CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

huashu-prompt-save

自动识别Prompt类型并分类保存(技术/内容/教学/产品/通用)。当用户提到"保存prompt"、"记录prompt"、"整理prompt"时使用。

Quality

77%

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-prompt-save/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 a well-organized, reasonably actionable instruction-only skill: concrete naming conventions, a save template, and a clear execution flow. It is held back by redundant sections (核心功能 vs 执行流程), off-topic branding padding, a stale date, and the absence of any post-save validation or index-entry format.

Suggestions

Merge 核心功能 and 执行流程 into a single section to remove the duplicated identify/extract/save/index steps, and drop the author-branding trailer and "最后更新" line.

Add a validation checkpoint after saving (e.g., confirm the file exists in the expected category directory and verify the INDEX.md entry) to close the workflow-clarity gap.

Specify the INDEX.md entry format (columns/fields for 标题、分类、标签、文件名) and how the auto-increment 序号 is determined, and inline or summarize the rules currently delegated to /Prompt梳理/CLAUDE.md.

DimensionReasoningScore

Conciseness

"核心功能" and "执行流程" repeat the same identify/extract/save/index steps, the five-category count is stated twice, and the trailer ("花叔出品 | 公众号「花叔」| 30万+粉丝 | 代表作:小猫补光灯...") plus "最后更新: 2025-11-07" add padding and time-sensitive noise — mostly efficient but with several unnecessary repeated or padded sections.

3 / 5

Actionability

Concrete, executable guidance is present: the naming pattern "prompt-[自动递增序号]-[简短标题].md", the target directory "/Prompt梳理/[分类]/", a full save-format template, and the INDEX.md update step; minor gaps remain since the INDEX.md entry format and the auto-increment mechanism are unspecified. Not a 5 because those key details are missing.

4 / 5

Workflow Clarity

"执行流程" lists a clear five-step sequence (识别类型→提取信息→生成文件名→保存文件→更新索引) with one explicit checkpoint ("如果分类不明确,询问用户意图"), but there is no validation that the file was saved correctly or that the INDEX.md entry was added — checkpoints beyond the ambiguity check are missing or implicit, matching the anchor for 'steps listed but validation gaps'.

3 / 5

Progressive Disclosure

No bundle files exist and the body is organized into clear, well-scoped sections (何时使用、分类规则表、保存格式、执行流程、注意事项) with one clearly signaled external pointer ("/Prompt梳理/CLAUDE.md - Prompt管理规则") — good structure with a minor gap, since the referenced management rules are not inlined or summarized, leaving a small dependency outside the skill.

4 / 5

Total

14

/

20

Passed

Description

82%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 description: it states a clear capability with an enumerated taxonomy and pairs it with an explicit, natural-language trigger clause. The main gap is that it undersells the skill's actual scope (extraction, naming, index updates) and misses a few trigger synonyms the body already knows.

Suggestions

Fold the other concrete actions into the description (e.g., 提取用途/来源/标签、生成规范文件名、更新 INDEX.md) to raise specificity.

Add the natural trigger variants already listed in the body — "存起来"、"帮我整理" — to the trigger clause.

DimensionReasoningScore

Specificity

"自动识别Prompt类型并分类保存(技术/内容/教学/产品/通用)" names the domain and two concrete actions (identify type, classified save) with the five categories enumerated, but omits other capabilities performed (info extraction, index update), matching the '1-2 concrete actions, not comprehensive' anchor rather than the 'several specific actions' anchor.

3 / 5

Completeness

It explicitly answers both 'what' (auto-identify prompt type and save by category across five listed categories) and 'when' with concrete trigger phrases ("当用户提到...时使用"), matching the top anchor; it is not a 4 because the 'when' clause is fully explicit rather than merely present.

5 / 5

Trigger Term Quality

"当用户提到'保存prompt'、'记录prompt'、'整理prompt'时使用" provides three natural phrases users would actually say, matching 'good keyword coverage; a few natural terms missing' — common variants like "存起来" or "帮我整理" (which the body itself lists) are absent from the description.

4 / 5

Distinctiveness Conflict Risk

Prompt saving/classification is a clear niche with distinct, unambiguous triggers ("保存prompt" etc.) that no generic file- or document-handling skill would claim, giving minimal conflict risk.

5 / 5

Total

17

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

alchaincyf/huashu-skills

Path

huashu-prompt-save/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.