ai-engineer

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

12%

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

The body functions as a persona/knowledge catalog rather than an actionable skill: it name-drops many technologies Claude already knows, contains no executable guidance, and packs everything into one monolithic file. It reads as an expanded profile, not a focused, progressive skill.

Suggestions

Replace the technology catalog with concise, actionable guidance and executable code/command examples for the core tasks (e.g., a minimal RAG or agent wiring snippet).

Move the long capability lists and version-specific model names into a separate reference file and keep SKILL.md as a lean overview with one-level-deep links.

Add explicit validation/checkpoint steps to the workflow (e.g., validate retrieval, test against adversarial inputs) rather than abstract process steps.

Dimension	Reasoning	Score
Conciseness	The body is a ~180-line catalog of model and framework names (e.g., 'OpenAI GPT-4o/4o-mini, o1-preview', 'Llama 3.1/3.2, Mixtral 8x7B/8x22B') that Claude largely already knows, and embeds time-sensitive version numbers outside any deprecated section, making it verbose rather than lean.	1 / 3
Actionability	It describes capabilities rather than instructing: there is no executable code or commands anywhere, and sections like 'Instructions' ('Clarify use cases… Design the AI architecture…') are abstract high-level direction.	1 / 3
Workflow Clarity	A sequence exists in the 'Instructions' and 'Response Approach' lists, but the steps are abstract and lack any validation checkpoints or feedback loops, matching the 'steps present but checkpoints missing' anchor rather than the clearer level.	2 / 3
Progressive Disclosure	The skill is a monolithic wall of text with everything inline and no bundle files (references/scripts/assets are absent) or one-level-deep references, matching the monolithic-anchor level.	1 / 3
	Total	5 / 12 Passed

Description

60%

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 concrete capabilities and a clear AI-engineering niche, but it omits an explicit 'Use when…' trigger and is padded with some buzzword phrasing. It is solid but not exemplary, scoring just above the midpoint.

Suggestions

Add an explicit 'Use when…' clause naming concrete user triggers (e.g., 'Use when building LLM apps, RAG pipelines, AI agents, or vector search') to raise completeness and trigger quality.

Trim buzzword phrases like 'agent orchestration' and 'enterprise AI integrations' in favor of plain natural terms users would actually say.

Sharpen distinctiveness by contrasting with adjacent domains (e.g., 'Not for traditional ML/data science without LLMs').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Build production-ready LLM applications, advanced RAG systems, and intelligent agents' and 'Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations'), matching the multi-action anchor.	3 / 3
Completeness	It clearly states what the skill does but provides no 'Use when…' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	Contains relevant natural terms ('LLM applications', 'RAG systems', 'intelligent agents', 'vector search') but is padded with buzzword phrases ('agent orchestration', 'enterprise AI integrations', 'multimodal AI') and misses common variations, so it sits at the partial-coverage level rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The AI/LLM/RAG/agent niche is fairly clear, but broad phrasing like 'LLM applications' and 'enterprise AI integrations' could overlap with general ML, data-science, or coding skills, so it is not unambiguously distinct.	2 / 3
	Total	9 / 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: 9fc5f98

Reviewed: about 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.