CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

22

Quality

11%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

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

SKILL.md
Quality
Evals
Security

Quality

Content

22%Scale 1-3

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 overview or table of contents than actionable guidance. The patterns are described conceptually without executable code, the anti-patterns are empty headers, and the Sharp Edges table is truncated with incomplete solutions. Claude would gain very little actionable knowledge from this content beyond what it already knows about agent architectures.

Suggestions

Replace the pseudocode bullet lists in Patterns with actual executable code examples (e.g., a working ReAct loop implementation in Python/JavaScript with iteration limits).

Complete the Sharp Edges table by providing actual code snippets or concrete solutions for each issue instead of truncated text ending with colons.

Fill in the Anti-Patterns sections with concrete examples of what bad implementations look like and why they fail, or remove the empty headers.

Add validation/verification steps to the workflow patterns, such as how to detect when an agent is stuck in a loop or how to test tool integrations.

DimensionReasoningScore

Conciseness

The skill has some unnecessary filler (e.g., repeating the description in the body, listing 'Requirements' that Claude already knows, the vague 'When to Use' section). However, the patterns and sharp edges sections are reasonably compact.

2 / 3

Actionability

The content is almost entirely abstract and descriptive. The 'patterns' sections contain bullet-point descriptions rather than executable code. The Sharp Edges table lists solutions but truncates them (e.g., 'Always set limits:' with no actual code or example). There is nothing copy-paste ready or concretely executable.

1 / 3

Workflow Clarity

While patterns like ReAct and Plan-and-Execute are mentioned, they are described at a conceptual level with no concrete sequencing, validation checkpoints, or error recovery steps. The Sharp Edges table hints at solutions but never completes them.

1 / 3

Progressive Disclosure

There is some structural organization with sections (Patterns, Anti-Patterns, Sharp Edges, Related Skills), but anti-patterns are listed as headers with no content, the Sharp Edges table has incomplete entries, and there are no references to deeper documentation files for advanced topics.

2 / 3

Total

6

/

12

Passed

Description

0%Scale 1-3

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 capability statement written in first person ('I build', 'I understand', 'I design') rather than a functional skill description. It lacks concrete actions, natural trigger terms, explicit 'when to use' guidance, and any distinguishing specificity that would help Claude select it appropriately from a pool of skills.

Suggestions

Rewrite in third person and list specific concrete actions, e.g., 'Designs agent architectures with tool-use loops, implements retry/fallback logic, adds human-in-the-loop checkpoints, and defines escalation policies for autonomous AI systems.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about building AI agents, designing agentic workflows, implementing tool-use patterns, or adding human oversight to autonomous systems.'

Narrow the scope to a distinct niche to reduce conflict risk, e.g., focus on 'agentic workflow design' or 'agent reliability patterns' rather than the broad concept of 'AI systems that act autonomously.'

DimensionReasoningScore

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 (building AI agent systems) 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 and could overlap with any skill related to AI, agents, automation, or system design. There are no distinct triggers or a clear niche to differentiate it.

1 / 3

Total

4

/

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.