Name: antigravity-skill-orchestrator
Rating: 51.2 (1 reviews)
Author: administrakt0r

antigravity-skill-orchestrator

A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/antigravity-skill-orchestrator/SKILL.md

The canonical home for this skill is antigravity-skill-orchestrator in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-structured, mostly actionable guide with a clear multi-step workflow and guardrail checkpoints. It is slightly verbose due to repeated guardrail and catalog messaging, and could split detailed memory-tool usage into a reference file.

Suggestions

Reduce repetition of the guardrail and master catalog URL (each currently restated 3-4 times) to tighten conciseness.

Add an explicit verification step after recording a combination (e.g., confirm the memory_write succeeded and re-search to verify retrievability) to strengthen the feedback loop.

Move the detailed memory_search/read/write examples into a references file linked from the body to improve progressive disclosure and keep the overview lean.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with well-organized sections, but it repeats several ideas (the master catalog URL appears twice, the guardrail is restated across Overview, Core Concepts, Best Practices, and Examples), adding padding that could be tightened.	3 / 5
Actionability	It provides mostly executable guidance including concrete memory_search/memory_write/memory_read tool calls with realistic arguments and a real catalog URL, with only minor gaps such as the discovery step leaving the mechanism partly abstract.	4 / 5
Workflow Clarity	The four-step guide is clearly sequenced with explicit trigger conditions and decision branches (If YES/If NO), and the guardrail acts as a validation checkpoint; minor gaps are the lack of an explicit verify-after-record step and the absence of an error-recovery loop.	4 / 5
Progressive Disclosure	The skill is well structured with clear overview, when-to-use, concepts, step-by-step, examples, and best-practices sections, and the external catalog is one level deep and clearly signaled; minor gaps are the absence of separate reference files for the memory tool usage or catalog.	4 / 5
	Total	15 / 20 Passed

Description

46%Weight 40%Scale 1-5

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 conveys a clear 'what' around meta-skill orchestration and memory tracking, but it lacks explicit 'when to use' trigger guidance and leans on jargon rather than natural user phrases. It is mostly distinct from other skills but would benefit from concrete trigger language.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases (e.g., 'Use when the user asks to orchestrate, combine, or select the best skills for a complex multi-domain task').

Replace technical jargon ('agent-memory-mcp', 'task-evaluation') with natural keywords a user would actually say, such as 'combine skills', 'pick the right skill', or 'manage complex tasks'.

Sharpen the concrete actions by naming a couple more specific behaviors (e.g., 'searches a curated skill catalog', 'records successful combinations') to lift specificity above a generic overview.

Dimension	Reasoning	Score
Specificity	The description names the domain (meta-skill orchestration) and lists a few concrete actions ('dynamically selects appropriate skills', 'tracks successful skill combinations', 'prevents skill overuse'), but the actions are generic and not comprehensive, matching the 'Names domain and 1-2 concrete actions' anchor.	3 / 5
Completeness	It clearly states 'what' the skill does (understands task requirements, selects skills, tracks combinations, prevents overuse) but provides no 'when should Claude use it' trigger guidance, so per the judging guidelines completeness is capped at 3.	3 / 5
Trigger Term Quality	It relies on technical jargon ('meta-skill', 'agent-memory-mcp', 'task-evaluation') rather than natural phrases a user would say, with only generic terms like 'selects appropriate skills'; it lacks the natural trigger vocabulary found in higher anchors.	2 / 5
Distinctiveness Conflict Risk	The orchestration/meta-skill niche with memory tracking is fairly distinct and unlikely to trigger for the wrong skill, with only minor overlap risk against general task-management skills, matching the 'mostly distinct; minor overlap risk' anchor.	4 / 5
	Total	12 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/antigravity-skill-orchestrator/SKILL.md
Commit: 900c504

Reviewed: 5 hours 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.