CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

idea-refiner

막연한 1문장 아이디어를 타겟, 문제, 가치제안, 차별점이 있는 아이디어 정의서로 정제한다.

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A lean, highly actionable single-file instruction skill: exact questions, a copy-paste output template, and concrete quality gates with no wasted tokens. The only weaknesses are minor — the workflow sequence is implicit in section order rather than explicit, there is no worked input→output example, and handling of missing inputs is left unstated.

DimensionReasoningScore

Conciseness

The body is a lean ~55 lines with zero explanation of concepts Claude already knows; every line is either behavioral direction ("전략 컨설턴트처럼 질문한다. 좋은 말로 포장하는 것이 아니라, 고객과 문제가 선명해질 때까지 좁힌다"), an exact question, template scaffolding, or a quality rule. Every token earns its place, matching anchor 5.

5 / 5

Actionability

The skill provides a copy-paste-ready output template (the fill-in elevator pitch formula "[누가] [어떤 상황]에서 [어떤 문제]를 겪을 때...", the 5-block value proposition table, and the alternatives/differentiation table) plus an exact list of five questions and concrete banned-word quality rules ("모두", "누구나", "편리하게"). It falls short of anchor 5 only through minor gaps: no worked input→output example, and the 입력 section does not say how to obtain the inputs when the user has not supplied them.

4 / 5

Workflow Clarity

A clear sequence is implied by section order (gather inputs → ask at most 5 questions, capped by "최대 5개만 묻는다" → fill the template → apply 품질 기준), and the quality bar acts as an explicit checkpoint ("타겟이 너무 넓으면 실패다"). It matches anchor 4 rather than 5 because the ordering is implicit in section layout rather than an explicit numbered workflow, and missing-input handling is unspecified; it is above anchor 3 because validation criteria are present and unambiguous.

4 / 5

Progressive Disclosure

This is a single self-contained file with no bundle directories (references/, scripts/, assets/ are absent) and nothing that belongs in a separate file — the question list, template, and quality rules are all appropriately inline at ~55 lines. Sections (역할/입력/질문 패턴/출력 형식/품질 기준) are well-organized and easy to navigate, which per the simple-skill guidance merits a 5.

5 / 5

Total

18

/

20

Passed

Description

75%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 states a concrete, third-person 'what' with enumerated output components and is backed by explicit, natural trigger terms in the frontmatter, giving it good discoverability and low conflict risk. Its main limitations are the absence of an inline use-when clause in the description text itself and somewhat limited synonym coverage in the triggers.

Suggestions

Add an inline use-when clause to the description itself (e.g., "창업자가 막연한 아이디어를 구체화해야 할 때 사용한다") instead of relying solely on the separate triggers field.

Broaden trigger terms with common synonyms users would naturally say, such as "사업 아이디어", "스타트업 아이디어", "아이디어 구체화", "피치 문장".

Mention the interaction mode in the description (asks up to 5 clarifying questions before producing the definition document) to sharpen the 'what' further.

DimensionReasoningScore

Specificity

The description specifies a concrete input ("막연한 1문장 아이디어"), a transformation ("정제한다"), and four enumerated output components ("타겟, 문제, 가치제안, 차별점이 있는 아이디어 정의서"), which is more concrete than the anchor-3 example. It is not 5 because it names only one action verb rather than multiple distinct concrete actions.

4 / 5

Completeness

The 'what' is clear and concrete (refine a vague one-sentence idea into a structured idea definition document), and the 'when' is supplied as equivalent explicit trigger guidance via the dedicated frontmatter "triggers" list (아이디어 정제, 엘리베이터 피치, 아이디어 정의서, 1문장 아이디어). It matches anchor 4 rather than 5 because the description text itself contains no inline 'Use when...' phrasing and the trigger coverage could be more extensive.

4 / 5

Trigger Term Quality

The frontmatter trigger guidance lists four natural Korean phrases users would actually say ("아이디어 정제", "엘리베이터 피치", "아이디어 정의서", "1문장 아이디어") and the description repeats "아이디어 정의서". Good coverage but missing common synonyms and variations (e.g., 사업 아이디어, 스타트업 아이디어, 피치 만들기), so it does not reach the comprehensive synonym-level coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The niche (early-stage idea refinement producing an elevator pitch / idea definition document) is clearly distinct, and triggers like "아이디어 정의서" are unlikely to fire for unrelated skills. Minor overlap risk remains with pitch-deck/presentation or general brainstorming skills via "엘리베이터 피치", fitting anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

retention-corp/road-to-founders

Path

skills/idea-refiner/SKILL.md

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.