antigravity-swarm

Deploys autonomous sub-agents to perform tasks in the Antigravity IDE. Supports both manual dispatch and dynamic "Auto-Hiring" of agent teams.

Quality

48%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Critical

Do not install without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./public/skills/0xnagato/antigravity-swarm/SKILL.md

Quality

Discovery

32%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description identifies its domain (agent deployment in Antigravity IDE) and mentions two operational modes, but fails to specify concrete actions the agents perform or provide explicit trigger conditions. The lack of a 'Use when...' clause significantly weakens Claude's ability to know when to select this skill over others.

Suggestions

Add a 'Use when...' clause with explicit triggers like 'Use when the user wants to delegate tasks to multiple agents, spawn sub-agents, or parallelize work in Antigravity'

Specify concrete actions the sub-agents can perform (e.g., 'code review', 'file processing', 'testing') rather than generic 'perform tasks'

Include natural trigger terms users might say such as 'delegate', 'spawn agents', 'parallel tasks', 'agent team', or 'multi-agent'

Dimension	Reasoning	Score
Specificity	Names the domain (Antigravity IDE, sub-agents) and mentions two modes (manual dispatch, Auto-Hiring), but lacks concrete actions describing what tasks the agents actually perform or what outcomes they produce.	2 / 3
Completeness	Describes what it does at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'sub-agents', 'Auto-Hiring', and 'Antigravity IDE', but missing common variations users might say like 'spawn agents', 'delegate tasks', 'parallel execution', or 'agent teams'.	2 / 3
Distinctiveness Conflict Risk	The mention of 'Antigravity IDE' and 'Auto-Hiring' provides some distinctiveness, but 'autonomous sub-agents' and 'perform tasks' are generic enough to potentially overlap with other agent or automation skills.	2 / 3
	Total	7 / 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 provides solid actionable guidance with executable commands and clear usage modes. However, it includes philosophical explanations that Claude doesn't need, and the workflow lacks explicit validation/error recovery steps for a system involving multiple autonomous agents and shared state files.

Suggestions

Remove or significantly condense the FAQ section - Claude understands parallelism, context isolation, and fault tolerance concepts

Add explicit validation steps: how to verify agents completed successfully, what to check in log files, and recovery steps when agents fail

Move detailed implementation notes (syntax patterns, Manus Protocol details) to separate reference files and link to them

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary explanations (e.g., the FAQ section explaining 'Why Sub-agents?' with concepts Claude already understands like context isolation and fault tolerance). The core instructions are reasonably efficient but could be tightened.	2 / 3
Actionability	Provides concrete, executable bash and Python commands throughout. Examples are copy-paste ready with specific file paths, flags, and expected patterns. The dispatch and orchestration commands are fully specified.	3 / 3
Workflow Clarity	Multi-step processes are listed (generate team → run team) but lack explicit validation checkpoints. No guidance on verifying agent completion beyond polling logs, and no error recovery steps if agents fail despite mentioning fault tolerance.	2 / 3
Progressive Disclosure	Content is reasonably organized with clear sections, but everything is inline in one file. The Manus Protocol files and script details could be referenced externally. No links to separate documentation for advanced configuration or troubleshooting.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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.

Repository: Demerzels-lab/elsamultiskillagent
Commit: 45f9fac

Reviewed: 27 days ago

Table of Contents

Discovery Implementation Validation

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.