ai-ml

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

50%

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 seven-phase orchestration bundle with concrete skill-invocation prompts, but it is padded with repetitive prompts, lacks concrete executable step detail, and has no validation checkpoints or progressive disclosure via separate files. Every dimension lands at the midpoint as a result.

Suggestions

Add explicit validation/quality-gate checkpoints between phases (e.g., verify RAG retrieval accuracy before proceeding to agent development) to introduce feedback loops.

Tighten the repetitive copy-paste prompt blocks and generic checklists to reduce token padding.

Split per-phase detail into reference files with clearly signaled one-level-deep links, or move the checklist/quality-gate material to a separate reference, to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but it is padded with repetitive near-identical copy-paste prompts ('Use @x to ...') and generic checklists across seven phases that could be tightened.	2 / 3
Actionability	Concrete skill-invocation prompts ('Use @rag-engineer to design RAG pipeline') provide actionable triggers, but the per-phase 'Actions' lists ('Define AI use cases', 'Design system architecture') are high-level descriptions rather than concrete, executable guidance.	2 / 3
Workflow Clarity	The seven phases are clearly sequenced Phase 1 through 7, but there are no interleaved validation or feedback checkpoints between phases; the end-of-document checklists are not phase gates, so validation gaps cap this at 2.	2 / 3
Progressive Disclosure	The file is well-organized into clearly headed sections, but at 250+ lines it is monolithic with no bundle files and no one-level-deep references to split detail out, so structure is present but content that should be separate is inline.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 is broad and lists relevant AI/ML capability areas with natural keywords, but it reads as a domain catalog rather than a set of concrete actions and lacks any explicit 'Use when...' trigger guidance. This caps both completeness and distinctiveness, leaving every dimension at the midpoint.

Suggestions

Add an explicit 'Use when...' trigger clause naming concrete user scenarios (e.g., 'Use when building LLM apps, RAG systems, or AI agents') to raise completeness and distinctiveness.

Replace capability-category phrasing with concrete actions so the skill states what it does operationally, not just what domains it spans.

Narrow or qualify the scope to reduce overlap with the individual sub-skills it orchestrates, improving conflict resistance.

Dimension	Reasoning	Score
Specificity	The description names the AI/ML domain and several capability areas ('LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features'), but these are capability categories rather than concrete actions like 'extract' or 'merge', so it does not reach the concrete-action level of 3.	2 / 3
Completeness	It states what the workflow covers, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	It includes relevant natural keywords users might say ('LLM', 'RAG', 'AI agents', 'ML pipelines', 'AI-powered features'), but coverage is incomplete (missing common variations like chatbots, embeddings, vector search) and lacks natural trigger phrasing.	2 / 3
Distinctiveness Conflict Risk	It is distinguishable as an AI/ML orchestration bundle, but its broad scope (LLM apps, RAG, agents, ML pipelines, observability, security) overlaps heavily with the many individual sub-skills it references.	2 / 3
	Total	8 / 12 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: sickn33/antigravity-awesome-skills
Commit: b69437e

Reviewed: about 17 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.