ai-agents-architect

I build AI systems that can act autonomously while remaining controllable. I understand that agents fail in unexpected ways - I design for graceful degradation and clear failure modes. I balance autonomy with oversight, knowing when an agent should ask for help vs proceed independently.

Quality

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

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

Quality

Discovery

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 description reads as a personal bio or philosophy statement rather than a functional skill description. It uses first person ('I build', 'I understand', 'I design') throughout, provides no concrete actions, lacks any trigger guidance, and is too generic to be distinguishable from other AI-related skills.

Suggestions

Rewrite in third person voice (e.g., 'Designs and implements agentic AI systems with...') and list specific concrete actions such as 'implements tool-use loops, designs retry logic, builds human-in-the-loop checkpoints'.

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when building AI agents, designing agentic workflows, implementing tool-calling loops, or adding human oversight to autonomous systems.'

Narrow the scope to a clear niche — specify what types of agents, what frameworks or patterns, and what outputs this skill produces to reduce overlap with other AI-related skills.

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language like 'build AI systems', 'design for graceful degradation', and 'balance autonomy with oversight' without listing any concrete, specific actions. No tangible operations are described.	1 / 3
Completeness	There is no explicit 'Use when...' clause or equivalent trigger guidance. The 'what' is vague and the 'when' is entirely missing, making it unclear when Claude should select this skill.	1 / 3
Trigger Term Quality	The terms used ('AI systems', 'autonomously', 'graceful degradation', 'failure modes') are abstract and jargon-heavy. Users are unlikely to naturally say these phrases when requesting help with a specific task.	1 / 3
Distinctiveness Conflict Risk	The description is extremely generic — 'AI systems', 'agents', 'autonomy', 'oversight' could overlap with virtually any AI-related skill. There are no distinct triggers or a clear niche to differentiate it.	1 / 3
	Total	4 / 12 Passed

Implementation

14%

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

This skill reads more like a high-level topic outline or table of contents than actionable guidance. The patterns are described conceptually without executable code, the anti-patterns section is empty, and the Sharp Edges table has truncated solutions that provide no actual remediation. The skill fails to provide the concrete, executable guidance that would make it useful for building agent systems.

Suggestions

Replace pseudocode bullet lists in Patterns with complete, executable code examples (e.g., a working ReAct loop implementation with iteration limits, tool registry with actual schema definitions).

Complete the Sharp Edges table by adding actual code snippets or concrete solutions for each issue instead of trailing colons with no content.

Add content to the Anti-Patterns section - currently they are empty headers. Provide concrete examples of what bad implementations look like and how to fix them.

Split detailed pattern implementations into separate referenced files (e.g., REACT_PATTERN.md, TOOL_REGISTRY.md) and keep SKILL.md as a concise overview with clear navigation links.

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary framing (repeating the description in the body, listing 'Requirements' that Claude already knows like 'Understanding of function calling'). The patterns section uses pseudocode-style bullet lists rather than being truly lean, but it's not excessively verbose.	2 / 3
Actionability	The content is almost entirely abstract and descriptive. The 'patterns' are bullet-point descriptions rather than executable code or concrete examples. The Sharp Edges table lists problems and promises solutions but the solutions are truncated/empty (e.g., 'Always set limits:' with no actual code). There is nothing copy-paste ready or directly executable.	1 / 3
Workflow Clarity	While patterns like ReAct and Plan-and-Execute are mentioned, they are described at a conceptual level without concrete sequencing, validation checkpoints, or error recovery steps. The Sharp Edges table hints at validation concerns but provides no actual workflow guidance. Multi-step agent design processes have no explicit validation or feedback loops.	1 / 3
Progressive Disclosure	The content is a monolithic file with no references to external detailed documents. Anti-patterns are listed as headers with no content beneath them. The Sharp Edges table has truncated solutions. There's no navigation structure pointing to deeper resources for any of the six listed capabilities.	1 / 3
	Total	5 / 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

Repository: sickn33/antigravity-awesome-skills
Commit: d739c8b

Reviewed: 4 days 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.