CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-agents-architect

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool use, function calling.

44

Quality

44%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent/skills/ai-agents-architect/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

22%

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

This skill is essentially a hollow table of contents with no actionable content in the body itself. It lists capabilities and links to sub-skills but provides zero concrete guidance, code examples, or workflows for building AI agents. The introductory paragraph and capability/requirements lists add little value since Claude already understands these concepts.

Suggestions

Add at least one concrete, executable code example in the main body — e.g., a minimal ReAct loop implementation or a tool-calling pattern with actual API code.

Replace the 'Capabilities' and 'Requirements' bullet lists with a quick-start workflow that sequences the sub-skills (e.g., '1. Design tool registry → 2. Implement ReAct loop → 3. Add memory → 4. Evaluate').

Add brief 1-2 sentence descriptions next to each sub-skill link explaining what it covers and when to use it, so the main file provides standalone value.

Include a concrete decision framework or checklist for choosing between patterns (ReAct vs Plan-and-Execute) with specific criteria.

DimensionReasoningScore

Conciseness

The content is relatively short but includes unnecessary sections like 'Capabilities' and 'Requirements' that describe what Claude already knows. The introductory paragraph explaining what agents are and how they fail is padding rather than actionable instruction.

2 / 3

Actionability

There is no concrete code, no executable examples, no specific commands, and no actionable guidance in the body itself. The content describes capabilities and links to sub-skills but provides zero executable or copy-paste-ready content. It reads as a table of contents with no substance.

1 / 3

Workflow Clarity

There is no workflow, no sequenced steps, and no validation checkpoints. The skill merely lists links to sub-skills without explaining how they relate, when to use each pattern, or how to sequence agent-building tasks.

1 / 3

Progressive Disclosure

The skill does reference sub-skills via links, which is good progressive disclosure structure. However, no bundle files were provided to verify these references exist, the references lack descriptions of what each sub-skill contains, and the main file provides almost no standalone value — it's essentially just a link list with no overview content.

2 / 3

Total

6

/

12

Passed

Description

67%

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 covers the domain adequately and includes an explicit 'Use when' clause, which is good for completeness. However, it leans on vague/fluffy language ('Expert in', 'Masters') rather than listing concrete actions, and the trigger terms, while relevant, miss several common user phrasings. The capability areas read more like topic headers than specific actions Claude would perform.

Suggestions

Replace vague claims like 'Expert in' and 'Masters' with concrete actions such as 'Designs agent architectures, implements tool-calling loops, builds memory/retrieval systems, creates multi-agent workflows'.

Expand trigger terms to include more natural user phrasings like 'agentic workflow', 'LLM agent', 'ReAct pattern', 'agent loop', 'chatbot with tools', 'agent orchestration framework'.

DimensionReasoningScore

Specificity

Names the domain (AI agents) and lists some capability areas (tool use, memory systems, planning strategies, multi-agent orchestration), but these are more like topic categories than concrete actions. 'Masters' is vague fluff rather than a specific action. It doesn't list concrete actions like 'designs agent architectures, implements tool-calling loops, builds memory retrieval pipelines.'

2 / 3

Completeness

Clearly answers both 'what' (designing and building autonomous AI agents, tool use, memory systems, planning strategies, multi-agent orchestration) and 'when' with an explicit 'Use when:' clause listing trigger terms.

3 / 3

Trigger Term Quality

Includes some natural keywords like 'build agent', 'AI agent', 'autonomous agent', 'tool use', 'function calling', but misses many common variations users might say such as 'agentic workflow', 'agent framework', 'ReAct', 'chain of thought', 'LLM agent', 'chatbot with tools', 'agent loop', or 'orchestration'. The trigger terms are decent but not comprehensive.

2 / 3

Distinctiveness Conflict Risk

The AI agent niche is somewhat specific, but terms like 'tool use' and 'function calling' could overlap with general API/SDK skills or LLM integration skills. 'Memory systems' could conflict with database or caching skills. The description is moderately distinctive but has some overlap risk.

2 / 3

Total

9

/

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
Dokhacgiakhoa/antigravity-ide
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.