/blueprint
Use this skill when a product, UI, or workflow decision needs a stable decision surface before implementation.
$ npx -y skills add Joonghyun-Lee-Frieren/oh-my-antigravity --skill blueprint --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/blueprint
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use this skill when a product, UI, or workflow decision needs a stable decision surface before implementation.
SKILL.md
blueprint.SKILL.mdname = "blueprint"
description = "Create a product/UI blueprint with durable interface decisions, states, constraints, and verification hooks."
Purpose
Use this skill when a product, UI, or workflow decision needs a stable decision surface before implementation.
Trigger
- A feature touches user flows, screens, copy, navigation, forms, dashboards, or visual hierarchy
- Multiple implementation lanes need one agreed product/interface contract
- Acceptance criteria exist, but the desired interaction states or content hierarchy are still fuzzy
- A redesign or frontend change needs accessibility and responsive behavior called out before coding
Workflow
1. Identify target users, core job, success signal, and non-goals. 2. Map the primary workflow from entry through success and recovery paths. 3. Define interface decisions by surface, including empty, loading, error, disabled, and success states. 4. Capture content hierarchy, navigation, controls, responsive behavior, and accessibility constraints. 5. Mark assumptions and open questions separately from firm decisions. 6. Attach implementation owners, affected files or surfaces, and verification evidence. 7. Recommend whether to persist the result to `.omg/state/blueprint.md` before `team-plan` or `team-prd`.
Output Template
## Product Frame
- Target users:
- Core job:
- Success signal:
- Non-goals:
## Workflow Map
| Flow | Entry | Steps | Exit / Success | Failure / Recovery |
| --- | --- | --- | --- | --- |
## Interface Decisions
| Surface | Decision | Rationale | State Coverage | Owner | Evidence |
| --- | --- | --- | --- | --- | --- |
## Content / IA
- ...
## Accessibility / Responsiveness
- ...
## Open Questions
- ...
## Handoff
- Recommended next command:
- Taskboard sync:
- Verification notes:
Read more
name = "blueprint" description = "Create a product/UI blueprint with durable interface decisions, states, constraints, and verification hooks."
Purpose
Use this skill when a product, UI, or workflow decision needs a stable decision surface before implementation.
Trigger
- A feature touches user flows, screens, copy, navigation, forms, dashboards, or visual hierarchy
- Multiple implementation lanes need one agreed product/interface contract
- Acceptance criteria exist, but the desired interaction states or content hierarchy are still fuzzy
- A redesign or frontend change needs accessibility and responsive behavior called out before coding
Workflow
1. Identify target users, core job, success signal, and non-goals. 2. Map the primary workflow from entry through success and recovery paths. 3. Define interface decisions by surface, including empty, loading, error, disabled, and success states. 4. Capture content hierarchy, navigation, controls, responsive behavior, and accessibility constraints. 5. Mark assumptions and open questions separately from firm decisions. 6. Attach implementation owners, affected files or surfaces, and verification evidence. 7. Recommend whether to persist the result to `.omg/state/blueprint.md` before `team-plan` or `team-prd`.
Output Template
## Product Frame - Target users: - Core job: - Success signal: - Non-goals: ## Workflow Map | Flow | Entry | Steps | Exit / Success | Failure / Recovery | | --- | --- | --- | --- | --- | ## Interface Decisions | Surface | Decision | Rationale | State Coverage | Owner | Evidence | | --- | --- | --- | --- | --- | --- | ## Content / IA - ... ## Accessibility / Responsiveness - ... ## Open Questions - ... ## Handoff - Recommended next command: - Taskboard sync: - Verification notes:
Antigravity CLI: Gemini CLI will be replaced by Antigravity CLI on June 18th. If you previously installed oh-my-gemini-cli in Gemini CLI, Antigravity CLI will ask whether to import plugins during installation. Check that option to bring your plugin over.
Repo: Joonghyun-Lee-Frieren/oh-my-antigravity
Other skills on oh-my-antigravity.
- /context-optimize
Use this skill when context is growing quickly or cache consistency drops.
Open skill - /deep-dive
Use this skill when requirements are incomplete, conflicting, or too vague to begin implementation safely.
Open skill - /execute
Use this skill when the task is implementation-ready and requires code changes now.
Open skill - /learn
Automatically evaluates OmA sessions to extract reusable patterns (error resolutions, workarounds, conventions) and save them to `.omg/rules/learned/`.
Open skill - /oma-plan
Use this skill when the request is non-trivial and should be planned before editing code.
Open skill - /plan
Use this skill when the request is non-trivial and should be planned before editing code.
Open skill

