Install
$ agentstack add skill-abysscn-oh-my-dag-omd-slim ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
/omd-slim — 精益审计(先债后瘦)
两步:先把已知欠账(你主动留的 ponytail: 捷径)收成台账,再让车队找你没意识到的过度工程。两者不同——债是你故意留的,过度工程是意外长出来的。
Pass 0 — debt 台账(先记已知债)
跑 bun run scripts/omd-debt.ts [--paths "src,scripts"]:纯 grep 扫全仓 // ponytail: , 标记,收成 ledger(缺升级触发的标 - = rot 风险)。零 LLM。让"以后再说"不烂成"永远不说"。这是已知债的账,不判对错,只收拢。
Pass 1+2 — 过度工程专审(经 dag_slim)
调 omd MCP dag_slim(可能带 mcp__omd__ 前缀;未加载先 ToolSearch "dag_slim"),scope 可选收窄。异步三段式:dag_slim(scope?) → dag_status 轮询 → dag_result 取报告路径自己 Read。车队按 global-first 两遍法(系统级先跑,-50% 在这):
Pass 1 — global(系统级):跨文件找 —
dedup:同一逻辑手写在 N 处 → 一个共享 util(最大赢面)collapse:一个概念的并行实现 → 合并成一个layer:没人需要的整层/包装/间接 → 删掉这层couple:局部"最小"选择造成的耦合/重复 → 全局一致的替代
Pass 2 — local(逐 hunk):delete: 死代码/用不上的灵活性 · stdlib: 标准库/Bun 已有 · native: 平台已有(CSS/DB 约束)· yagni: 单实现的抽象/无人设的配置 · shrink: 同逻辑更少行。 格式:L: . .
不要 flag(不是膨胀)
文档化的 ponytail:/DEFER、契约面、刻意留的扩展缝 = 规划非投机,别 yagni/delete;前端体验代码(动效/状态/层级)= 交付物非灵活性,别删。
转述纪律
每条删除建议给"删了它谁受损"的反证——确认无真实调用方 + 无近期演进信号才建议删。报告是候选,动手前自己核实引用面,别凭车队一句话砍代码。
与既有 skill 的边界
- omd-slim = 只找过度工程 + 记已知债,只删不加。找 bug/正确性 → /omd-review;扫安全 → /omd-audit;架构浅模块加厚(是"加"不是"删") → /omd-deepen。
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: AbyssCN
- Source: AbyssCN/oh-my-dag
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.