ai-ml

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

Quality

56%

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 ./skills/antigravity-ai-ml/SKILL.md

Quality

Content

60%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.

This is a well-structured orchestration skill: clear phase sequencing, explicit skill routing, and closing checklists give it solid workflow clarity. Its weaknesses are generic, non-executable action steps and redundancy between skill lists, actions, and copy-paste prompts, which inflate tokens without adding guidance Claude doesn't already have.

Suggestions

Drop the 'Copy-Paste Prompts' sections (they restate the preceding skill list) or merge them into the skill list to cut roughly a third of the body.

Replace generic action items with concrete, verifiable steps per phase — e.g., for RAG: 'benchmark retrieval accuracy on a golden set before adding reranking'.

Move the per-phase skill catalogs and checklists into reference files (e.g., references/rag.md, references/agents.md) and keep SKILL.md as a lean routing overview.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but much of it is redundant scaffolding: "Copy-Paste Prompts" like 'Use @ai-product to design AI-powered features' merely restate the skill lists above them, and generic action items such as 'Define AI use cases' and 'Choose appropriate models' add little Claude doesn't know. Mostly efficient with noticeable tightening possible, matching the level-3 anchor.	3 / 5
Actionability	Concrete guidance exists in the form of specific skill invocations (e.g., 'Use @llm-application-dev-langchain-agent to create LangChain agents'), but the substantive Actions steps are high-level directions ('Design data pipeline', 'Configure retrieval') with no commands, code, or key details. This sits between vague direction and executable guidance — level 3.	3 / 5
Workflow Clarity	Seven phases are clearly sequenced, each pairing skills, actions, and prompts, and the closing 'AI Development Checklist' and 'Quality Gates' sections serve as explicit checkpoints. Not a 5 because there are no validation or feedback loops (e.g., verify retrieval accuracy or agent behavior before proceeding to the next phase); minor validation gaps only.	4 / 5
Progressive Disclosure	The file is well-organized with clear phase sections, a checklist, quality gates, and limitations, and it makes no references to nonexistent files. Not a 5 because at ~250 lines the per-phase skill catalogs and checklists could be split into per-domain reference files, leaving SKILL.md as a leaner routing overview.	4 / 5
	Total	14 / 20 Passed

Description

53%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 names a broad domain with recognizable subtopics (LLM, RAG, agents, ML pipelines) but provides no concrete actions, no trigger guidance, and high overlap risk with the many individual skills it references. It reads as a category label rather than an operational skill description.

Suggestions

Add an explicit 'Use when...' clause naming the triggering scenarios (e.g., 'Use when building LLM-powered apps, chatbots, or RAG pipelines').

Replace domain labels with concrete actions, e.g., 'Orchestrates design, integration, evaluation, and deployment of LLM apps, RAG pipelines, and AI agents'.

Include natural synonyms users would actually say — chatbot, prompt engineering, embeddings, vector search — and narrow the scope to reduce conflict with the individual skills it routes to.

Dimension	Reasoning	Score
Specificity	The description lists several named areas — "LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features" — but these are domain labels rather than concrete actions (nothing like 'extract', 'build', 'deploy' with a concrete object). It matches the anchor 'names domain and 1-2 concrete actions, but not comprehensive' more than 'lists several specific actions', since no executable capability is stated.	3 / 5
Completeness	The 'what' is reasonably clear ("workflow covering LLM application development, RAG implementation..."), but there is no 'Use when...' clause or any explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It cannot score 4 because 'when' is entirely absent rather than merely imprecise.	3 / 5
Trigger Term Quality	Terms like "LLM", "RAG", "agent architecture", "ML pipelines", and "AI-powered features" are phrases users would naturally say. Not a 5 because common variations such as 'chatbot', 'prompt engineering', 'embeddings', 'vector database', or specific framework names are missing.	4 / 5
Distinctiveness Conflict Risk	"AI and machine learning workflow" is very broad and overlaps heavily with the individual skills it orchestrates (rag-engineer, ai-engineer, ml-engineer, etc.) as well as any general ML/AI skill. It fits 'very broad; high overlap risk with many similar skills' rather than 'somewhat specific but could still overlap'.	2 / 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: boisenoise/skills-collections
Path: skills/antigravity-ai-ml/SKILL.md
Commit: 690de8f

Reviewed: 9 minutes 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.