agentmods.dev

backend-service-spec-skill

A Chinese-language version of a workflow for documenting backend systems, services, message flows, and current code-based requirements. It emphasizes recording only facts supported by code and clearly marking uncertain evidence.

In plain words
What is it for?
Use it to create service maps, trace calls and messages, organize business-domain knowledge, perform service deep dives, and extract requirements from legacy code.
Why use it?
It gives teams a consistent way to turn scattered backend knowledge into shared documentation. It reduces the risk of presenting one-sided dependencies or guesses as confirmed system behavior.

Skill for Claude CodeCodex

9 2mo ago A scan 97 tokens original MIT
View the source file SYZ-Coder/codebase-knowledge-wiki
Install

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.

agentmods
npx agentmods add skills/syz-coder/codebase-knowledge-wiki/backend-service-spec-skill
Any agent
npx skills add SYZ-Coder/codebase-knowledge-wiki --skill backend-service-spec-skill
Clone the repo
git clone --depth 1 https://github.com/SYZ-Coder/codebase-knowledge-wiki

Made for: Claude Code, Codex.

Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,248 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00097 $0.03248
Opus 5 $0.00048 $0.01624
Sonnet 5 $0.00019 $0.00650
Haiku 4.5 $0.00010 $0.00325

Measured 3d ago against content hash 5c43e4f2fb33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend-service-spec-skill 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 3d 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.

backend-service-spec-skill/SKILL.md · 351 lines

How it starts

The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backend Service Spec Skill

用于把单服务、跨服务、业务域、通信链路、事实需求五类梳理动作统一成一套可复用知识技能。

0. 何时使用

当用户出现以下目标时，使用本技能：

  • 想梳理旧系统、微服务、平台型仓库的代码总图
  • 想做跨服务调用链、接口链路、消息链路排查
  • 想把零散服务文档上卷成“域 -> 服务 -> 规范”三层知识
  • 想对单个高价值服务做纵切梳理
  • 想在历史 PRD 缺失时，按功能模块从代码事实抽取当前系统事实需求
  • 想把代码知识沉淀成团队可复用的中央知识库，而不是停留在一次对话里

如果只是实现功能、修 Bug、写测试，而不是做知识梳理，不优先使用本技能。

1. 核心原则

始终遵守以下约束：

  • 严格按代码事实输出，不把猜测写成事实
  • 先索引，后正文：先建立地图，再沉淀稳定知识页
  • Codemap 是索引层，不是最终知识库正文
  • 业务域页的价值是“上卷整理”，不是重复抄写服务页
  • 跨服务链路必须区分同步调用、异步消息、定时/补偿、实时通道
  • 事实需求抽取必须区分当前代码事实、单边线索、数据线索和待人工确认项
  • 无法闭环验证的内容必须显式标注证据等级，不能伪装成已确认
  • 如果只看到单边依赖、单边契约、单边 producer/listener，不得直接写成双边已确认闭环
  • 在进入正式梳理前，先做 workspace 范围识别

2. 执行前置：workspace 范围识别

在运行核心功能前，先用最小成本判断当前 scope 属于哪一种：

  • single-system: 单一系统 / 单一运行时家族
  • service-family: 同一家族、多服务协作
  • multi-system-workspace: 多套系统共存的工作区

最少要回答三个问题：

  1. 当前 scope 是单系统、服务家族，还是多系统并存工作区
  2. 本轮目标是全景索引、关键链路、还是稳定知识页
  3. 当前产物应该落在 mydocs/ 的哪一层

如果识别为 multi-system-workspace：

  • 第一轮优先 create_codemap: mode=service_landscape
  • 先切 family，再做闭环链路
  • 不要直接上 build_domain_map

详见：references/workspace-classification.md

3. 核心功能

3.1 跨服务 create_codemap

用途：

  • 在多服务、微服务、平台仓库中生成跨服务 CodeMap
  • 继承 sdd-riper 的 create_codemap 思想，但升级为“服务间视角”
  • 不只看单项目结构，还看服务注册、调用方向、依赖关系、上下游角色、关键链路

适用输入：

create_codemap: mode=service_landscape, scope=<系统名或服务群>, goal=<梳理目标>

也兼容：

create_codemap: mode=project, scope=<项目名>, goal=<输出项目总图与核心流程>
create_codemap: mode=feature, scope=<关键功能或链路>, goal=<梳理核心入口与主链路>
create_codemap: mode=service_chain, scope=<跨服务业务链>, goal=<梳理服务级链路>

输出重点：

  • 服务清单
  • 服务职责边界
  • 服务间调用关系
  • 入口与出口
  • 同步/异步链路索引
  • 外部系统依赖
  • 风险热点
  • 代码证据来源
  • workspace 范围判断

默认产物：

  • mydocs/codemap/YYYY-MM-DD_hh-mm_<name>服务总图.md
  • mydocs/codemap/YYYY-MM-DD_hh-mm_<name>链路地图.md

详情模板见 references/codemap-modes.md

3.2 跨服务业务域梳理

用途：

  • 把零散服务知识提升为团队可复用的上下文层
  • 形成“域 -> 服务 -> 规范”三层知识结构
  • 支持中央仓库、Wiki、OpenSpec、旧系统知识库共建

适用输入：

build_domain_map: scope=<系统或服务群>, goal=<按业务域梳理>

输出规则：

  • 域层只做上卷整理，不重写服务页全文
  • 域层必须区分：强事实承载服务、线索级关联服务、仍待补证关系
  • 规范层必须区分：code-fact-summary 与 team-proposed-standard
  • 最好先完成关键服务的 service_deep_dive，再做业务域梳理

Read the full file on GitHub · 351 lines

Files

What ships with it

29 files 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.

Changes

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.

  1. 3d ago First seen · 351 lines · 97 tokens per session scan A 5c43e4f2fb33

Subscribe to this mod's changes

backend-service-spec-skill is a skill published in the GitHub repository SYZ-Coder/codebase-knowledge-wiki (9 stars, last pushed 2mo ago), licensed MIT. It adds 97 tokens to every session and 3,248 once invoked, about $0.0005 per session on Opus 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 2026-08-31.

Backend and APIsWriting and docs
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens