AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Omd Sdd

skill-abysscn-oh-my-dag-omd-sdd · by AbyssCN

把审议结论结晶成正式 SDD 文档落盘 docs/plan/,当 /omd-execute 的执行契约。承接 /omd-grill 的决策记录表,写给没有对话上下文的执行器看。含 crystallize/crystals 职能。Trigger:/omd-sdd、写成 SDD、结晶、方案定了记下来、列结晶。

No reviews yet
0 installs
7 views
0.0% view→install

Install

$ agentstack add skill-abysscn-oh-my-dag-omd-sdd

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-abysscn-oh-my-dag-omd-sdd)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
16d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Omd Sdd? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

/omd-sdd — 审议结晶成执行契约

对应 pi TUI 的 /sdd(并入 /crystallize/crystals 职能)。审议(/omd-grill、pathfinder 裁决)收敛后,把结论写成结构化 SDD 落盘——它是 /omd-execute 的执行契约,写给没有对话上下文的执行器看,不是给人读的散文。

承接 /omd-grill 的决策记录表

/omd-grill 收尾产的是一张决策记录表(不是散文):

| # | 决策 | 定论 | 落点(/omd-note · pathfinder 票 · SDD 章节) | 证据 | |---|------|------|--------------------------------------------|------|

本 skill 把这张表结晶成 SDD:表里落点标「SDD 章节」的行 → 进下面的「决策」与「契约」段;标 /omd-note 的轻量决策留在台账不必入 SDD;标 pathfinder 票的附票 id 进「未决」段。表里「待 owner / 待实测」的未解项 → 原样进「未决」段,绝不当成结论写死。

落盘

路径:docs/plan/YYYY-MM-DD-.md(日期用今天,slug 从主题取 kebab-case)。

每段都要能被无上下文的执行器独立消费:

# 
## 目标 (Destination)   一句话讲清做成什么样
## 决策 (Decisions)     D-1..D-N:每条已定型裁决 + 一句为什么 + 证据(承决策记录表)
## 契约 (Contracts)     不变量 + GWT 验收点(Given/When/Then)——/omd-execute 逐条判 pass/fail 的依据
## 分解 (Breakdown)     建议施工切片与依赖(conductor 可参考,不必照抄)
## 非目标 (Non-goals)   明确不做什么(防 scope 蔓延)
## 未决 (Open)          还没裁的问题;有 pathfinder 图的附票 id,待实测的标「待实测」

契约段是关键:GWT 验收点写得越可证伪,/omd-execute 的四选一验收越不含糊。一个「模糊验收点」= 一个执行器和你各自解读的裂缝。

纪律

  • 只写已定型的决策;未决进 Open 段(或直接 path_add 开票),不把猜测写成结论。
  • 决策记录表里没证据的行,先补证据或降级进 Open,不裸奔进 Contracts。
  • 写完提示 owner:确认后 /omd-execute 交 DAG 执行。
  • 用户要看已有结晶(原 /crystals)→ ls docs/plan/*.md 按时间列给他。

与既有 skill 的边界

  • /omd-sdd已收敛的结论结晶成正式契约;审议过程本身在 /omd-grill(问透之前不结晶)。
  • 一句话的轻量决策/引用 → /omd-note 记台账,不必起 SDD。
  • 契约写完的执行 → /omd-execute,本 skill 不碰实现。

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.