CtrlK
BlogDocsLog inGet started
Tessl Logo

market-research

进行市场调研(Market Research)、竞品分析(Competitive Analysis)、投资者尽职调查(Investor Due Diligence)以及行业情报(Industry Intelligence)收集,提供来源归因与面向决策的总结。适用于用户需要市场规模估算(Market Sizing)、竞品对比、基金研究、技术扫描或为商业决策提供参考的场景。

70

Quality

86%

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

72%Weight 40%Scale 1-3

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

A concise, well-organized framework that sets clear research standards, collection targets, an output structure, and a pre-delivery quality gate. It is weaker on actionability (no worked examples) and workflow clarity (no explicit error-recovery loop).

Suggestions

Add one concrete worked example for the hardest mode — e.g., a short top-down + bottom-up TAM calculation showing the explicit assumptions — to lift actionability from framework-level to copy-paste-ready.

Turn the 质量门禁 into an explicit validate→fix→re-validate loop: state that if any gate item fails, the report must be corrected and re-checked before delivery, so the feedback loop is not just implied.

Reframe 调研标准 items 4–5 ('将发现转化为决策建议', '明确区分事实、推断和建议') as concrete output signals (e.g., a labeled 'Recommendations' subsection with evidence citations) instead of abstract directives.

DimensionReasoningScore

Conciseness

Lean bullet/numbered lists with no padding or explanation of concepts Claude already knows ('产出支持决策的研究报告,而非流于形式的研究'), assuming Claude's research competence — every token earns its place rather than the 2-level 'could be tightened' anchor.

3 / 3

Actionability

Concrete collection lists ('基金规模、阶段和典型支票额度', '产品现状,而非营销文案'), a numbered output format, and a quality-gate checklist provide real guidance, but it lacks worked examples (e.g., a sample TAM calculation or dossier) and mixes in abstract directives ('将发现转化为决策建议'), so it stops short of fully copy-paste-ready guidance.

2 / 3

Workflow Clarity

The '质量门禁' checklist is an explicit pre-delivery validation checkpoint, but the overall flow is a standards/framework layout rather than a tightly sequenced end-to-end workflow, and there is no explicit validate→fix→re-validate error-recovery loop, leaving it at the 'sequence present but checkpoints implicit' level rather than 3.

2 / 3

Progressive Disclosure

A single self-contained file (~70 lines) with clear section headers (何时激活, 调研标准, 常用调研模式, 输出格式, 质量门禁), no nested references and no content that needs splitting out — easy navigation per the simple-skill scoring note.

3 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 strong, third-person description that states concrete capabilities, provides bilingual natural trigger terms, and includes an explicit '适用场景' activation clause with a clear niche. No over-claims or fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions in third person ('进行市场调研...竞品分析...投资者尽职调查...行业情报收集...提供来源归因与面向决策的总结'), matching the 'Lists multiple specific concrete actions' anchor rather than the partial-coverage anchor at 2.

3 / 3

Completeness

Explicitly answers what ('进行市场调研...提供来源归因与面向决策的总结') and when ('适用于用户需要市场规模估算、竞品对比、基金研究、技术扫描或为商业决策提供参考的场景'), an explicit 'Use when'-equivalent clause, so it is not capped at 2.

3 / 3

Trigger Term Quality

Covers natural terms users would say in both Chinese and English ('市场调研/Market Research', '竞品分析/Competitive Analysis', '市场规模估算/Market Sizing', '基金研究', '技术扫描'), giving good variation coverage beyond the 2-level single-term anchor.

3 / 3

Distinctiveness Conflict Risk

The market-research / diligence / sizing niche has distinct triggers unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor rather than the overlapping-skill anchor at 2.

3 / 3

Total

12

/

12

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.

Validation15 / 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
xu-xiang/everything-claude-code-zh
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.