/ultragoal
Use this skill to break down complex, multi-stage projects into sequential micro-goals that persist across sessions. It prevents state loss and ensures only the current active goal can be executed, verified, or updated.
$ npx -y skills add Joonghyun-Lee-Frieren/oh-my-antigravity --skill ultragoal --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
/ultragoal
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use this skill to break down complex, multi-stage projects into sequential micro-goals that persist across sessions. It prevents state loss and ensures only the current active goal can be executed, verified, or updated.
SKILL.md
ultragoal.SKILL.mdname = "ultragoal"
description = "Manage durable multi-goal workflows with sequential execution, repo-native checkpointing, and fail-closed safety."
Purpose
Use this skill to break down complex, multi-stage projects into sequential micro-goals that persist across sessions. It prevents state loss and ensures only the current active goal can be executed, verified, or updated.
Trigger
- User requests a long-running, multi-step, or complex change spanning many files.
- The project needs repo-native tracking of progress that survives session restarts.
- Transitioning between major milestones where clear checkpoints and evidence audits are required.
Workflow
1. **Brief & Decompose**:
- Parse the high-level objective/brief.
- Decompose into an ordered array of 3-7 discrete micro-goals.
- Ensure each goal has explicit verification criteria and a defined owner/lane.
2. **Durable Persistence**:
- Create or update `.omg/ultragoal/brief.md` containing the overall mission and constraints.
- Initialize `.omg/ultragoal/goals.json` mapping goals to statuses (`todo`, `in-progress`, `completed`, `blocked`, `failed`).
- Initialize `.omg/ultragoal/ledger.jsonl` to log transition records, timestamps, and verification evidence.
3. **Fail-Closed Execution**:
- Identify the first or next `todo` goal and set its status to `in-progress`.
- Prevent executing or planning subsequent goals until the `in-progress` goal is marked `completed` with clear validation evidence.
- If a goal fails or is blocked, halt the workflow and prompt for troubleshooting or manual recovery.
4. **Handoff generation**:
- Generate a precise `/oma:goal` or `/oma:team` command using the `--intent` pin pattern for the current active goal.
Output Template
## Active Goal
- ID: ...
- Intent: ...
## Progress Overview
- Completed: X / Y goals
- Active: [Goal Description]
## Goal Registry
| ID | Goal | Status | Verification Criteria | Evidence / Blockers |
| --- | --- | --- | --- | --- |
| ... | ... | ... | ... | ... |
## Handoff Directive
- Command: `/oma:goal "..."`
Read more
name = "ultragoal" description = "Manage durable multi-goal workflows with sequential execution, repo-native checkpointing, and fail-closed safety."
Purpose
Use this skill to break down complex, multi-stage projects into sequential micro-goals that persist across sessions. It prevents state loss and ensures only the current active goal can be executed, verified, or updated.
Trigger
- User requests a long-running, multi-step, or complex change spanning many files.
- The project needs repo-native tracking of progress that survives session restarts.
- Transitioning between major milestones where clear checkpoints and evidence audits are required.
Workflow
1. **Brief & Decompose**:
- Parse the high-level objective/brief.
- Decompose into an ordered array of 3-7 discrete micro-goals.
- Ensure each goal has explicit verification criteria and a defined owner/lane.
2. **Durable Persistence**:
- Create or update `.omg/ultragoal/brief.md` containing the overall mission and constraints.
- Initialize `.omg/ultragoal/goals.json` mapping goals to statuses (`todo`, `in-progress`, `completed`, `blocked`, `failed`).
- Initialize `.omg/ultragoal/ledger.jsonl` to log transition records, timestamps, and verification evidence.
3. **Fail-Closed Execution**:
- Identify the first or next `todo` goal and set its status to `in-progress`.
- Prevent executing or planning subsequent goals until the `in-progress` goal is marked `completed` with clear validation evidence.
- If a goal fails or is blocked, halt the workflow and prompt for troubleshooting or manual recovery.
4. **Handoff generation**:
- Generate a precise `/oma:goal` or `/oma:team` command using the `--intent` pin pattern for the current active goal.
Output Template
## Active Goal - ID: ... - Intent: ... ## Progress Overview - Completed: X / Y goals - Active: [Goal Description] ## Goal Registry | ID | Goal | Status | Verification Criteria | Evidence / Blockers | | --- | --- | --- | --- | --- | | ... | ... | ... | ... | ... | ## Handoff Directive - Command: `/oma:goal "..."`
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.
- /blueprint
Use this skill when a product, UI, or workflow decision needs a stable decision surface before implementation.
Open skill - /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

