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 ...

Install with Tessl CLI

npx tessl i github:sickn33/antigravity-awesome-skills --skill ai-agents-architect

What are skills?

1.13x

Quality

51%

Does it follow best practices?

Impact

82%

1.13x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/ai-agents-architect/SKILL.md

SKILL.md

Review

Evals

Discovery

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 adequately covers the AI agent domain and includes an explicit 'Use when' clause with trigger terms, which is good for skill selection. However, it relies on high-level capability categories rather than concrete actions, and the truncated trigger list suggests incomplete coverage. The 'Expert in' and 'Masters' phrasing is somewhat fluffy rather than action-oriented.

Suggestions

Replace abstract categories with concrete actions (e.g., 'Designs agent architectures, implements tool-calling loops, builds memory/retrieval systems, orchestrates multi-agent workflows').

Complete the trigger term list with natural variations users would say: 'agentic system', 'LLM agent', 'agent framework', 'ReAct pattern', 'function calling agent'.

Remove fluffy qualifiers like 'Expert in' and 'Masters' in favor of direct action verbs in third person.

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 like 'design agent architectures' or 'implement tool calling loops'.	2 / 3
Completeness	Clearly answers both what (designing/building autonomous AI agents with tool use, memory, planning, orchestration) and when (explicit 'Use when:' clause with trigger terms), meeting the rubric requirement for explicit trigger guidance.	3 / 3
Trigger Term Quality	Includes some natural keywords users would say ('build agent', 'AI agent', 'autonomous agent', 'tool'), but the truncation ('...') suggests incomplete coverage and misses common variations like 'agentic workflow', 'agent framework', 'LLM agent', or 'ReAct'.	2 / 3
Distinctiveness Conflict Risk	Reasonably specific to AI agents, but 'tool use' could overlap with general coding skills, and 'planning strategies' is vague enough to potentially conflict with project planning or task management skills.	2 / 3
	Total	9 / 12 Passed

Implementation

35%

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

This skill provides a reasonable conceptual overview of agent architecture patterns but fails to deliver actionable, executable guidance. The Sharp Edges table is particularly problematic with truncated solutions, and the code blocks contain bullet-point pseudocode rather than working examples. The content describes rather than instructs.

Suggestions

Replace pseudocode bullet points in Patterns section with actual executable code examples (e.g., a working ReAct loop implementation)

Complete the Sharp Edges table solutions - each 'Solution' cell currently ends with a colon and no actual code or guidance

Add concrete, copy-paste ready examples for at least one complete agent implementation pattern

Remove or condense the Capabilities/Requirements sections which describe what Claude already knows about the skill

Dimension	Reasoning	Score
Conciseness	The content is reasonably efficient but includes some unnecessary framing (role description, capabilities list) that Claude already knows. The patterns section could be tighter.	2 / 3
Actionability	The code blocks contain pseudocode/bullet points rather than executable code. The Sharp Edges table references solutions but doesn't show them - entries like 'Always set limits:' are incomplete with no actual code.	1 / 3
Workflow Clarity	Patterns describe workflows conceptually (ReAct, Plan-and-Execute) but lack concrete implementation details, validation checkpoints, or error recovery steps. The Sharp Edges table mentions issues but solutions are truncated.	2 / 3
Progressive Disclosure	References related skills at the end, but the main content is somewhat monolithic. No clear navigation to detailed resources for each pattern or anti-pattern.	2 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 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

Reviewed: about 23 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.