:是否有 steering instructions 应该移到 coding standards 或 automated checks?当 repo 或用户 global scope 中的 AGENTS.md 特别庞大时使用。
- Tool economy:agent 是否进行了可以简化的昂贵 tool calls?是否有特别消耗 tokens 的自定义 tooling(CLI、MCP 等)?当 agent 进行昂贵 tool call 时使用。
- No-ops:steering files 中是否有不改变 agent 行为的 instructions?当 steering files 庞大且难以维护时使用。
- Information access:是否有机会让 agent 获得更多信息?例如把 dev server logs tee 出来,或提供对 third-party services 的 read-only access。当关键的信息对 agent 不可用时使用。
- 按严重程度顺序向用户呈现这些候选项。
参考
Implementation 与 Review
记住,所有工作都经过两个阶段:implementation 和 review。implementation agent 承受最大的 context pressure,负责探索、编写代码和调试失败。
review agent 承受最小的 context pressure:它收到的是 diff,因此不需要探索。它通常也不需要编写代码或调试。
因此,review agent 应负责施加 coding standards,而不是 implementation agent。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 19d ago Changed c84f93dae389
- 1mo ago First seen · 45 lines · 9 tokens per session scan A 4397f82ad292
retro is a skill published in the GitHub repository vinvcn/mattpocock-skills-zh-CN (5,357 stars, last pushed 8d ago), licensed MIT. It adds 9 tokens to every session and 991 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-22.
Other skills, from other repositories
claude-handoff
A handoff tool that prepares a summary of the current conversation for another coding agent and starts that agent in the background.
wayfinder
A planning method for large or unclear work that maps the decisions needed between the current situation and a defined destination. It records the map and decision tickets in an issue tracker.
codebase-design
A design vocabulary and set of principles for organizing software modules, meaning pieces of code with an interface and an implementation. It focuses on small interfaces that hide substantial behavior, clear points for changing behavior, and code that is easier to test.
setup-matt-pocock-skills
A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.
triage
A structured issue-triage process that moves issues and, where configured, pull requests through classification and status steps. Triage means deciding what a report is, whether more information is needed, and who should handle it.
setup-ts-deep-modules
A setup for TypeScript packages that hides their implementation behind files at the package root. Dependency-cruiser checks that outside code uses these entry points, prevents dependency cycles, and keeps internal folders private.