CtrlK
BlogDocsLog inGet started
Tessl Logo

huashu-research

结构化网络调研流程,确保调研成果增量保存到文件,不因会话截断丢失。当用户说"调研"、"搜索资料"、"帮我查一下"、"了解一下"、"最新信息"时使用此技能。

62

Quality

73%

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 ./huashu-research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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-structured, actionable research workflow with useful templates and a clear step sequence. Its weaknesses are a missing save-verification checkpoint in a batch process, a dangling SHARED-RULES.md reference, and a promotional footer that pads the context.

Suggestions

Add an explicit verification step after incremental saves (e.g., confirm the file exists and the new entry was appended before continuing), which would lift workflow_clarity above the batch-operation cap of 3.

Resolve the 'SHARED-RULES.md' reference: either inline the source-priority rules or add the file under references/ and link it with a clear path, so the reference is not dangling.

Remove the promotional footer and the '最后更新' date line; they do not help Claude execute the skill and consume context-window budget.

DimensionReasoningScore

Conciseness

The body is efficient with lean bullets and purposeful templates that earn their tokens, but the promotional footer ('花叔出品…30万+粉丝…小猫补光灯') and the '最后更新: 2026-02-06' line are padding that could be trimmed, so it is 'efficient; minor instances of over-explanation' rather than fully lean.

4 / 5

Actionability

Gives concrete path templates and copy-paste markdown templates for both the research file and the final briefing, which is mostly executable guidance; minor gaps remain (e.g., how to assess 可信度 concretely), so it does not reach fully copy-paste-ready coverage of common cases.

4 / 5

Workflow Clarity

The four-step sequence is clear and the every-3-searches stage summary is an explicit checkpoint, but this is a batch operation of repeated incremental saves with no verification that a save succeeded, so per the batch-operation cap workflow clarity cannot exceed 3.

3 / 5

Progressive Disclosure

Sections are well organized and the skill needs no bundle files, but Step 2 references 'SHARED-RULES.md' which is absent from the bundle (no references/ directory), a dangling reference that creates a minor navigation gap and holds it below a clean 5.

4 / 5

Total

15

/

20

Passed

Description

78%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 is strong: it concisely states a clear purpose and supplies explicit, natural trigger phrases answering both what and when. Its main weakness is that the capability list is narrow and some triggers are generic enough to risk overlap with a general search skill.

DimensionReasoningScore

Specificity

Names the domain (structured web research) plus one to two concrete actions ('增量保存到文件', '不因会话截断丢失'), but does not enumerate several specific actions, so it sits at the 'names domain and 1-2 concrete actions' anchor rather than the 'several specific actions' level above.

3 / 5

Completeness

Explicitly answers both 'what' (structured research process with incremental file persistence) and 'when' with concrete trigger phrases via '当用户说…时使用此技能', matching the anchor that requires clear what-and-when with concrete triggers.

5 / 5

Trigger Term Quality

Provides five natural Chinese trigger phrases users would actually say ('调研', '搜索资料', '帮我查一下', '了解一下', '最新信息'), giving good coverage, though a few common variations like '查资料' or '搜集信息' are absent, keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

The research-plus-persistence niche is mostly distinct, but generic triggers such as '帮我查一下' and '了解一下' carry minor overlap risk with a general web-search skill, so it is 'mostly distinct; minor overlap risk' rather than minimal-conflict.

4 / 5

Total

16

/

20

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
alchaincyf/huashu-skills
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.