antigravity-coding
Use when the user asks for coding help, architecture analysis, debugging strategy, refactoring options, implementation planning, or code explanation where Antigravity model assistance can complement Codex's local repo work.
- License 许可
- MIT
- 所属仓库
- Meapri/agent-hub
- 最近更新
- 2026-08-04
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- antigravity-coding
- description
- Use when the user asks for coding help, architecture analysis, debugging strategy, refactoring options, implementation planning, or code explanation where Antigravity model assistance can complement Codex's local repo work.
03 SKILL.md 正文
Antigravity Coding
Use this skill for engineering tasks where Codex should combine local repo inspection with Antigravity model reasoning.
For code reviews, regression audits, or security findings, use
antigravity-code-review instead. That workflow keeps finding discovery and
technical verification in Codex and limits Antigravity to a writing-only pass.
Workflow
- Inspect the local files, errors, tests, and git state in Codex first.
- If Antigravity is not authenticated, use
google_antigravity_login_statusand the login_start / login_complete flow (seegoogle-antigravityskill). - Use
google_antigravity_route_modelwithtask: "code"when model choice matters or the task is complex. - Use
google_antigravity_chatfor code reasoning, architecture tradeoffs, bug hypotheses, refactor plans, or alternative implementation sketches. Optional:stream: truefor long answers;messagesfor multi-turn / tool-call context; data-URL images when needed. - Apply edits in Codex only after validating the model output against the actual codebase.
- Run local tests or focused verification before reporting completion.
Tool Shape
Preferred google_antigravity_chat arguments:
{
"model": "gemini-3.1-pro-preview",
"prompt": "Analyze this code context and suggest the root-cause fix.",
"retry_count": 1,
"timeout_sec": 180,
"stream": false
}
Use google_antigravity_list_models when a specific Gemini model is requested
and availability is uncertain.
Boundaries
- Do not send secrets, credential files, tokens, private keys, or raw
.envcontents to Antigravity. - Do not paste large unrelated files. Summarize local context and include only the relevant snippets.
- Codex remains responsible for final code edits, tests, and user-facing conclusions.
04 同仓库更多 Skills
grok-doctor
Diagnose Grok Codex consent, API key, and MCP readiness.
grok-codex
Use the Grok Codex leaf MCP for consent-gated xAI chat, model listing, and provider status.
claude-doctor
Diagnose Claude Codex consent, API key, and MCP readiness.
claude-codex
Use the Claude Codex leaf MCP for consent-gated Anthropic chat, model listing, and provider status.
release-copilot
Use when the user asks Codex to prepare a release, PR description, changelog, release notes, tag plan, GitHub release plan, version summary, or release checklist from a local git repository. This integrated version uses google_antigravity_release_snapshot, google_antigravity_release_draft, and optional google_antigravity_write polishing.
google-grounded-search
Use consent-gated Google-grounded search for current facts, source checks, versions, policies, prices, schedules, and verification.