wang-baohai/omni-stack/omni-change
Claude Code and agent skill by wang-baohai/omni-stack
- community
Checking that the SKILL.md file is still in the repository.
Implement or review Omni-Stack changes using the project's fact documents, module catalog, controlled Docker verification, and delivery boundaries. Use for changes in this repository or generated Omni-Stack projects.
Install
npx vskill@latest install wang-baohai/omni-stack/omni-changeSKILL.md
Find the repository root from AGENTS.md and scaffold/catalog/modules.yaml. Read root AGENTS.md, then the facts and domain rules relevant to the requested change. The current source, configuration, and tests define behavior; historical acceptance is only evidence for its recorded baseline.
Use the catalog to determine module membership and required dependencies. Respect service boundaries, immutable migrations, tenant isolation, explicit permissions, and API contracts. Consult the repository Wiki for operating instructions rather than copying its teaching material into fact documents.
Build, run tests, launch applications, and collect browser evidence in local Docker. Confirm the Docker endpoint and target project before writes. Fixture identities belong to test classpaths; real CAPTCHA login is human-entered. Keep secrets, raw logs, auth state, and database dumps outside Git.
For generation, inspect the dry-run and use the generator's apply/validation path. Test the generated project's own assets and references; do not rely on the original checkout or personal installation.
Review the final diff and run checks justified by the actual change. Distinguish build, unit, integration, E2E, screenshots, and human translation review. Report failures, skips, and missing evidence accurately. Automatic approval is not human translation sign-off.
Follow the current user's authorization. This skill adds no permission to publish, merge, send messages, reset data, rewrite history, or connect third-party accounts.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingai/skills/omni-change/SKILL.md
Popularity
- Repository stars
- 89
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/wang-baohai/omni-stack/omni-change)