CtrlK
BlogDocsLog inGet started
Tessl Logo

spec-interview

进行深入访谈以收集需求并编写详细的规格说明书 (spec)

64

Quality

75%

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 ./.cursor/skills/spec-interview/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%

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 concise, well-structured methodology skill that provides concrete tooling, a clear sequenced workflow with confirmation loops, and well-organized sections without verbose padding.

DimensionReasoningScore

Conciseness

The body is lean and well-organized with no padding or explanation of concepts Claude already knows; each principle and section earns its place (e.g., the probe list under '问非显而易见的问题' is concrete and useful).

3 / 3

Actionability

It gives concrete, actionable guidance: a specific tool ("通过 `AskUserQuestion`"), a cadence ("每轮…2-4 个问题"), six concrete question domains, a specific output path ("docs/specs/<feature-name>.md"), and a sequenced process.

3 / 3

Workflow Clarity

The "访谈流程" is a clear 4-step sequence with feedback/confirmation loops (synthesize and follow up on gaps, periodically summarize to confirm understanding); since this is conversational rather than a destructive/batch operation, no validation cap applies.

3 / 3

Progressive Disclosure

At ~46 lines with a single purpose and no need for external references, the well-organized sections (概述, 核心原则, 问题领域, 访谈流程, 输出, 调用) satisfy the simple-skill allowance for a top progressive-disclosure score.

3 / 3

Total

12

/

12

Passed

Description

50%

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 the skill's purpose clearly with several relevant terms, but it omits an explicit usage trigger and relies on process-level verbs, leaving it at a mid-level score across all dimensions.

Suggestions

Add an explicit 'Use when…' clause naming natural trigger phrases (e.g., 'Use when the user wants to define requirements, write a spec, or scope a new feature').

Sharpen the action verbs into more concrete capabilities (e.g., 'conduct multi-round requirement interviews, probe edge cases and tradeoffs, and draft spec documents').

Include common natural variations users would say ('规格', '需求文档', '功能设计', 'technical spec') to broaden trigger coverage.

DimensionReasoningScore

Specificity

Names the domain and several actions ("进行深入访谈", "收集需求", "编写详细的规格说明书"), but these are high-level process verbs rather than concrete capabilities like 'fill forms, merge documents'.

2 / 3

Completeness

It states what the skill does but provides no explicit 'when should Claude use it' trigger; per the judging guidelines a missing 'Use when…' clause caps completeness at 2.

2 / 3

Trigger Term Quality

Includes relevant keywords ("访谈", "需求", "spec") a user might say, but lacks a 'Use when…' clause and misses common natural variations, matching the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

The interview-to-spec niche is somewhat specific but could still overlap with general requirements-gathering or planning skills, matching the 'somewhat specific but could still overlap' anchor.

2 / 3

Total

8

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
4thfever/cultivation-world-simulator
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.