SDV-G-Deploy
- 5 skills
- 0 followers
- 8 hours ago last updated
- ▌ Ant Compact · sdv-g-deploy bundleCompact plain-language communication layer for AI coding agents. Use when the user asks for short, concise, brief, low-token, token-saving, compact, minimal, no-fluff, "без воды", "коротко", or ANT Compact answers while still needing understandable technical help for coding, debugging, commands, Git, deployments, APIs, databases, errors, or project building.
- ▌ Ant Low Words · sdv-g-deploy bundleUltra-compact, respectful communication layer for AI coding agents. Use when the user explicitly asks for ANT Low Words, ultra short, maximum token saving, few words, terse mode, "caveman style", "экономь максимум токенов", "очень коротко", or when repeated coding-agent updates must be extremely small while preserving meaning, commands, checks, and safety warnings.
- ▌ Ant Product Map · sdv-g-deploy bundleProduct-map skill for AI agents helping non-technical builders turn an idea, repo, feature brief, messy notes, or product discussion into a simple evidence-based HTML product map. Use when the user asks for a product map, HTML scheme, HTML schema, visual project map, app map, startup idea map, MVP map, user-flow map, service/integration map, or a clear non-technical overview of what a product is, who it serves, what screens/flows/data/integrations exist, what is unknown, and what to do next.
- ▌ Ant Research Run · sdv-g-deploy bundleBreak deep AI research into recoverable, evidence-based passes. Use when a user asks for deep research, market/lookalike research, repo critique, roadmap research, multi-source investigation, or any long AI-agent research that may hit timeouts, context limits, or produce weak final-only summaries.
- ▌ Ant Plain Language · sdv-g-deploy bundlePlain-language communication layer for AI coding agents. Use when building, planning, debugging, deploying, editing code, explaining errors, terminal commands, APIs, databases, auth, Git, or technical decisions for a non-technical or mixed-technical user. Translate jargon into the user's language, give safe concrete steps, explain how to verify, and put deep technical detail in an optional appendix.