grill-me

针对方案或设计的高强度追问式面试（adversarial design review / grill session），暴露假设漏洞与缺失约束，过程中同步维护领域模型（术语表和 ADR）。手动调用 /grill-me。

Quality

80%

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/grill-me/SKILL.md

Quality

Content

77%

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

A well-structured, actionable instruction skill with clear workflow checkpoints and concrete templates. It loses points on conciseness due to duplicated structure explanations and on progressive disclosure because everything sits in one file with no external references.

Suggestions

De-duplicate the file-structure material: present the single-vs-multi-context decision once and reference it rather than repeating the trees and logic in two sections.

Move the CONTEXT.md and ADR format templates into reference files (e.g. references/context-format.md, references/adr-format.md) and link to them from the body to improve progressive disclosure.

Tighten the domain-modeling behavior section by consolidating the five short sub-sections into a single checklist of triggers and responses.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not explain concepts Claude already knows, but it is redundant: the file-structure trees are shown twice and the single-vs-multi-context logic is repeated across '文件结构' and '单上下文 vs 多上下文', so it could be tightened.	2 / 3
Actionability	Despite being instruction-only with no code, the guidance is highly actionable — exact challenge phrasings ('你的术语表把"取消"定义为 X…'), concrete file paths (CONTEXT.md, docs/adr/), a 3-condition ADR checklist, and copy-ready templates.	3 / 3
Workflow Clarity	Clear sequencing with explicit checkpoints: a numbered 启动步骤, the '一次只问一个问题…等我回复' loop, and the hard gate '在我明确确认达成共识之前，不要开始执行方案', plus a code-cross-validation feedback loop for exposing contradictions.	3 / 3
Progressive Disclosure	Well-organized with clear section headers and no nested references, but it is a single monolithic file with no external bundle files; the large CONTEXT.md and ADR format-reference blocks are inline where separate reference files would aid navigation.	2 / 3
	Total	10 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, distinctive description that names concrete actions and natural trigger terms in two languages. Its main weakness is the absence of an explicit 'Use when…' trigger clause, leaving the invocation timing implied rather than stated.

Suggestions

Add an explicit trigger clause such as 'Use when reviewing a proposed design or plan and you want to stress-test its assumptions' to make the 'when' unambiguous.

Consider adding common user phrasings like 'stress-test', '挑刺', or '找漏洞' to broaden natural trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '追问式面试', '暴露假设漏洞与缺失约束', '维护领域模型（术语表和 ADR）' — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly states what the skill does, but the 'when' is only implied via context ('针对方案或设计') and manual-invocation guidance; there is no explicit 'Use when…' clause, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Covers natural trigger terms a user would say in both Chinese ('方案或设计', '追问') and English ('adversarial design review', 'grill session'), giving good coverage of how the need is actually expressed.	3 / 3
Distinctiveness Conflict Risk	The adversarial design review / grill-session niche combined with synchronous domain-model maintenance is a clear, distinct purpose unlikely to trigger for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 missing, 3 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: feiskyer/claude-code-settings
Path: skills/grill-me/SKILL.md
Commit: 45ad30f

Reviewed: about 5 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.