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.
59
Quality
56%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent/skills/ai-agents-architect/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description with excellent trigger terms and completeness. The main weakness is the use of vague qualifiers ('Expert in', 'Masters') instead of concrete action verbs, and the capability areas listed are categories rather than specific actions like 'implement tool calling interfaces' or 'design agent memory architectures'.
Suggestions
Replace 'Expert in designing and building' and 'Masters' with concrete action verbs describing what the skill does (e.g., 'Designs agent architectures, implements tool calling interfaces, builds memory systems')
Convert high-level categories into specific actions (e.g., instead of 'memory systems', say 'implements vector stores and conversation history management')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AI agents) and lists some capability areas ('tool use, memory systems, planning strategies, multi-agent orchestration') but these are high-level categories rather than concrete actions. Uses 'Expert in' and 'Masters' which are vague claims rather than specific capabilities. | 2 / 3 |
Completeness | Explicitly answers both what ('designing and building autonomous AI agents' with specific areas) and when (explicit 'Use when:' clause with trigger terms). The structure clearly separates capabilities from trigger conditions. | 3 / 3 |
Trigger Term Quality | Includes good natural trigger terms that users would actually say: 'build agent', 'AI agent', 'autonomous agent', 'tool use', 'function calling'. These cover common variations of how users would request this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on AI agent development with distinct triggers like 'autonomous agent', 'multi-agent orchestration', and 'function calling'. Unlikely to conflict with general coding or other AI-related skills due to specific agent-focused terminology. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill functions as a sparse index to sub-skills rather than a functional skill document. It lacks any actionable content, concrete examples, or workflow guidance in the main file. The structure suggests good progressive disclosure intent, but the main skill body provides insufficient standalone value.
Suggestions
Add a 'Quick Start' section with a minimal executable agent example (e.g., a basic ReAct loop implementation) before linking to detailed sub-skills
Include a brief workflow showing the decision process: when to use ReAct vs Plan-and-Execute, with concrete criteria
Remove the first-person role description and replace with actionable guidance - Claude doesn't need to be told what role it's playing
Add at least one complete, copy-paste ready code example demonstrating basic tool calling or agent loop structure
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is relatively brief but includes some unnecessary framing ('I build AI systems...', 'I understand that agents fail...'). The role description and capabilities list add tokens without providing actionable guidance. | 2 / 3 |
Actionability | No concrete code, commands, or executable examples provided. The content describes capabilities and links to sub-skills but offers no actual implementation guidance, patterns, or copy-paste ready content in the main file. | 1 / 3 |
Workflow Clarity | No workflow or process is defined. The 'Patterns' section header exists but contains no content - only links to sub-skills. There's no sequencing, validation steps, or guidance on how to approach agent building. | 1 / 3 |
Progressive Disclosure | Links to sub-skills are present and one-level deep, which is good. However, the main skill provides almost no overview content - it's essentially just a table of contents with no quick-start or summary of key concepts before diving into references. | 2 / 3 |
Total | 6 / 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
- Dokhacgiakhoa/antigravity-ide
- Commit
3395991
- 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.