ai-engineer
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.
23
12%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/antigravity-awesome-skills-claude/skills/ai-engineer/SKILL.mdQuality
Discovery
25%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 like a marketing pitch with buzzwords rather than a precise skill selector. It covers an overly broad domain without concrete actions or explicit trigger conditions, making it difficult for Claude to distinguish when to use this skill versus more targeted alternatives. Adding a 'Use when...' clause and narrowing the scope or listing specific concrete actions would significantly improve it.
Suggestions
Add an explicit 'Use when...' clause with trigger terms, e.g., 'Use when the user asks to build RAG pipelines, configure vector databases, create LLM-powered agents, or integrate AI APIs into applications.'
Replace broad buzzwords with concrete actions, e.g., 'Configures vector stores and embedding pipelines, implements retrieval-augmented generation with chunking strategies, builds multi-step agent workflows with tool use.'
Narrow the scope or clarify boundaries to reduce conflict risk — specify what framework or stack this targets (e.g., LangChain, LlamaIndex, OpenAI API) to distinguish it from other AI-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (LLM applications, RAG systems, agents) and lists some actions (vector search, multimodal AI, agent orchestration, enterprise AI integrations), but these are more like buzzword categories than concrete, specific actions. It doesn't describe what it actually does with these things (e.g., 'configures vector databases', 'chains LLM calls with tool use'). | 2 / 3 |
Completeness | Describes what it does (builds LLM apps, RAG systems, agents) but completely lacks any 'Use when...' clause or explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause should cap completeness at 2, and since the 'what' is also somewhat vague with buzzwords, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'RAG', 'vector search', 'agents', 'LLM applications', and 'multimodal AI' that users might mention. However, it misses common variations and natural phrasings users would say, such as 'chatbot', 'embeddings', 'retrieval augmented generation', 'AI pipeline', 'LangChain', 'prompt chaining', etc. | 2 / 3 |
Distinctiveness Conflict Risk | The description is extremely broad, covering LLM applications, RAG, agents, vector search, multimodal AI, and enterprise integrations — essentially the entire AI/ML application space. This would easily conflict with more specific skills for any of these individual areas (e.g., a dedicated RAG skill, a vector database skill, an agent framework skill). | 1 / 3 |
Total | 6 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads as a persona description or resume rather than an actionable skill document. It catalogs an enormous breadth of AI/ML technologies and concepts Claude already knows, without providing any concrete code, specific workflows, or executable guidance. The content is almost entirely descriptive, offering no unique value that would help Claude perform tasks better than it would without the skill.
Suggestions
Replace the extensive 'Capabilities' catalog with 2-3 concrete, executable code examples for the most common tasks (e.g., a production RAG pipeline setup with specific code, a multi-agent workflow with LangGraph).
Transform the vague 4-step 'Instructions' into specific workflows with validation checkpoints, e.g., 'After implementing RAG retrieval, validate with: `pytest tests/test_retrieval.py` and verify recall@10 > 0.8'.
Remove sections that describe what Claude already knows (Purpose, Knowledge Base, Behavioral Traits, most of Capabilities) and replace with project-specific patterns, anti-patterns, and decision trees (e.g., 'Choose Qdrant over Pinecone when: self-hosted requirement, >10M vectors').
Split detailed reference material (model comparison tables, vector DB selection guides, prompt templates) into separate bundle files and reference them from a concise SKILL.md overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and padded with information Claude already knows. The massive 'Capabilities' section is essentially a resume listing technologies and concepts (vector databases, embedding models, agent frameworks) without providing any actionable guidance. The 'Knowledge Base', 'Behavioral Traits', and 'Purpose' sections repeat information Claude inherently possesses. Most of the content is descriptive catalog rather than instructional. | 1 / 3 |
Actionability | No concrete code, commands, or executable examples anywhere in the skill. The 'Instructions' section is four vague bullet points ('Clarify use cases', 'Design the AI architecture'). The 'Example Interactions' are just prompt strings with no corresponding outputs or implementation patterns. Everything describes rather than instructs. | 1 / 3 |
Workflow Clarity | The four-step 'Instructions' workflow is extremely vague ('Clarify use cases, constraints, and success metrics' → 'Design the AI architecture') with no validation checkpoints, no error recovery, and no concrete sequencing. The 'Response Approach' is similarly abstract. For a skill involving production systems and potentially destructive operations, there are no feedback loops or verification steps. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no external references or bundle files. All content is inline in a single massive file with no navigation structure. The extensive capability listings could be split into reference files, but instead everything is dumped into one document with no clear hierarchy or signposting for discovery. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
90%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
- sickn33/antigravity-awesome-skills
- Commit
22710e9
- Reviewed
Table of Contents
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.