ai-agents-architect

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.

Quality

59%

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 ./skills/ai-agents-architect/SKILL.md

Quality

Content

57%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 a well-organized, actionable architectural reference with strong pattern and anti-pattern coverage, but it stays monolithic and conversational where tighter prose and a referenced detail file would reduce token load. It also lacks an end-to-end validated workflow for destructive operations.

Suggestions

Trim the 'Why this breaks' explanations to one line each or fold into the symptom list, since Claude already understands these failure mechanics.

Add an explicit validate->fix->retry feedback loop (or reference the worked-example test sequence as a mandatory checkpoint) for destructive and batch operations to lift workflow clarity above the cap.

Move the sharp-edges catalog into a one-level-deep reference file (e.g., SHARP_EDGES.md) with a clearly signaled pointer from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-structured, but the repeated 'Why this breaks' blocks re-explain consequences (e.g., agents getting stuck in loops, silent failures compounding) that Claude already understands.	3 / 5
Actionability	Provides concrete, actionable checklists ('max_iterations on agent loops', 'Return error messages to agent', 'Use structured output (JSON mode, function calling)'); as an instruction-only skill it lacks copy-paste code but the guidance is specific and executable in intent.	4 / 5
Workflow Clarity	Organized as patterns and sharp edges rather than a sequenced workflow; the worked-example test list gives expected outcomes but there is no validate->fix->retry feedback loop for destructive/batch operations, which caps this dimension at 3.	3 / 5
Progressive Disclosure	Single monolithic file with clear section headers but no bundle files; substantial material (e.g., the sharp-edges catalog) that could live in a one-level-deep reference is all inlined, so structure is present but not split.	3 / 5
	Total	13 / 20 Passed

Description

61%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 clearly identifies the domain and its pillars but reads as a capability summary rather than a trigger-oriented pitch, lacking any explicit 'Use when...' guidance. It is specific and mostly distinct but would benefit from a concrete activation clause.

Suggestions

Add an explicit 'Use when...' clause naming the concrete situations that should trigger this skill (e.g., 'Use when designing an agent execution loop, tool boundary, or memory lifecycle for a concrete task').

Reframe the capability list as concrete actions (e.g., 'Designs agent execution loops, defines tool schemas, builds memory and planning systems') to raise specificity.

Include a couple of natural user-facing synonyms ('AI agents', 'autonomous agents', 'multi-agent systems') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete facets ('tool use, memory systems, planning strategies, multi-agent orchestration') but states them as noun phrases rather than concrete actions the skill performs.	3 / 5
Completeness	Has a clear 'what' (designs/builds autonomous AI agents) but no 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant terms ('autonomous AI agents', 'multi-agent orchestration', 'tool use') that a user would plausibly say, though it leans technical and misses a few common synonyms.	4 / 5
Distinctiveness Conflict Risk	Targets a fairly distinct niche (autonomous AI agent architecture) with only minor overlap risk against closely related skills like rag-engineer, prompt-engineer, or mcp-builder.	4 / 5
	Total	14 / 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: sickn33/agentic-awesome-skills
Path: skills/ai-agents-architect/SKILL.md
Commit: b1aebac

Reviewed: ~18 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.