ohmg
Ultimate multi-agent framework for Google Antigravity. Orchestrates specialized domain agents (PM, Frontend, Backend, Mobile, QA, Debug) via Serena Memory.
61
Quality
41%
Does it follow best practices?
Impact
96%
6.40xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent-skills/ohmg/SKILL.mdDiscovery
17%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description relies heavily on technical jargon and internal terminology without explaining concrete capabilities or when to use the skill. It assumes familiarity with 'Google Antigravity' and 'Serena Memory' without context, and lacks the explicit trigger guidance needed for Claude to select it appropriately from a skill library.
Suggestions
Add a 'Use when...' clause specifying trigger scenarios, e.g., 'Use when working on the Google Antigravity project or when the user mentions multi-agent coordination for this codebase'
Replace abstract terms like 'orchestrates' with concrete actions, e.g., 'Coordinates code reviews, delegates frontend/backend tasks, runs QA checks'
Include natural keywords users might say, such as project-specific commands, file types, or common task requests related to this framework
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('Google Antigravity') and mentions orchestrating specialized agents with specific roles (PM, Frontend, Backend, Mobile, QA, Debug), but doesn't describe concrete actions - 'orchestrates' is vague about what it actually does. | 2 / 3 |
Completeness | Describes a vague 'what' (orchestrates agents) but completely lacks any 'when' clause or explicit trigger guidance. No indication of when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Uses technical jargon ('multi-agent framework', 'Serena Memory', 'orchestrates') that users wouldn't naturally say. 'Google Antigravity' may be a project name but lacks common user-facing trigger terms. | 1 / 3 |
Distinctiveness Conflict Risk | The specific mention of 'Google Antigravity' and 'Serena Memory' provides some distinctiveness, but 'multi-agent framework' and generic agent roles could overlap with other orchestration or project management skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is concise and well-organized with good use of tables and code blocks for quick reference. However, it lacks complete executable examples for the multi-agent coordination workflows and missing validation/verification steps for what are inherently complex, multi-step operations. The progressive disclosure could be improved with explicit links to detailed documentation.
Suggestions
Add a complete end-to-end example showing the full coordination workflow from PM planning through agent spawning to QA review, with expected outputs at each step
Include explicit validation checkpoints in the coordination workflow (e.g., 'Verify agent spawned successfully before proceeding')
Add links to detailed documentation files for Serena Memory structure, agent configuration options, and troubleshooting guides
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient with no unnecessary explanations. Tables, code blocks, and quick reference sections maximize information density without explaining concepts Claude already knows. | 3 / 3 |
Actionability | Provides concrete commands and configuration examples, but lacks complete executable workflows. The agent spawning and coordination patterns are shown as fragments rather than full working examples with expected outputs. | 2 / 3 |
Workflow Clarity | Multi-step coordination is mentioned ('PM planning → agent spawning → QA review') but lacks explicit validation checkpoints or error recovery steps. The workflow for complex multi-agent orchestration needs clearer sequencing and feedback loops. | 2 / 3 |
Progressive Disclosure | Content is well-structured with clear sections, but references to external files (.serena/memories/, .agent/skills/, .agent/config/) lack navigation links to detailed documentation. No explicit pointers to advanced guides or API references. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.