ai-engineer

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

1.00x

Quality

48%

Does it follow best practices?

Impact

56%

1.00x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/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 description padded with lists of well-known tools rather than actionable, token-efficient guidance. It lacks executable examples, validation checkpoints, and any progressive disclosure via reference files.

Suggestions

Replace the tool/model enumerations with concise, executable examples (e.g., a minimal RAG snippet, a serving config) and move vendor lists to a reference file.

Add explicit validation/verification checkpoints to the workflow steps (e.g., 'validate retrieval with eval set before rollout').

Split the capability catalogs into references/ files and keep SKILL.md as a lean overview with one-level-deep, clearly signaled links.

Dimension	Reasoning	Score
Conciseness	The ~177-line body is dominated by enumerations of tools and models Claude already knows ('OpenAI GPT-4o/4o-mini, o1-preview...', 'Anthropic Claude 4.5 Sonnet/Haiku...', 'Pinecone, Qdrant, Weaviate, Chroma, Milvus'), which is padded reference material rather than net-new guidance; this is noticeably verbose.	2 / 5
Actionability	There is no executable code, no commands, and no concrete examples — only high-level hints like 'Production RAG architectures with multi-stage retrieval pipelines' and tool name-drops, which describe rather than instruct.	2 / 5
Workflow Clarity	The 'Instructions' (4 steps) and 'Response Approach' (8 steps) sections provide a rough sequence, but steps are abstract with no validation checkpoints or feedback loops, fitting 'sequence present but checkpoints missing or implicit.'	3 / 5
Progressive Disclosure	The body has clear section headers (some structure), but no bundle files exist and the large capability enumerations are inlined rather than moved to reference files, so it is only partly organized with no signaled references.	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 in a correct third-person voice, but it omits any explicit 'Use when...' trigger guidance, which caps its completeness. Distinctiveness is moderate given the broad AI-engineering scope.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger situations (e.g., 'Use when building or debugging RAG pipelines, agent workflows, or LLM serving infrastructure').

Narrow the scope or lead with the single most distinctive capability to reduce overlap with general coding/ML skills.

Include common user phrasings and synonyms (e.g., 'chatbot', 'embeddings', 'retrieval', 'LLM inference') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several specific concrete actions and components — 'Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations' — covering the domain comprehensively, with only minor gaps; not a full 5 because the actions remain somewhat high-level rather than finely granular.	4 / 5
Completeness	The description clearly answers 'what' (build LLM apps, RAG systems, agents; implements vector search, multimodal AI, etc.) but provides no 'when' / 'Use when...' trigger clause, so per the guideline a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural keywords a user would say — 'LLM applications', 'RAG systems', 'AI agents', 'vector search', 'multimodal AI', 'agent orchestration' — giving good coverage, though a few common variants/synonyms are missing, keeping it just below a 5.	4 / 5
Distinctiveness Conflict Risk	The phrase 'production-ready LLM applications, advanced RAG systems, and intelligent agents' is fairly specific, but the broad AI-engineering scope still overlaps with adjacent skills (general coding, ML/data-science, or other AI skills), so it sits at 'somewhat specific but could still overlap.'	3 / 5
	Total	14 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/ai-engineer/SKILL.md
Commit: 900c504

Reviewed: 15 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.