ai-ml

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

Quality

22%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/antigravity-awesome-skills-claude/skills/ai-ml/SKILL.md

Quality

Content

20%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 a high-level orchestration document that lists many sub-skills and generic action items but provides zero concrete, executable guidance. It reads like a table of contents with filler rather than an actionable workflow. The repetitive structure (skills list → vague actions → trivial copy-paste prompts) across seven phases wastes significant token budget without adding value Claude couldn't infer on its own.

Suggestions

Replace vague action items ('Choose appropriate models', 'Design system architecture') with concrete decision criteria, code snippets, or specific commands that Claude can execute.

Add at least one concrete, executable example per phase — e.g., actual API calls, configuration files, or code patterns for LLM integration or RAG setup.

Add explicit validation checkpoints and feedback loops between phases (e.g., 'Test retrieval accuracy with eval script before proceeding to Phase 4').

Dramatically condense the document by removing obvious/generic steps and consolidating the repetitive phase structure into a compact reference table mapping phases to skills and key decision points.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and repetitive. The document is essentially a long list of skill references, generic action items (e.g., 'Define AI use cases', 'Choose appropriate models'), and copy-paste prompts that all follow the same trivial pattern ('Use @X to do Y'). Most content is filler that Claude doesn't need — listing obvious steps like 'implement error handling' or 'set up API access' adds no value.	1 / 3
Actionability	No concrete code, commands, configurations, or executable guidance anywhere. Every 'action' is a vague directive like 'Design agent architecture' or 'Configure retrieval.' The copy-paste prompts are just '@skill-name' invocations with no substance. There's nothing Claude can actually execute or follow as specific technical guidance.	1 / 3
Workflow Clarity	The phases are sequenced logically (design → integration → RAG → agents → ML → observability → security), and checklists provide some structure. However, there are no validation checkpoints, no feedback loops, no error recovery steps, and no criteria for when to move between phases. The quality gates at the end are generic checkboxes with no specifics.	2 / 3
Progressive Disclosure	The content references many external skills by name, which implies a layered structure. However, no bundle files are provided, references are just skill names without clear file paths or descriptions of what each contains, and the SKILL.md itself is a monolithic wall of repetitive sections that could be significantly condensed. The structure is present but not well-signaled.	2 / 3
	Total	6 / 12 Passed

Description

25%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.

The description reads as a high-level topic listing rather than a functional skill description. It lacks concrete actions (verbs), has no 'Use when...' clause, and covers such a broad domain that it would conflict with virtually any AI/ML-related skill. The terms used are relevant but insufficient to distinguish this skill from others in a large skill library.

Suggestions

Add an explicit 'Use when...' clause with specific trigger scenarios, e.g., 'Use when the user asks to build a RAG pipeline, create an LLM-powered application, design an agent architecture, or set up ML training workflows.'

Replace broad category nouns with concrete action verbs describing what the skill does, e.g., 'Scaffolds LLM applications, implements retrieval-augmented generation with vector databases, designs multi-step agent workflows, configures ML training pipelines.'

Narrow the scope or add boundary conditions to reduce conflict risk, e.g., specifying which frameworks or patterns it covers, or explicitly stating what it does NOT cover (e.g., 'Does not cover traditional statistical modeling or data visualization').

Dimension	Reasoning	Score
Specificity	Names the domain (AI/ML) and lists several areas like 'LLM application development, RAG implementation, agent architecture, ML pipelines,' but these are broad categories rather than concrete actions. No specific verbs describing what the skill actually does (e.g., 'builds', 'configures', 'deploys').	2 / 3
Completeness	Describes 'what' at a high level (AI/ML workflow covering several areas) but completely lacks any 'when' clause or explicit trigger guidance. There is no 'Use when...' or equivalent, which per the rubric should cap completeness at 2, and the 'what' itself is also quite vague, bringing this to a 1.	1 / 3
Trigger Term Quality	Includes some relevant keywords users might say like 'RAG', 'LLM', 'agent', 'ML pipelines', and 'AI-powered features', but misses many common variations and natural phrases users would use such as 'chatbot', 'embeddings', 'vector database', 'fine-tuning', 'prompt engineering', 'model training', or 'inference'.	2 / 3
Distinctiveness Conflict Risk	The description is extremely broad, covering LLM development, RAG, agents, ML pipelines, and AI features — essentially the entire AI/ML domain. This would easily conflict with any other AI-related skill and provides no clear niche or boundary.	1 / 3
	Total	6 / 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: plugins/antigravity-awesome-skills-claude/skills/ai-ml/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.