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

49%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

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-agents-architect/SKILL.md

The canonical home for this skill is ai-agents-architect in sickn33/agentic-awesome-skills

Quality

Content

53%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 body is well-structured and concise-ish but its code blocks are non-executable bullet lists, the Sharp Edges solutions are left blank, and it re-explains agent concepts Claude already knows, so it lands mid-rubric on actionability and conciseness.

Suggestions

Replace the bullet-list 'javascript' blocks with actual executable code examples for the ReAct loop, plan-and-execute, and tool registry to lift actionability above 3.

Fill in the empty Sharp Edges 'Solution' column with concrete mitigations (e.g., 'set max_iterations=10 and a stuck detector') so the guidance is actionable.

Remove the verbatim restatement of the description at the top and drop generic explanations of ReAct/plan-and-execute that Claude already knows, to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with clear sections, but it restates the description verbatim and explains concepts Claude already knows (ReAct loop, plan-and-execute), placing it at anchor 3 rather than the leaner anchor 4.	3 / 5
Actionability	The 'javascript' code blocks are non-executable bullet lists and the Sharp Edges 'Solution' column is empty ('Always set limits:', 'Write complete tool specs:' with nothing after), so guidance is present but incomplete/pseudocode-like, matching anchor 3.	3 / 5
Workflow Clarity	The patterns describe rough sequences with implicit feedback (replanning, repeat-until-stuck, max iteration limits) but there is no unified operational workflow or explicit validation checkpoints for Claude to follow, fitting anchor 3.	3 / 5
Progressive Disclosure	No bundle files exist and the single self-contained file is organized into clear, well-signaled sections (Capabilities, Requirements, Patterns, Sharp Edges); minor gaps (empty solutions, verbatim role repetition) keep it at anchor 4 rather than 5.	4 / 5
	Total	13 / 20 Passed

Description

45%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 conveys a clear domain and design philosophy but uses first-person abstract language with no concrete actions and no 'when to use' trigger clause, which caps its completeness and limits trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggering scenarios (e.g., designing agent architectures, multi-agent orchestration, tool/function-calling systems) to raise completeness above 3.

Replace first-person abstract verbs ('I build', 'I design', 'I balance') with third-person concrete actions ('Designs agent loops with iteration limits', 'Implements tool registries with schemas') to lift specificity.

Include natural trigger keywords and synonyms users actually say ('AI agents', 'autonomous agents', 'tool calling', 'multi-agent', 'agent evaluation') to improve trigger-term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names the domain ('AI systems that can act autonomously while remaining controllable') but its actions are abstract and generic ('build', 'design for graceful degradation', 'balance autonomy with oversight') rather than concrete tasks, matching anchor 2; it does not list the specific concrete actions needed for anchor 3.	2 / 5
Completeness	It states a clear 'what' (building controllable autonomous AI systems) but provides no 'when'/'Use when...' trigger guidance, so per the rubric cap it cannot exceed 3; anchor 3 is the best fit.	3 / 5
Trigger Term Quality	It includes some relevant natural terms ('AI systems', 'agents', 'autonomously', 'oversight') but misses common variations a user would actually say ('agent architecture', 'tool calling', 'multi-agent'), fitting anchor 3 rather than the fuller coverage of anchor 4.	3 / 5
Distinctiveness Conflict Risk	The agent-autonomy niche is somewhat specific, but the wording is broad enough to overlap with related AI skills (rag-engineer, prompt-engineer) and lacks distinct trigger phrases, matching anchor 3 rather than the mostly-distinct anchor 4.	3 / 5
	Total	11 / 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-agents-architect/SKILL.md
Commit: 900c504

Reviewed: less than a minute 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.