CtrlK
BlogDocsLog inGet started
Tessl Logo

huashu-info-search

多渠道搜索新产品新技术,交叉验证后存入知识库。当用户提到"最新信息"、"新产品"、"搜索资料"、"查资料"、"了解XX"时使用。

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./huashu-info-search/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 body is well-structured and provides concrete, actionable guidance for searching and saving knowledge, but it is held back by an implicit (rather than explicitly sequenced) workflow, missing verification checkpoints, and token-wasting self-promotional padding that should be removed.

Suggestions

Remove the self-promotional signature footer ('花叔出品 | AI Native Coder…') and deduplicate the trigger list under '## 何时使用' against the frontmatter description to tighten the token budget.

Rewrite the core flow as an explicit numbered sequence (search multi-channel → cross-verify against authoritative sources → resolve conflicts → save to knowledge base) with an explicit verification checkpoint before saving.

Move the full save-format markdown template into a referenced file (e.g. references/save_template.md) so SKILL.md stays a lean overview pointing one level deep, which would also let progressive_disclosure reach the top anchor.

DimensionReasoningScore

Conciseness

Mostly efficient with bullet lists and short headers, but includes unnecessary padding — the self-promotional signature block ('花叔出品 | AI Native Coder · 独立开发者…') and the repeated trigger list under '## 何时使用' that duplicates the frontmatter description — so it falls at 'mostly efficient but includes some unnecessary explanation or could be tightened'.

3 / 5

Actionability

Gives concrete, actionable guidance for an instruction-only skill: a file naming convention '[主题]-[时间].md', specific save paths, a copy-paste-ready markdown save template, and concrete keyword combos like '"AI detection 2025"', placing it at 'mostly executable guidance; concrete with minor gaps'.

4 / 5

Workflow Clarity

The search → verify → save flow is only implicitly conveyed via the '核心功能' list rather than an explicitly numbered sequence, and while '注意事项' offers some validation guidance (优先采信权威来源, 标注来源和时间), there are no explicit verification checkpoints in the flow, matching 'steps listed but validation gaps; checkpoints missing or implicit'.

3 / 5

Progressive Disclosure

No bundle files exist, and the body is well-organized into clearly signaled sections (何时使用, 核心功能, 搜索策略, 知识管理, 注意事项), but at ~80 lines with the promotional footer and no external reference split, it sits at 'good structure; most content appropriately placed; minor organization gaps' rather than the lean top anchor.

4 / 5

Total

14

/

20

Passed

Description

91%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.

A strong, concise description that clearly states both what the skill does and when to use it, with a rich set of natural Chinese trigger phrases and synonyms. It is held back only slightly by a relatively broad 'search info' framing that could overlap with other research skills.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions — '多渠道搜索' (multi-channel search), '交叉验证' (cross-verify), and '存入知识库' (save to knowledge base) — comparable to 'lists several specific actions; minor gaps', though it stops short of fully comprehensive coverage of what 'knowledge base' management entails.

4 / 5

Completeness

Explicitly answers both 'what' (multi-channel search, cross-verify, save to knowledge base) and 'when' with concrete trigger phrases via '当用户提到…时使用', matching the top anchor that requires both what AND when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Provides a comprehensive set of natural trigger phrases users would say — '最新信息', '新产品', '搜索资料', '查资料', '了解XX' — including synonyms (搜索资料/查资料) and varied phrasings, matching the 'comprehensive coverage including synonyms' anchor.

5 / 5

Distinctiveness Conflict Risk

Has a clear niche (new product/tech research + knowledge-base storage) with specific trigger terms that reduce misfiring, but the broad 'search/look up info' framing carries minor overlap risk with general research skills, placing it at 'mostly distinct; minor overlap risk' rather than fully distinct.

4 / 5

Total

18

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

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.