Agent skill

Agent Dev Workshop

by hashgraph-online in hashgraph-online/awesome-codex-plugins

交互式 AI Agent 开发工作坊：通过 6 阶段深度协作对话，引导用户完成 Agent 需求分析、架构设计、工具定义、Prompt 与编排设计、代码生成、验证迭代，产出可直接运行的 Agent 项目。

Apache-2.0Auto-check passedAI & LLM Engineering

Install Agent Dev Workshop

skills CLI

$ npx skills add hashgraph-online/awesome-codex-plugins --skill agent-dev-workshop -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install hashgraph-online/awesome-codex-plugins agent-dev-workshop --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/Colin4k1024/tsp/skills/agent-dev-workshop .claude/skills/agent-dev-workshop && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "agent-dev-workshop" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Colin4k1024/tsp/skills/agent-dev-workshop into .claude/skills/agent-dev-workshop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-dev-workshop", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Colin4k1024/tsp/skills/agent-dev-workshop

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add hashgraph-online/awesome-codex-plugins --skill agent-dev-workshop -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install hashgraph-online/awesome-codex-plugins agent-dev-workshop --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/Colin4k1024/tsp/skills/agent-dev-workshop .agents/skills/agent-dev-workshop && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "agent-dev-workshop" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Colin4k1024/tsp/skills/agent-dev-workshop into .agents/skills/agent-dev-workshop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-dev-workshop", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add hashgraph-online/awesome-codex-plugins --skill agent-dev-workshop -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install hashgraph-online/awesome-codex-plugins agent-dev-workshop --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/Colin4k1024/tsp/skills/agent-dev-workshop .cursor/skills/agent-dev-workshop && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "agent-dev-workshop" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Colin4k1024/tsp/skills/agent-dev-workshop into .cursor/skills/agent-dev-workshop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-dev-workshop", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/hashgraph-online/awesome-codex-plugins.git --path plugins/Colin4k1024/tsp/skills/agent-dev-workshop

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add hashgraph-online/awesome-codex-plugins --skill agent-dev-workshop -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install hashgraph-online/awesome-codex-plugins agent-dev-workshop --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/Colin4k1024/tsp/skills/agent-dev-workshop .gemini/skills/agent-dev-workshop && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "agent-dev-workshop" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Colin4k1024/tsp/skills/agent-dev-workshop into .gemini/skills/agent-dev-workshop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-dev-workshop", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install hashgraph-online/awesome-codex-plugins agent-dev-workshop

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add hashgraph-online/awesome-codex-plugins --skill agent-dev-workshop -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/Colin4k1024/tsp/skills/agent-dev-workshop .github/skills/agent-dev-workshop && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "agent-dev-workshop" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Colin4k1024/tsp/skills/agent-dev-workshop into .github/skills/agent-dev-workshop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-dev-workshop", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add hashgraph-online/awesome-codex-plugins --skill agent-dev-workshop -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install hashgraph-online/awesome-codex-plugins agent-dev-workshop --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/Colin4k1024/tsp/skills/agent-dev-workshop .opencode/skills/agent-dev-workshop && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "agent-dev-workshop" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Colin4k1024/tsp/skills/agent-dev-workshop into .opencode/skills/agent-dev-workshop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-dev-workshop", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: agent-dev-workshop
GitHub stars: 1.2k
Token cost: ~1.8k tokens
SKILL.md length: 586 words
Files: 9 (incl. references)
Skills in repo: 736
Repo updated: Oct 6, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Works in 6 steps: 需求发现（Discovery） → 架构设计（Architecture） → 工具与能力定义（Tools & Capabilities） → …
Tasks that involve Building AI agents
SKILL.md covers 何时激活, 三种运行模式, 严格约束 and 工作方式, plus 11 more sections
Calls pip, go and npm

What it does

Agent Dev Workshop is an agent skill from hashgraph-online/awesome-codex-plugins. 交互式 AI Agent 开发工作坊：通过 6 阶段深度协作对话，引导用户完成 Agent 需求分析、架构设计、工具定义、Prompt 与编排设计、代码生成、验证迭代，产出可直接运行的 Agent 项目。框架无关设计优先，支持 LangChain / EINO / AutoGen / AgentScope / CrewAI 等 ADK 框架。

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `agents/openai.yaml`, `references/phase1-discovery.md` and `references/phase2-architecture.md`).

It sits in AI & LLM Engineering, covering Building AI agents. It works with LangChain and CrewAI. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.

When your agent uses it

Tasks that involve Building AI agents

Example prompts

“/agent-dev-workshop”

Requirements

Python 3
Node.js

Workflow steps

6 steps, taken from the step headings in SKILL.md.

需求发现（Discovery）
架构设计（Architecture）
工具与能力定义（Tools & Capabilities）
Prompt 与编排设计（Prompt & Orchestration）
代码生成（Code Generation）
验证与迭代（Verification & Iteration）

What it can do on your machine

Read from SKILL.md and the folder at commit 16b4156. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- pip
- go
- npm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip and npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Dev Workshop loads about 1.8k tokens when it runs, and up to ~9.5k if it reads all its reference files. Until then it costs about 48 tokens; SKILL.md has 586 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~48
When it runs · the whole SKILL.md, loaded when a task matches: ~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~9.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from hashgraph-online/awesome-codex-plugins at commit 16b4156, republished under its Apache-2.0 licence (© hashgraph-online). 586 words, ~1,822 tokens.

Download SKILL.mdSave it as .claude/skills/agent-dev-workshop/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.

name: agent-dev-workshop
description: 交互式 AI Agent 开发工作坊：通过 6 阶段深度协作对话，引导用户完成 Agent 需求分析、架构设计、工具定义、Prompt 与编排设计、代码生成、验证迭代，产出可直接运行的 Agent 项目。框架无关设计优先，支持 LangChain / EINO / AutoGen / AgentScope / CrewAI 等 ADK 框架。
origin: ECC

Agent Dev Workshop

交互式 AI Agent 开发工作坊。用户通过深度协作式对话，逐阶段完成 Agent 设计并生成可直接运行的项目代码。

何时激活

用户说"开发 agent"、"创建 agent"、"构建 agent"、"agent 开发"
用户要基于 EINO / LangChain / AutoGen / AgentScope / CrewAI 创建 Agent 应用
用户要将已有 Agent 迁移到另一个框架
用户说"agent dev"、"build agent"、"create agent"、"develop agent"
/agent-dev 命令入口

三种运行模式

默认模式（深度协作）

完整 6 阶段交互流程。每个阶段结束必须用户确认后才推进到下一阶段，每个工具/组件逐一交互确认。

快速模式（`--quick`）

用户给一句话需求 → 自动执行 Phase 1-4（推断 Agent 类型、匹配架构模式、生成默认工具和 Prompt）→ 仅在 Phase 5 代码生成后做一次整体确认 → Phase 6 验证。适合有经验用户或原型快速验证。

快速模式约束：

自动推断时，选择最常见的默认值（如：单 Agent 默认 ReAct，多角色默认 Multi-Agent Conversation）
框架选择依据用户指定语言自动匹配（Python → LangChain，Go → EINO，未指定 → LangChain）
生成后必须完整展示项目结构和核心文件内容，等待用户确认

导入模式（`--import`）

用户指定已有 Agent 代码路径：

分析现有代码：识别框架、Agent 类型、工具列表、Prompt、编排逻辑
生成 agent-spec.md（逆向提取）— 展示给用户确认
用户确认：确认提取结果 + 选择目标框架
跳转 Phase 5：用目标框架重新生成代码
Phase 6：对比验证原 Agent 行为是否保留

导入模式约束：

必须列出代码分析中的不确定项，让用户确认
原 Agent 的所有工具必须在新框架中保留等效实现
生成 diff 摘要：原框架 vs 目标框架的关键差异

严格约束

每个阶段必须用户确认后才能进入下一阶段。严禁静默推进。
每个阶段开始前，先读取 references/phase{N}-*.md 获取该阶段详细指引。
遇到需求冲突或不明确的约束，立即暂停并提问，不自行推测。
每个阶段的核心产出必须立即写入磁盘，不允许仅停留在对话上下文中。
代码生成阶段（Phase 5），必须读取 adk-framework-adapters 对应框架的 reference 文件后再生成代码。
框架适配 reference 文件标注了 verified_date，若距今超过 90 天，应提醒用户 API 可能已变化。

工作方式

阶段驱动：按 Phase 1 → 6 顺序推进，每阶段有明确的输入、活动、产出和确认点。
追踪表：在 Phase 1 结束后创建 {output_dir}/tracking.md，每个阶段完成后更新状态。
引用 reference：每个阶段开始前，读取对应 references/phase{N}-*.md 获取详细引导。
立即落盘：每个阶段的产出文件在完成后立即写入 {output_dir}/，并展示给用户确认。
跨 skill 调用：Phase 2 调用 agent-patterns-catalog 匹配架构模式；Phase 5 调用 adk-framework-adapters 加载框架模板。

阶段概览

Phase	名称	核心活动	产出文件	Reference
1	需求发现	业务场景、Agent 类型、框架、约束	`agent-spec.md`	`references/phase1-discovery.md`
2	架构设计	架构模式匹配、组件拓扑、数据流	`agent-architecture.md`	`references/phase2-architecture.md`
3	工具与能力	工具定义、Memory 策略、RAG pipeline	`agent-tools.md`	`references/phase3-tools.md`
4	Prompt 与编排	System Prompt、编排逻辑、路由策略	`agent-prompts.md` + `agent-orchestration.md`	`references/phase4-prompts.md`
5	代码生成	框架代码、项目结构、配置、脚本	完整项目目录	`references/phase5-codegen.md`
6	验证迭代	依赖安装、测试、Smoke Test、迭代	验证报告	`references/phase6-verification.md`

输出目录规范

{agent-name}/                    # 项目根目录（Phase 5 生成）
├── README.md
├── pyproject.toml / go.mod / package.json
├── .env.example
├── src/
│   ├── agent.py / agent.go / agent.ts
│   ├── tools/
│   ├── prompts/
│   ├── memory/
│   └── orchestrator/            # multi-agent 时
├── tests/
├── configs/
└── scripts/
    └── run.sh

docs/agent-dev/                  # 设计文档目录（Phase 1-4 生成）
├── tracking.md                  # 进度追踪表
├── agent-spec.md                # Phase 1
├── agent-architecture.md        # Phase 2
├── agent-tools.md               # Phase 3
├── agent-prompts.md             # Phase 4
└── agent-orchestration.md       # Phase 4

Phase 1: 需求发现（Discovery）

交互方式: 深度对话 + 结构化提问

活动:

用户描述 Agent 要解决的业务场景
引导确认：目标用户、核心能力、输入/输出、成功标准
确定 Agent 类型（提供选项）：
- ReAct Agent（推理+行动循环）
- Multi-Agent 协作（多角色对话/编排）
- RAG Agent（检索增强生成）
- Tool-Use Agent（工具调用链）
- Workflow Agent（固定流程编排）
- Autonomous Agent（自主规划+执行）
确定目标框架偏好（或根据场景推荐）
确认约束：部署环境、编程语言、LLM provider、外部依赖
导入模式入口：如果用户有已有 Agent 代码，先分析代码再提取 spec

产出: agent-spec.md

Agent 名称、描述、类型
核心能力列表
输入/输出契约
目标框架 + 编程语言
LLM provider + 模型
约束与外部依赖
成功标准

确认点: 用户审批 agent-spec.md 后进入 Phase 2

Phase 2: 架构设计（Architecture）

交互方式: 展示架构方案 + Mermaid 图 + 用户确认/调整

活动:

读取 agent-patterns-catalog 中对应 Agent 类型的参考架构
设计组件拓扑：Agent Core → Memory → Tools → LLM → Orchestrator
Multi-Agent 场景：角色拆分、通信拓扑（星型 / 链式 / 网状 / 层级）
RAG 场景：检索策略、向量存储选型、chunk 策略
生成 Mermaid 架构图
列出关键设计决策及其理由

产出: agent-architecture.md

架构模式名称与简述
组件拓扑图（Mermaid）
组件职责表
数据流描述
关键设计决策
Multi-Agent 场景的角色定义（如适用）

确认点: 架构确认后进入 Phase 3

Show full SKILL.md (274 more words)Show less

Phase 3: 工具与能力定义（Tools & Capabilities）

交互方式: 逐个工具交互确认

活动:

根据 agent-spec 和 architecture 列出所有需要的工具（Tool）
每个工具逐一确认：
- 名称（name）
- 描述（description）
- 输入参数 schema（JSON Schema 格式）
- 输出 schema
- 实现策略（API 调用 / 数据库查询 / 文件操作 / 自定义逻辑）
定义 Memory 策略：
- 类型（conversation_buffer / entity / summary / vector）
- 存储后端（in-memory / Redis / SQLite / 向量数据库）
- 窗口大小或 token 限制
RAG pipeline 定义（如适用）：
- 数据源（文件 / API / 数据库）
- Embedding 模型
- 向量存储（FAISS / Chroma / Milvus / Weaviate）
- 检索策略（similarity / MMR / hybrid）
- Chunk 策略（大小 / 重叠 / 分隔符）

产出: agent-tools.md

工具清单表（name / description / input / output / strategy）
Memory 配置
RAG pipeline 定义（如适用）
外部依赖清单

确认点: 全部工具定义确认后进入 Phase 4

Phase 4: Prompt 与编排设计（Prompt & Orchestration）

交互方式: 展示 prompt 草稿 + 用户迭代修改

活动:

设计 System Prompt：
- 角色定义
- 行为约束与规则
- 输出格式要求
- 可用工具说明
设计编排逻辑：
- 单 Agent：执行循环（max_iterations / 终止条件）
- Multi-Agent：状态机 / DAG / 对话轮次 / 投票机制
- Workflow：阶段定义 / 条件分支 / 并行节点
Multi-Agent 特有：
- 每个角色的 prompt
- 路由策略（round-robin / LLM-based / rule-based）
- 终止条件
错误处理与兜底策略
Few-shot examples（如需要）

产出:

agent-prompts.md：所有 prompt 全文
agent-orchestration.md：编排逻辑 + Mermaid 流程图 + 路由规则 + 错误处理

确认点: Prompt 和编排逻辑确认后进入 Phase 5

Phase 5: 代码生成（Code Generation）

交互方式: 生成代码 + 逐文件审查确认

活动:

读取 adk-framework-adapters 中目标框架的 reference 文件
检查 reference 文件的 verified_date，若超 90 天则提醒用户
根据 Phase 1-4 的全部设计文档 + 框架模板生成完整项目：
- 项目结构（目录、依赖文件）
- Agent 核心代码
- 所有工具实现
- Prompt 模板文件
- Memory 配置
- 编排逻辑代码
- 配置文件（.env.example / config.yaml）
- 启动脚本（scripts/run.sh）
- README.md（含安装运行说明）
- 基础测试文件
每个核心代码文件生成后展示给用户确认
需要用户提供的敏感配置（API Key 等）统一放在 .env.example 中标注

产出: 完整可运行项目目录

确认点: 项目结构和核心文件确认后进入 Phase 6

Phase 6: 验证与迭代（Verification & Iteration）

交互方式: 自动验证 + 反馈循环

活动:

依赖安装验证（pip install / go mod tidy / npm install）
语法检查 / 类型检查
单元测试执行
Agent 行为 Smoke Test：模拟一轮对话，验证 Agent 能正确调用工具并返回结果
如有问题：定位 → 修复 → 重跑
展示验证结果给用户
用户手动测试后的反馈 → 迭代调整 prompt / 工具 / 编排逻辑

产出: 验证通过的可运行项目 + 验证报告

确认点: 用户确认项目可用

追踪表模板

Phase 1 完成后创建 {output_dir}/tracking.md：

markdown

# Agent Dev Tracking

| Phase | 状态 | 产出文件 | 确认时间 |
|-------|------|----------|----------|
| 1. 需求发现 | ✅ 已确认 | agent-spec.md | {timestamp} |
| 2. 架构设计 | ⏳ 进行中 | — | — |
| 3. 工具定义 | 🔲 未开始 | — | — |
| 4. Prompt 与编排 | 🔲 未开始 | — | — |
| 5. 代码生成 | 🔲 未开始 | — | — |
| 6. 验证迭代 | 🔲 未开始 | — | — |

## 关键决策记录

| # | 决策 | 原因 | Phase |
|---|------|------|-------|
| 1 | Agent 类型: {type} | {reason} | 1 |
| 2 | 框架: {framework} | {reason} | 1 |

与其他 Skill 的协作

Skill	调用时机	用途
`agent-patterns-catalog`	Phase 2	匹配最佳 Agent 架构模式
`adk-framework-adapters`	Phase 5	加载框架特定代码模板和惯用模式
`systematic-debugging`	Phase 6	遇到复杂错误时切换到系统化调试
`tdd-workflow`	Phase 5-6	测试先行策略（可选）

默认命令入口

/agent-dev
/agent-dev --quick
/agent-dev --import

Files

SKILL.md and 8 other files (references) in plugins/Colin4k1024/tsp/skills/agent-dev-workshop of hashgraph-online/awesome-codex-plugins.

SKILL.md
agents/openai.yaml
references/phase1-discovery.md
references/phase2-architecture.md
references/phase3-tools.md
references/phase4-prompts.md
references/phase5-codegen.md
references/phase6-verification.md
references/shared.md

Open the folder on GitHubat commit 16b4156

Compare with similar skills

Agent Dev Workshop next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Dev Workshop compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Agent Dev Workshop this skillhashgraph-online/awesome-codex-plugins	1.2k	—	~1.8k	Automated safety check: Pass	Apache-2.0	yesterday
Mem0 Platform SDKmem0ai/mem0	67k	1 repos	~1.9k	Automated safety check: Pass	Apache-2.0	yesterday
Edgeone Makers MigrationTencentEdgeOne/edgeone-makers-tools	1.9k	1 repos	~4.1k	Automated safety check: Pass	MIT	14 days ago
Omnigent Framework Detectionomnigent-ai/omnigent	11k	—	~610	Automated safety check: Pass	Apache-2.0	today
Crewai Multi AgentOrchestra-Research/AI-Research-SKILLs	13k	2 repos	~3.4k	Automated safety check: Pass	MIT	3 mo ago
Agent Governancegithub/awesome-copilot	40k	2 repos	~4.6k	Automated safety check: Pass	MIT	today

Similar skills

Mem0 Platform SDK
mem0ai/mem0
Adds persistent memory to AI apps with the Mem0 Python and TypeScript SDKs: store, search, update and delete user memories, with framework integrations.
67k GitHub starsUsed in 1 repo~1.9k tokens
AI & LLM EngineeringAuto-check passed
Edgeone Makers Migration
TencentEdgeOne/edgeone-makers-tools
Migrate existing AI agent projects (LangChain, LangGraph, OpenAI Agents SDK, Claude Agent SDK, CrewAI) to EdgeOne Makers platform conventions.
1.9k GitHub starsUsed in 1 repo~4.1k tokens
AI & LLM EngineeringAuto-check passed
Omnigent Framework Detection
omnigent-ai/omnigent
Scans Python agent code for framework imports and recommends the matching Omnigent executor type, or says when the framework is not natively supported yet.
11k GitHub stars~610 tokensUpdated today
AI & LLM EngineeringAuto-check passed
Crewai Multi Agent
Orchestra-Research/AI-Research-SKILLs
Multi-agent orchestration framework for autonomous AI collaboration.
13k GitHub starsUsed in 2 repos~3.4k tokens
AI & LLM EngineeringAuto-check passed
Agent Governance
github/awesome-copilot
Official
Patterns and techniques for adding governance, safety, and trust controls to AI agent systems.
40k GitHub starsUsed in 2 repos~4.6k tokens
AI & LLM EngineeringAuto-check passed
Cloudbase Agent
TencentCloudBase/CloudBase-AI-Toolkit
Build and deploy AI agents with CloudBase Agent SDK (TypeScript & Python).
1.1k GitHub starsUsed in 2 repos~476 tokens
AI & LLM EngineeringAuto-check passed

More from hashgraph-online/awesome-codex-plugins

All 736 skills in this repo

Anime Reaction Gif
hashgraph-online/awesome-codex-plugins
Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.
1.2k GitHub stars~922 tokensUpdated yesterday
Auto-check passed
Calibredb
hashgraph-online/awesome-codex-plugins
Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).
1.2k GitHub stars~1k tokensUpdated yesterday
Auto-check passed
Rust API Test Harness
hashgraph-online/awesome-codex-plugins
A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…
1.2k GitHub stars~1.7k tokensUpdated yesterday
Auto-check passed
Art
hashgraph-online/awesome-codex-plugins
Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…
1.2k GitHub stars~2.4k tokensUpdated yesterday
Auto-check passed
Calle
hashgraph-online/awesome-codex-plugins
Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins.
1.2k GitHub stars~2.9k tokensUpdated yesterday
Auto-check passed
Game Balance Economy
hashgraph-online/awesome-codex-plugins
Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.
1.2k GitHub stars~618 tokensUpdated yesterday
Auto-check passed

Works with

Questions about Agent Dev Workshop

What does Agent Dev Workshop do?

交互式 AI Agent 开发工作坊：通过 6 阶段深度协作对话，引导用户完成 Agent 需求分析、架构设计、工具定义、Prompt 与编排设计、代码生成、验证迭代，产出可直接运行的 Agent 项目。. Agent Dev Workshop is an agent skill from hashgraph-online/awesome-codex-plugins.

When should I use Agent Dev Workshop?

Agent Dev Workshop fits situations like: tasks that involve Building AI agents.

How do I install Agent Dev Workshop in Claude Code?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill agent-dev-workshop -a claude-code`. Or copy the skill folder (plugins/Colin4k1024/tsp/skills/agent-dev-workshop in hashgraph-online/awesome-codex-plugins) into .claude/skills/agent-dev-workshop in your project. Claude Code loads it when a task matches its description.

How do I install Agent Dev Workshop in Codex?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill agent-dev-workshop -a codex`. Or copy the skill folder (plugins/Colin4k1024/tsp/skills/agent-dev-workshop in hashgraph-online/awesome-codex-plugins) into .agents/skills/agent-dev-workshop in your project. Codex loads it when a task matches its description.

Can I use Agent Dev Workshop in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hashgraph-online/awesome-codex-plugins --skill agent-dev-workshop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-dev-workshop, .gemini/skills/agent-dev-workshop, .github/skills/agent-dev-workshop and .opencode/skills/agent-dev-workshop in your project.

What does Agent Dev Workshop need to run?

Going by SKILL.md and its folder, Agent Dev Workshop needs the command-line tools its instructions call (pip, go and npm). Our summary lists: Python 3; Node.js.

Does Agent Dev Workshop access the network?

SKILL.md contains no URLs. Its commands use pip and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Agent Dev Workshop safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent Dev Workshop use?

Agent Dev Workshop is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Dev Workshop use?

About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.7k tokens, read only when the agent opens those files.

What are the alternatives to Agent Dev Workshop?

Skills that share tags, products or a category with Agent Dev Workshop: Mem0 Platform SDK (mem0ai/mem0, 67k stars), Edgeone Makers Migration (TencentEdgeOne/edgeone-makers-tools, 1.9k stars), Omnigent Framework Detection (omnigent-ai/omnigent, 11k stars) and Crewai Multi Agent (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Dev Workshop?

hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,232 GitHub stars. The repository holds 736 skills in this directory. The repository was last updated on October 6, 2026.

Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Agent Dev Workshop

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Agent Dev Workshop

何时激活

三种运行模式

默认模式（深度协作）

快速模式（--quick）

导入模式（--import）

严格约束

工作方式

阶段概览

输出目录规范

Phase 1: 需求发现（Discovery）

Phase 2: 架构设计（Architecture）

Phase 3: 工具与能力定义（Tools & Capabilities）

Phase 4: Prompt 与编排设计（Prompt & Orchestration）

Phase 5: 代码生成（Code Generation）

Phase 6: 验证与迭代（Verification & Iteration）

追踪表模板

与其他 Skill 的协作

默认命令入口

Files

Compare with similar skills

Similar skills

More from hashgraph-online/awesome-codex-plugins

Related

Questions about Agent Dev Workshop

快速模式（`--quick`）

导入模式（`--import`）