Dsh Plugin Dev

开发 DeepSeek Harness (DSH) 插件的标准与权威参考：编写/修改/审查/调试 DSH/Cordis 插件、服务、事件、插件配置、模型工具、LLM 适配器、三种角色拆分、打包安装、workspace 包、cordis.yml 组合时使用；提到 DSH 插件、Cordis、plugin、服务、事件、工具、适配器即触发。 The authoritative standard for developing DeepSeek Harness (DSH) plugins — create, modify, review or debug DSH/Cordis plugins, services, events, config, model tools, LLM adapters, three-role capabilities, packaging, and cordis.yml composition.

16 stars 3 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add zimodzh/dsh-plugin-dev-skills --skill dsh-plugin-dev

Manual install

git clone --depth 1 https://github.com/zimodzh/dsh-plugin-dev-skills.git /tmp/dsh-plugin-dev-skills
mkdir -p ~/.claude/skills
cp -r /tmp/dsh-plugin-dev-skills/. ~/.claude/skills/dsh-plugin-dev

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 开发 DSH 插件标准

本技能是开发 DeepSeek Harness（DSH）插件的唯一标准：它把 DSH 官方文档中分散在教程、参考手册与生成目录里的约定，收敛为可执行的工作流、硬规则与检查清单。DSH 的一切都是插件——模型适配器、工具注册表、会话日志乃至 agent loop 本身——因此按本技能行事，就是在按 DSH 自己的架构方式扩展它。

## 适用范围

- 仓库内、文件式的 DSH 插件开发：编写插件包、注册 cordis.yml 行、patch overlay、开发工具、接模型、打包安装。
- DSH monorepo 内的 workspace 包开发（packages/<group>/<pkg>）也属本技能（references/workspace-package.md）。
- 本技能**不**覆盖：会话内动态插件（cordis_define/cordis_run 流）与 agent preset 组合编辑——这两类由各部署的专项技能或官方工具覆盖。

## 硬规则（任何场景都必须遵守）

1. **接口以生成参考为准。** 服务名、公开方法、事件签名、ctx 键均以仓库自动生成的子系统页面与 TypeScript 接口为准；不要凭服务名、示例或旧代码推断完整 API，也不要维护另一份静态清单。
2. **所有贡献都是副作用。** 通过 ctx 做的一切注册（事件监听、工具、适配器、ctx.effect）在插件卸载时自动撤销；不要在模块作用域创建进程级/页面级副作用；不返回 disposer 的第三方订阅要主动查清清理机制。
3. **waterfall 监听器必须调用 next()。** 不调用 next() 即有意短路下游（用于拦截/网关），不是可选项。
4. **失败要响亮。** apply 抛异常则进程终止；配置校验失败则明确报错；schema 应表达自身完备的约束，不要在运行时悄悄吞掉错误。
5. **必需依赖用 inject 声明，可选依赖用 ctx.get() 判空。** 不要用 inject 规避 undefined 检查；也不要直接访问未声明注入的 ctx.xxx——未声明的服务经服务解析器求值可能得到 undefined。
6. **配置一律 Schemastery。** 导出 interface Config 与同名 Schema，默认值写在 schema 里；不导出普通对象充当 Config；凡不同部署可能改值的参数都必须进配置。
7. **工具 execute 返回规范 JSON 值，不返回内容块。** 面向人类的文本放 output.render；部署策略/钩子不要内建进工具体。
8. **模型可见即已记录。** 新增任何模型可见输入，都要落在会话日志可重建的机制里（新增持久事件或经 agent.inject()），并有运行时不变式断言。

Read the full skill on GitHub

Details

Skill name: dsh-plugin-dev
Repository: zimodzh/dsh-plugin-dev-skills
License: MIT
Repo updated: 4 September 2026

FAQ

What does the Dsh Plugin Dev skill do?

How do I install the Dsh Plugin Dev skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add zimodzh/dsh-plugin-dev-skills --skill dsh-plugin-dev. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Dsh Plugin Dev popular?

It lives in zimodzh/dsh-plugin-dev-skills, which has 16 GitHub stars and 3 forks.

Related skills

Korean Humanizer

dotoricode/korean-humanizer

한국어로 작성된 AI 생성 텍스트에서 "AI 티"가 나는 표현을 걷어내 사람이 쓴 것처럼 자연스럽게 다듬는 skill. 사용자가 "한국어 humanizer", "AI 티 빼줘", "사람처럼 써줘", "자연스럽게 다듬어줘", "번역체 고쳐줘", "한국어 AI 냄새 제거", "humanize Korean", "AI 티 제거" 등을 언급할 때 반드시 사용. 외부(이메일, LinkedIn, 블로그, YouTube 스크립트, 뉴스레터, 마케팅 카피)로 나가는 한국어 AI 생성 텍스트 전반에 사용한다. 의미를 바꾸지 않고 표현만 다듬는 것이 목적. 호출 결과는 `Humanized` 교정문과 `주요 변경 (최대 5개)` 두 섹션의 Markdown 문서로 반환한다. 영어 텍스트, 단순 오탈자 교정, 내부 메모 / 기술 문서 / 법률 문서에는 사용하지 않는다.

AI, LLMs & Agents

AI Spending Judge

chunfeng11221/ai-spending-judge

建立专属 AI 消费助手：首次提供大白话填写模板和示例，了解收入、日常花销、贷款负债与现金，生成个人价格区间和消费规则；以后按档案判断“能买吗、买什么、预算多少”并更新经济状况。适用于安装后建档、消费预算、订阅和升级判断，不用于投资或信贷审批。

AI, LLMs & Agents

Poggioai Msc Claude

PoggioAI/PoggioAI_MSc-claude

pAI/MSc research pipeline: hypothesis to paper in ≤10 steers. Runs persona debate, adversarial lit review, parallel theory+experiment tracks, and editorial quality gates.

AI, LLMs & Agents

Agent Card

tiny-agent-company/agent-card-skill

Manage virtual Visa cards for AI agents with AgentCard. Fund a wallet with Apple Pay or Google Pay, create single-use or multi-use cards, check balances, view credentials, pay for things, shop and check out at merchants like DoorDash, close cards, manage plans, and get support. Use when the user wants to create or manage virtual payment cards for AI agents, fund their AgentCard wallet, pay for online purchases, shop on their behalf, set up agent spending, or configure card billing and limits.

AI, LLMs & AgentsIn 1 list

Agents Md Generator

Eriemon/agents-md-generator

Use when creating, updating, compressing, reviewing, or verifying AGENTS.md and other AI coding-agent rules; when a managed root AGENTS.md is missing, malformed, stale, or version-incompatible; when the user explicitly mentions AGENTS.md, agent rules, or scoped AGENTS.md; when a managed skill README needs a functional illustration set; or when a request about the current workspace, repository, or work folder is a planning request and therefore requires a root AGENTS.md check first.

AI, LLMs & Agents

Inspect

howardpen9/cc-inspect

Show installed Claude Code skills, plugins, hooks, MCP servers, and commands in a browser dashboard

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.