Omd
One table of every routed oh-my-dag skill: name → when to use. The one name to remember. Trigger: /omd / list skills / which skill / 有哪些技能 / 该用哪个技能.
Install
$ agentstack add skill-abysscn-oh-my-dag-omd ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-abysscn-oh-my-dag-omd) 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 — routed-skill router
Most oh-my-dag skills are hidden from the prompt (disable-model-invocation) to keep the Smart Zone lean. All still work — invoke with /. This table is the whole map.
| 组 | skill | when to use | |---|---|---| | 会话 | /start | new session: restore last context, print a briefing | | 会话 | /handoff | wrap up: save plan + session log so context survives | | 会话 | /caveman | ultra-compressed replies (~75% fewer tokens) | | 规划 | /council | wide decision: N personas in parallel, judged winner | | 规划 | /ponytail | laziest solution that works; anti over-engineering | | 实现 | /commit | smart git commit: zone checks + conventional message | | 实现 | /dag-build | coding task: plan → parallel build → oracle gate | | 审查 | /review | audit: security / coverage / tech-debt / gate / PR | | 审查 | /dag-review | adversarial multi-lens diff review + verify/refute | | 研究 | /dag-research | web research: retrieve → fanout → judged synthesis | | 研究 | /omd-video | video → per-segment notes (MiMo reads screen+audio); corpus for dag | | 复利 | /retro | engineering retrospective from git history | | 复利 | /dream | consolidate raw session events into durable memory | | 复利 | /skill-creator | create / improve / eval skills | | DAG | /dag-council | auto-authored expert council, judged winner | | DAG | /dag-fanout | hand-written lens spec fanout (manual gearbox) | | DAG | /dag-deepen | hotspot scan for shallow modules → refactor targets | | DAG | /dag-slim | scan repo for over-engineering → deletion targets |
Not listed (resident, always in the prompt): verify · recall · investigate · codebase-design.
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.