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

62%

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

71%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 content is a well-sequenced, concise, and actionable instruction set for conducting AI Agent interviews, with concrete examples and a clear gradient. Its main weakness is progressive disclosure: the single referenced resource file does not exist in the bundle.

Suggestions

Create the referenced ai-agent-dev.md (under references/) so the category-to-file navigation actually resolves, or remove the reference if no bundle is intended.

Format the Additional Resources links as explicit relative paths (e.g., [ai-agent-dev.md](references/ai-agent-dev.md)) so the one-level-deep references are clearly signaled and clickable.

Add a brief feedback/checkpoint step (e.g., re-confirm candidate stack mid-interview and adjust depth) to push workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is lean with numbered, specific instructions and no padding about concepts Claude already knows; the Overview persona framing ('而不是只会描述概念') is slightly more editorial than strictly necessary, keeping it just below the 'every token earns its place' 5 anchor.	4 / 5
Actionability	As an instruction-only skill the guidance is concrete and actionable — specific追问 targets (协议选型、Token 预算分配、错误重试策略、可观测性指标) and concrete example metrics (TTFT、P99、召回率、Token 利用率) plus a scenario question ('线上 Agent 出现幻觉循环，你怎么排查'), fitting 'mostly executable guidance with minor gaps' rather than fully copy-paste-ready 5.	4 / 5
Workflow Clarity	A clear six-step sequenced process with an explicit gradient (使用经验 -> 原理机制 -> 边界与故障 -> 优化与权衡) is present; this is not a destructive/batch operation so the validation cap does not apply, but it lacks explicit feedback/checkpoint loops, placing it at 4 rather than 5.	4 / 5
Progressive Disclosure	The Additional Resources section attempts one-level-deep, category-signaled navigation (AGENT_BASIS / LLM_CALLING / ... -> ai-agent-dev.md), but the referenced ai-agent-dev.md does not exist in any references/ bundle, so the navigation points to a missing file and the structure is only partially realized.	3 / 5
	Total	15 / 20 Passed

Description

53%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, specific niche and good topic coverage but lacks an explicit 'Use when...' trigger clause and relies on a single concrete action, capping completeness and trigger quality at the mid level. It is distinctive but would benefit from explicit trigger guidance.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., when preparing interview questions for an AI Agent developer role).

Reframe the topic list as concrete actions the skill performs (e.g., '生成梯度面试题、设计权衡追问、要求可量化指标') rather than only listing coverage areas.

Include natural user-facing trigger phrases or synonyms (面试题、面试官、Agent 岗位、出题) to improve trigger term quality.

Dimension	Reasoning	Score
Specificity	The description names the domain (AI Agent 开发岗位面试出题) and lists multiple coverage areas (Agent 架构、LLM 调用、MCP 协议、RAG、上下文工程、多 Agent 协作), but the only concrete action is '出题' (question setting); the topic list is coverage rather than distinct actions, so it sits at the 'names domain and 1-2 concrete actions' level rather than the 'lists several specific actions' level above.	3 / 5
Completeness	It clearly states the 'what' (interview question generation across the listed topics) but provides no explicit 'when/Use when...' clause; per the guideline a missing trigger clause caps completeness at 3, and the 'when' is only weakly implied.	3 / 5
Trigger Term Quality	Relevant niche keywords are present (AI Agent、面试、MCP、RAG、多 Agent) that a user needing this skill might say, but there are no natural 'Use when...' trigger phrases and limited synonym/variation coverage, matching 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The niche is clear and specific (AI Agent dev interview question setting) with low conflict risk; it is mostly distinct with only minor overlap against general interview-question skills, fitting 'mostly distinct; minor overlap risk' rather than the fully-distinct 5 anchor.	4 / 5
	Total	13 / 20 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: b2d1ca0

Reviewed: 19 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.