huashu-material-search

搜索个人素材库1800+条真实经历和观点，为内容增加人味。当用户提到"个人经历"、"真实案例"、"素材"、"人味"时使用。

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%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.

The body is highly actionable with concrete Grep commands and a clear search→rewrite workflow, but it is verbose and monolithic: padded with a promo footer, repeated rewrite guidance, scattered dates, and no use of separate reference files.

Suggestions

Trim padding: remove the self-promo footer ('花叔出品...30万+粉丝...代表作') and the 成功案例/作者推广 block, and consolidate the 改写规范 guidance — currently repeated in 方法A、方法B、改写规范、注意事项 — into a single section.

Isolate time-sensitive details (the '2025.05-2025.10' range, '2025.10最新', '最后更新: 2025-11-07') into one '数据时效' note or a deprecated/old-patterns section so they do not bloat the main flow.

Split the monolithic file: move the four 典型使用场景 long-form rewrite examples and the FAQ into separate reference files (e.g. scenarios.md, faq.md) and link to them one level deep, keeping SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly useful domain guidance, but padded with a self-promo footer ('花叔出品...30万+粉丝...代表作：小猫补光灯'), rewrite rules repeated across 方法A/方法B/改写规范/注意事项, and scattered time-sensitive dates ('2025.05-2025.10', '2025.10最新', '最后更新: 2025-11-07') outside any deprecated section.	2 / 3
Actionability	Provides concrete, copy-paste-ready Grep commands with exact parameters ('output_mode: content', '-n: true', '-i: true', '-C: 2') and specific pattern examples — fully executable rather than pseudocode.	3 / 3
Workflow Clarity	Methods A and B give a clear search → extract → rewrite sequence with numbered steps, and the FAQ supplies error recovery ('搜索不到相关素材怎么办'); the task is read-only so no validation checkpoint is required.	3 / 3
Progressive Disclosure	A ~360-line monolithic SKILL.md with no bundle files; the four detailed scenarios, full rewrite examples, and FAQ are inline rather than split into one-level-deep reference files, though section headers are clear.	2 / 3
	Total	10 / 12 Passed

Description

90%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 clearly states what the skill does and when to trigger it with natural user keywords. Its only gap is naming a single action rather than enumerating multiple concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ('个人素材库1800+条真实经历和观点') and one concrete action ('搜索') plus purpose ('为内容增加人味'), but does not list multiple distinct actions — matching 'names domain and some actions, but not comprehensive' rather than the multi-action level above.	2 / 3
Completeness	Explicitly answers both what ('搜索个人素材库...为内容增加人味') and when ('当用户提到...时使用') with explicit trigger guidance, in third-person voice.	3 / 3
Trigger Term Quality	Includes natural quoted triggers a user would actually say — '个人经历'、'真实案例'、'素材'、'人味' — giving good coverage of natural terms rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	Clear niche — a personal material library for adding human touch to content — with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alchaincyf/huashu-skills
Path: huashu-material-search/SKILL.md
Commit: 35e7cf3

Reviewed: 12 days ago

Table of Contents

Discovery Implementation Validation

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.