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 use, function calling.

Install with Tessl CLI

npx tessl i github:duclm1x1/Dive-Ai --skill ai-agents-architect

What are skills?

Review — 62%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

96%

48%

Product FAQ Assistant Agent

ReAct loop safeguards

Criteria

Without context

With context

Iteration limit defined

100%

Loop exits on limit

100%

Thought-Action-Observation structure

50%

100%

Tool errors surfaced

100%

Execution is traced/logged

80%

Robust output parsing

40%

80%

Terminates when stuck

37%

100%

Graceful degradation message

75%

100%

README safeguards documented

80%

100%

catalog.json used

100%

Without context: $0.7304 · 2m 45s · 36 turns · 40 in / 10,724 out tokens

With context: $0.9467 · 3m 35s · 40 turns · 332 in / 13,584 out tokens

87%

-4%

Customer Support Agent Toolset

Tool specification and curation

Criteria

Without context

With context

Parameter schema present

100%

Descriptive docstrings

90%

70%

Example calls in registry

20%

50%

Tools scoped to the task

100%

Total tool count reasonable

100%

Tool errors returned

100%

TOOL_REGISTRY implemented

100%

Tool selector implemented

100%

Selector actually filters

100%

58%

mock_data.json used

100%

Without context: $0.6618 · 2m 24s · 31 turns · 35 in / 9,869 out tokens

With context: $0.6108 · 2m 35s · 27 turns · 29 in / 9,804 out tokens

91%

34%

Automated Research Pipeline Architecture

Multi-agent justification and memory management

Criteria

Without context

With context

Planning phase described

10%

100%

Execution phase described

87%

100%

Replanning mentioned

100%

Multi-agent decision justified

25%

Memory is selective

83%

100%

Failure modes documented

100%

Graceful degradation behavior

87%

100%

Pipeline skeleton present

100%

Planner component in code

100%

Memory/state structure in code

87%

100%

Architecture-code alignment

100%

Without context: $0.4405 · 2m 31s · 14 turns · 19 in / 9,940 out tokens

With context: $0.7681 · 4m 6s · 27 turns · 32 in / 14,533 out tokens

Evaluated: about 2 hours ago
Agent: Claude Code

Table of Contents

Product FAQ Assistant Agent Customer Support Agent Toolset Automated Research Pipeline Architecture

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.