Gospec

Go 后端 SDLC 全流程中文规范。覆盖 Bounded Context 切分、Kratos 风格分层（cmd/server/service/biz/data/model）、API 设计、数据模型（MySQL / Redis / ClickHouse / InfluxDB）、测试、CI/CD、日志指标追踪 SLO、认证密钥安全、部署与事故、数据库 migration、PRD/RFC/ADR/HLD 文档。框架中性——Web 框架可选 Kratos / gin / Hertz / chi / echo，规范只约束分层和依赖方向。写或审查 Go 代码时按需加载。Go backend SDLC spec — framework-neutral, load on demand for coding/design/testing/ops/docs.

7 stars 2 forksDatabases

Install

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

npx skills add singchia/gospec --skill gospec

Manual install

git clone --depth 1 https://github.com/singchia/gospec.git /tmp/gospec
mkdir -p ~/.claude/skills
cp -r /tmp/gospec/. ~/.claude/skills/gospec

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

From the SKILL.md

# gospec

## 如何使用本 Skill

本 Skill 采用**渐进式披露**：详细规范按 SDLC 阶段拆分在 `spec/` 目录，**按需加载，不要一次性读完**。

1. **第一步**：根据用户当前任务，读 `spec/spec.md` 中的"任务路由表"，找到该任务对应的必读文件
2. **第二步**：只读路由表指定的 1-3 个文件，不要顺序读全部
3. **第三步**：实施 + 对照文件末尾的"自查清单"

## 首次在新项目中激活时

如果检测到当前是首次在某个项目中使用本 skill，**主动检查项目根目录是否有 `AGENTS.md`**：

- **有** → 直接按上面的工作流推进
- **没有** → 提示用户："要不要从 `docs/templates/project-agents-template.md` 创建一份项目根 `AGENTS.md`？这样 Cursor / Cline / Codex / Gemini CLI / Copilot 等其他 agent 打开本项目时也能识别 gospec 规范。" 用户同意后用 Read + Write 把模板复制到项目根。

这样无论用户是通过 `npx skills add singchia/gospec`（标准安装，不会自动放 AGENTS.md）还是 `bash <(curl .../install.sh)`（会自动放），最终都能让所有 agent 看到本项目用了 gospec。

## 技术栈（示例，非强制）

规范**只约束分层和依赖方向**，不锁框架。下表是参考选型，项目可按团队约定替换。

| 领域 | 参考选型 | 常见替换 |
|------|---------|---------|
| 语言 | Go 1.21+ | — |
| Web 框架 | Kratos v2 | gin / Hertz / chi / echo / 原生 net/http |
| ORM | gorm.io/gorm | sqlx / ent / sqlc |
| API 协议 | Protobuf v3 + gRPC + HTTP/REST | OpenAPI + REST |
| 认证 | JWT (golang-jwt/jwt v5) | Auth0 / Keycloak / Casdoor / 自研 |
| 日志 | log/slog（Go 1.21+ 推荐） | zap |
| 指标 | prometheus/client_golang | OpenTelemetry metrics |
| 追踪 | OpenTelemetry | — |
| 测试 | testing + stretchr/testify | — |
| API 文档 | swaggo/swag | grpc-gateway openapi |

## 入口文件

**Agent 拿到任务后第一步**：读 `spec/spec.md`。它包含完整的"任务 → 必读文件"路由表和不可违反的核心约束。

其他文件按路由表按需加载，不要主动读取。

## 文档模板

只有用户需要创建对应文档时再读：

- `docs/templates/product-requirement-template.md` — 产品需求文档（PRD）
- `docs/templates/technical-rfc-template.md` — 技术 RFC

Read the full skill on GitHub

Details

Skill name: gospec
Repository: singchia/gospec
License: MIT
Repo updated: 18 April 2026

FAQ

What does the Gospec skill do?

How do I install the Gospec skill?

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

Is Gospec popular?

It lives in singchia/gospec, which has 7 GitHub stars and 2 forks.

Related skills

DBT Semantic Layer Developer

keithbinkly/dbt-semantic-layer

Provides expert-level assistance with dbt Semantic Layer, MetricFlow, semantic models, metrics, dimensions, entities, measures, and BI tool integrations. Use this skill when building semantic models, creating metrics (simple, ratio, cumulative, derived, conversion), debugging validation errors, or integrating with BI tools. Extracted from official dbt documentation and optimized for data practitioners.

Databases

Genpark Lead Harvester

alphaparkinc/genpark-lead-harvester

High-precision social intent monitoring and lead acquisition engine. Scans social platforms for users experiencing high e-commerce friction (overpricing, refund failures, subscription traps) and aggregates them into a local actionable database for GenPark conversion.

Databases

Time Ledger

cruisekkk/time-ledger

Natural-language time tracking — the user says what they did in plain language, you parse it into Activity + Minutes + Date and write it to their Notion database; anything uncertain you mark To-confirm and BATCH-ASK rather than fabricate. Use when the user reports time spent (e.g. "read papers for two hours", "hit the gym for an hour", "coded all morning"), says log it / log my time / tidy up my time ledger / time ledger, or asks where their time went.

Databases

Paradedb Skill

paradedb/agent-skills

Expert guidance on ParadeDB text and vector search, hybrid search (BM25 + semantic), filters, facets, joins, and aggregations in Postgres. Use when writing ParadeDB queries, creating ParadeDB indexes, indexing vectors, configuring tokenizers, or implementing Elasticsearch-quality search in Postgres.

Databases

Xuanxue Database

yanouyuan-bit/xuanxue-database-skill

引导用户通过对话从零搭建个人玄学数据库——「命盘与结论库 / 应事与回测库 / 方法与资料库」三库体系，支持 Notion 一键建库与本地 Markdown 双模式，覆盖八字命理、六爻占卜、紫微斗数。当用户提到想搭建或整理命理资料库、记录命例/卦例、建立应事回测体系、验证断语准确率、系统化管理玄学学习笔记，或说「搭建玄学数据库」「整理我的命例」「怎么记录卦例」「想系统地学命理/追踪应验」时，使用本 skill——即使用户没有明确说出「数据库」三个字。

Databases

Cognitive Toolkit

glebis/claude-cognitive-toolkit

Evidence-based CBT and DBT intervention skills — guided thought records, opposite action, DEAR MAN roleplay, crisis skills with optional HRV biofeedback. Configurable therapeutic pushback. Triggers on "/cbt", "/dbt", "/thought-record", "/record", "/opposite", "/opposite-action", "I need to work through something", "help me with a thought", "cognitive distortion", "I'm spiraling", "can we do a thought record".

Databases

Browse the most popular Claude skills, all databases skills, or write your own with the skills generator.