ai-agent-dev

用于 AI Agent 开发岗位面试出题；覆盖 Agent 架构、LLM 调用、工具集成、MCP 协议、RAG、上下文工程与多 Agent 协作，强调工程落地与故障处理能力。

Quality

73%

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 ./app/src/main/resources/skills/ai-agent-dev/SKILL.md

Quality

Content

80%

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

The body is concise and actionable interview-question guidance, but workflow checkpoints are implicit and the lone referenced file (ai-agent-dev.md) is missing from the bundle, weakening progressive disclosure.

Suggestions

Create the referenced ai-agent-dev.md (or place it in a references/ directory) and link it explicitly, e.g. 'See references/ai-agent-dev.md for category-grouped question banks.'

Add an explicit verification checkpoint in the workflow, e.g. 'Before finishing, confirm each question has a tradeoff point and at least one quantifiable metric.'

Make the Additional Resources references clearly one-level-deep with markdown links rather than a flat category-to-file tag list.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept-explanation padding; each instruction (gradient, tradeoff points, quantifiable metrics, scenario questions) earns its place, matching the 'lean and efficient' anchor.	3 / 3
Actionability	Provides concrete, specific guidance (e.g. '每个主问题必须包含至少一个权衡点', '至少一次要求候选人给出可量化指标（如 TTFT、P99 延迟）'); as an instruction-only skill this is actionable without code.	3 / 3
Workflow Clarity	A numbered graded sequence exists (confirm stack → gradient questions → tradeoffs → quantifiable metrics), but the steps' validation checkpoints are implicit rather than explicit, fitting 'sequence present but checkpoints missing or implicit'.	2 / 3
Progressive Disclosure	Sections are organized and reference a single file (ai-agent-dev.md), but that referenced file does not exist in any bundle directory and the 'Additional Resources' mapping of category tags to one file is not clearly signaled one-level-deep navigation.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 is specific and occupies a clear niche, but lacks an explicit 'Use when...' trigger and natural user-facing keywords, capping completeness and trigger-term quality at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when preparing interview questions for AI Agent development roles covering LangChain/Spring AI, MCP, RAG, or multi-agent systems.'

Include common natural-language terms a hiring manager would say (e.g. 'agent interview questions', 'LangChain interview', 'MCP interview prep') to improve trigger-term coverage.

Consider switching to third-person action verbs framing the skill's action (e.g. 'Generates AI Agent developer interview questions...').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete coverage areas ('Agent 架构、LLM 调用、工具集成、MCP 协议、RAG、上下文工程与多 Agent 协作') plus explicit actions ('面试出题', '工程落地与故障处理能力'), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly states the 'what' (interview question generation covering listed topics) but the 'when' is only implied with no explicit trigger guidance; per guidelines a missing 'Use when...' clause caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant domain keywords (MCP 协议, RAG, 上下文工程) a specialist might say, but lacks common natural-user variations and has no 'Use when...' trigger phrase, fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	Targets a narrow niche (AI Agent dev interview question generation) with distinct domain triggers, making it unlikely to conflict with other skills — the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Snailclimb/interview-guide
Path: app/src/main/resources/skills/ai-agent-dev/SKILL.md
Commit: 0780137

Reviewed: 3 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.