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

17%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./skills/antigravity-skill-orchestrator/SKILL.md

Quality

Content

35%Scale 1-3

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

This skill is overly verbose for what it teaches—most of the content describes meta-cognitive processes (evaluating complexity, deciding when to use skills) that Claude can perform natively. The actionable parts (memory_write/memory_search examples, catalog URL) are useful but buried in explanatory text. The workflow lacks validation steps, particularly the instruction to 'assume success' before recording combinations.

Suggestions

Cut the content by at least 50%: remove the Overview paragraph, 'When to Use' section, and 'Core Concepts' explanations that restate what Claude already knows about task complexity evaluation. Distill to a decision rule + the concrete steps.

Add a validation checkpoint in Step 4 before recording the skill combination—verify the task output meets requirements rather than assuming success.

Replace the abstract guardrail guidance ('Ask yourself: Can I solve this efficiently?') with a concrete heuristic, such as a checklist of complexity indicators (e.g., >2 domains, >3 files across different subsystems, requires external service integration).

Consider extracting the Master Skill Catalog details and memory integration patterns into separate reference files to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The skill is highly verbose, explaining concepts Claude already understands (what an orchestrator is, what task complexity means, what 'simple tasks' are). The overview paragraph, 'Core Concepts' section, and 'When to Use This Skill' section all repeat similar information. Much of the content describes meta-reasoning that Claude can do natively without explicit instruction.	1 / 3
Actionability	The skill provides some concrete examples with memory_write and memory_search calls, which are executable. However, much of the guidance is abstract decision-making advice ('Ask yourself: Can I solve this efficiently?') rather than concrete, copy-paste-ready instructions. The catalog URL is specific and actionable, but the skill discovery and selection steps are vague.	2 / 3
Workflow Clarity	The 4-step workflow is clearly sequenced and logically ordered, but lacks validation checkpoints. There's no verification step after applying skills (e.g., confirming the combination actually worked before recording it). Step 4 says 'Assume the task was completed successfully,' which explicitly skips validation—a significant gap for a multi-step orchestration process.	2 / 3
Progressive Disclosure	The content is structured with clear sections and headers, but it's monolithic—everything is inline in a single file with no references to supporting documents. The 'Core Concepts' section contains material that could be separated. The reference to the external catalog URL is good, but there are no bundle files to support progressive disclosure.	2 / 3
	Total	7 / 12 Passed

Description

0%Scale 1-3

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 is highly abstract and uses internal/technical jargon rather than concrete, user-facing language. It describes a meta-orchestration concept without specifying concrete actions, user-facing trigger terms, or explicit 'when to use' guidance. It would be nearly impossible for Claude to reliably select this skill from a pool of others based on this description alone.

Suggestions

Replace abstract language with concrete actions — specify exactly what this skill does (e.g., 'Routes multi-step tasks to the correct specialized skills, combines skill outputs, and logs successful workflows').

Add an explicit 'Use when...' clause with specific trigger conditions (e.g., 'Use when a user request requires coordinating multiple tools or when a task spans more than one skill domain').

Include natural trigger terms a user might say, such as 'complex task', 'multi-step workflow', 'combine tools', or 'orchestrate' to improve discoverability and reduce conflict risk.

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language like 'understands task requirements', 'dynamically selects appropriate skills', and 'prevents skill overuse'. No concrete actions are listed — these are meta-concepts, not specific capabilities a user would recognize.	1 / 3
Completeness	The 'what' is vague and abstract (orchestrates other skills), and there is no 'when' clause or explicit trigger guidance. There is no 'Use when...' or equivalent, and the nature of the skill makes it unclear when Claude should select it.	1 / 3
Trigger Term Quality	There are no natural keywords a user would say. Terms like 'meta-skill', 'dynamically selects', 'skill combinations', and 'agent-memory-mcp' are internal jargon, not user-facing trigger terms. A user would never say 'I need dynamic skill selection'.	1 / 3
Distinctiveness Conflict Risk	As a 'meta-skill' that 'selects appropriate skills', it is extremely generic and would potentially conflict with or be triggered alongside virtually any other skill. Its scope is unbounded and indistinct.	1 / 3
	Total	4 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: popey/claude-code-skills
Path: skills/antigravity-skill-orchestrator/SKILL.md
Commit: a5a6601

Reviewed: 5 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.