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

48%

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-engineer/SKILL.md

Quality

Content

35%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.

The skill reads as a persona/competency manifesto enumerating well-known tools rather than a procedural skill. It lacks executable guidance and validation checkpoints, and inlines a large catalogue that should be offloaded to reference files.

Suggestions

Replace the tool/model name lists with concise, executable guidance (code patterns, command snippets) for the core workflows, and remove encyclopedia-style listings of widely known libraries.

Add explicit validation checkpoints to the workflow (e.g., verify retrieval quality, run safety/PII guardrails, confirm cost budgets) before proceeding.

Move the long capabilities catalogue into separate reference files (e.g., references/rag-patterns.md, references/agent-frameworks.md) and link them one level deep from SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is a ~180-line catalogue of tools and model names Claude already knows (GPT-4o, Pinecone, LangChain, BM25, HNSW) with no novel instruction, padding the context with widely known information rather than earned tokens.	2 / 5
Actionability	It lists capabilities and library names but provides no executable code, commands, or concrete steps; guidance like 'Implement with monitoring, safety, and cost controls' is high-level direction rather than instruction.	2 / 5
Workflow Clarity	The Instructions and Response Approach sections give a numbered sequence, but steps are abstract with no validation checkpoints or error-recovery loops despite the skill involving destructive/risky AI deployment operations.	3 / 5
Progressive Disclosure	Content is well sectioned, but the large capabilities/tool catalogue is inlined in SKILL.md with no bundle files and no offloaded references; the detail that should live in separate files is monolithic.	3 / 5
	Total	10 / 20 Passed

Description

62%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 is specific and uses natural trigger terms, but it lacks an explicit 'Use when...' trigger clause in the frontmatter itself, which caps completeness. It is mostly distinct from neighboring skills but slightly broad at the enterprise-integration edge.

Suggestions

Add an explicit 'Use when...' clause to the description naming the trigger scenarios (e.g., 'Use when building LLM features, RAG pipelines, AI agents, or vector search').

Tighten 'enterprise AI integrations' to a more concrete trigger phrase to reduce overlap with general backend-integration skills.

Dimension	Reasoning	Score
Specificity	Names concrete sub-areas ('vector search', 'multimodal AI', 'agent orchestration', 'enterprise AI integrations') but these are categories rather than specific executable actions like 'extract' or 'merge'.	4 / 5
Completeness	Clearly answers 'what' (build LLM/RAG/agent systems and integrations) but the description itself has no 'Use when...' clause or explicit 'when to use' trigger; that guidance lives only in the body, capping completeness at 3.	3 / 5
Trigger Term Quality	Includes natural phrases users say ('LLM applications', 'RAG systems', 'AI agents', 'vector search', 'embeddings') with good coverage, though it omits some synonyms and concrete file/format triggers.	4 / 5
Distinctiveness Conflict Risk	The 'ai-engineer' / production-LLM framing carves a fairly distinct niche with minimal overlap risk against non-LLM skills, though 'enterprise AI integrations' remains broad enough to risk some overlap with general backend skills.	4 / 5
	Total	15 / 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-engineer/SKILL.md
Commit: 652629d

Reviewed: ~14 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.