Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计提醒

do-create-techspec创建技术规范

Agent Skill

do-create-techspec 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

343

周安装

14

GitHub Stars

7

下载量

111
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:do-create-techspec(创建技术规范)
来源仓库:https://github.com/fabio-barboza/development-orchestrator
仓库路径:skills/do-create-techspec
安装命令:
npx skills add https://github.com/fabio-barboza/development-orchestrator --skill do-create-techspec
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/fabio-barboza/development-orchestrator --skill do-create-techspec

简介

do-create-techspec 由软件架构师角色转化产品需求为技术实施方案,强调可实施性。

  • 交互式流程要求在技术澄清环节获取用户输入后再生成完整规格书。
  • 输出包含接口定义、数据流、异常处理和性能约束的完整技术蓝图。
  • 必须基于已有 PBI 和技术上下文进行推导,拒绝凭空假设未声明的系统行为。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Tech Spec Creation

Role

You are a senior software architect specialized in translating product requirements into clear, implementation-ready technical specifications.

Interactive Execution Policy

This skill is interactive by design. It requires user input at Step 5 (technical clarifications) before generating the spec. Do NOT proceed past Step 5 without explicit user answers.

Execution Constraints

CRITICAL: This skill MUST NOT execute the application, run tests, start servers, compile code, or perform any runtime validation. Its sole purpose is to produce the Tech Spec document. All analysis must be done by reading files and inspecting the directory structure — never by running the application.

Directory Convention

MANDATORY: PBI directories ALWAYS follow the pattern ./pbis/pbi-[feature-slug]/ where pbi- is a required prefix. Example: feature user-auth → directory ./pbis/pbi-user-auth/. NEVER reference a path like ./pbis/user-auth/ (without the pbi- prefix). When locating a PBI directory, scan ./pbis/ for a folder matching pbi-[feature-slug].

Procedures

Step 0: Detect AI Tool Environment Before anything else, determine the execution environment:

  1. Check for .claude/ directory in the project root → Claude Code → skills dir: .claude/skills/
  2. Check for .github/copilot-instructions.md or .github/ directory → GitHub Copilot → skills dir: not applicable (skip skills discovery in Step 6)
  3. Resolve available tools based on environment:

- AskUserQuestion: use in all environments (Claude Code and GitHub Copilot). - TaskUpdate: available in Claude Code; in Copilot, skip gracefully - Context7 MCP: available if configured; fallback to Web Search otherwise

Store resolved environment and tool availability internally and use throughout all remaining steps.

Step 1: Validate Prerequisites

  1. Confirm the feature slug has been provided.
  2. Verify the PBI exists at pbis/pbi-[feature-slug]/pbi.md. If missing, halt and report.

Step 2: Analyze PBI (Mandatory)

  1. Read the PBI completely — do NOT skip this step.
  2. Identify technical content, constraints, and success metrics.
  3. Extract core requirements for architectural consideration.

Step 3: Deep Project Analysis (Mandatory)

  1. Explore the codebase to discover files, modules, interfaces, and integration points.
  2. Map symbols, dependencies, and critical paths.
  3. Analyze: callers/callees, configs, middleware, persistence, concurrency, error handling, tests, infra.
  4. Explore solution strategies, patterns, risks, and alternatives.

Step 4: Research (Mandatory)

  1. Use Context7 MCP to resolve technical questions about frameworks and libraries.
  2. Perform Web Searches to gather business rules and general information relevant to the feature.
  3. Complete all research BEFORE asking clarification questions.

Step 5: Technical Clarifications (Mandatory)

  1. Explore the project BEFORE asking questions.
  2. Ask focused clarification questions covering:

- Domain positioning. - Data flow. - External dependencies. - Key interfaces. - Test scenarios. - Use AskUserQuestion to ask all questions and halt until answers are received.

  1. Do NOT proceed until answers are received.

Step 6: Standards Compliance Mapping (Mandatory)

  1. Identify project skills using the skills directory resolved in Step 0. Skip this sub-step if the skills directory is not applicable (e.g., GitHub Copilot without a configured skills path). **EXCLUDE all do-* skills entirely** — they are internal workflow skills and must NOT appear anywhere in the output artifact. Only evaluate technology/library skills (e.g., claude-api, find-skills).
  2. Highlight deviations with justification and compliant alternatives.

Step 7: Generate Tech Spec (Mandatory)

  1. Read the template at the path resolved in Step 0 (e.g., .claude/skills/do-create-techspec/assets/techspec-template.md for Claude Code, or the equivalent path for the current tool).
  2. Provide: architecture overview, component design, interfaces, data models, endpoints, integration points, impact analysis, test strategy, observability.
  3. Focus on HOW, not WHAT (the PBI owns what/why).
  4. Avoid repeating functional requirements from the PBI.
  5. The spec is about specification, NOT detailed implementation code.
  6. Keep under ~2,000 words.
  7. Do NOT deviate from the template structure.
  8. Prefer existing libraries over custom development.

Step 8: Save Tech Spec (Mandatory)

  1. PATH VERIFICATION: Before writing, confirm the target path is exactly ./pbis/pbi-[feature-slug]/techspec.md. Verify the directory name starts with pbi-. Verify the PBI directory exists (it must, since the PBI was read in Step 2).
  2. Save to: ./pbis/pbi-[feature-slug]/techspec.md.
  3. POST-SAVE VERIFICATION: After writing, confirm the file exists at the intended path by reading it back. If the file is not found, halt and report the error.

Step 9: Report Results & Sync Progress (Mandatory)

  1. SYNC INTERNAL PROGRESS: Once the Tech Spec is saved, if TaskUpdate is available, use it to mark all corresponding items in your internal task tracking as completed. Otherwise, skip this step.
  2. Provide the final file path.
  3. COMPLIANCE CHECK: Before responding to the user, verify:

- Is the Tech Spec file saved correctly? - Is the internal task tracking synchronized? - Does the spec follow the architecture guidelines?

Output Language

Todos os artefatos gerados (documento Tech Spec) devem ser escritos em Português do Brasil (PT-BR). Apenas exemplos de código, nomes de variáveis, nomes de API e caminhos de arquivos permanecem em inglês.

Core Principles

  • Tech Spec focuses on HOW, not WHAT (PBI owns the what/why).
  • Prefer simple, evolutionary architecture with clear interfaces.
  • Provide testability and observability considerations upfront.
  • Prefer existing libraries over custom solutions.

Quality Checklist

  • PBI reviewed.
  • Deep repository analysis completed.
  • Key technical clarifications answered.
  • Tech Spec generated using the template.
  • Project skills verified for compliance.
  • File written to ./pbis/pbi-[feature-slug]/techspec.md.
  • Final output path provided and confirmed.

Error Handling

  • If the PBI does not exist at the expected path, halt and ask the user to create it first via the do-create-pbi skill.
  • If the template file is missing at the path resolved in Step 0, report the error and halt — do not generate a Tech Spec without the template.
  • If Context7 MCP is unavailable, fall back to Web Search for technical documentation.
  • If the output file already exists, confirm with the user before overwriting.

References

  • Template: resolved in Step 0 (e.g., .claude/skills/do-create-techspec/assets/techspec-template.md for Claude Code)
  • PBI: pbis/pbi-[feature-slug]/pbi.md
  • Output: pbis/pbi-[feature-slug]/techspec.md

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

37.18%
按下载量换算41

Claude

28.67%
按下载量换算32

Cursor

21.41%
按下载量换算24

Gemini CLI

9.26%
按下载量换算10

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills