CtrlK
BlogDocsLog inGet started
Tessl Logo

sima-qian-style

将现代文本改写为司马迁《史记》文笔风格。 **触发场景**(主动使用): - 用户明确要求"用太史公文笔改写"、"以史记风格写..."、"太史公曰"、"列传体" - 用户要求将现代文本转为文言文,且强调古雅、简洁、有文史韵味 - 用户提供人物传记、历史事件、技术概念等素材,要求古风改写 - 用户询问"司马迁会怎么写这件事" **功能**: - 三层转换:现代名词古化 → 白话转文言 → 太史公风格 - 应用《史记》特有句式(开篇定式、层递并列、简短断言、对话穿插动作等) - 应用《史记》修辞(白描、先抑后扬、排比对仗、跳跃式剪辑等) - 可选输出"太史公曰"评论段(50-80字精简版) **不做什么**: - 不复述《史记》原文内容 - 不模拟司马迁的历史观点 - 不套用《史记》名句 - 只学习语言形式、句法结构、修辞节奏 本技能基于《史记》130篇语料分析,适用于人物传记、历史事件、技术概念等现代素材的古风改写。

72

Quality

88%

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

77%

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 templates and a clear three-step workflow, but it runs long and repeats content, and one referenced bundle path is missing. Tightening the duplication and fixing the dangling evals/ reference would lift the weaker dimensions.

Suggestions

Remove the duplication between the inline step-6 self-check and the standalone 自检功能 section, and drop the redundant 触发示例 block since triggers already live in the frontmatter.

Trim the 太史公曰 deletion walkthrough to a single before/after pair to reduce token weight without losing the lesson.

Create the referenced `evals/` directory with the four named examples, or remove the reference so progressive_disclosure points only to real files.

DimensionReasoningScore

Conciseness

The ~500-line body is mostly valuable novel content (史记句式/修辞) but is padded with repetition — the self-check list appears both inline in step 6 and again as a top-level section, trigger examples duplicate the frontmatter, and the 太史公曰 deletion walkthrough is lengthy — so it could be tightened rather than being lean end-to-end.

2 / 3

Actionability

Provides copy-paste-ready patterns and templates — 'X者,Y也', '其所为有二:其一...其二...', the 对话场景 action/emotion/atmosphere template, and a worked 会议争论 example — giving concrete, specific guidance even without code.

3 / 3

Workflow Clarity

A clear three-step sequence (古化名词 → 转文言 → 太史公风格) with a 素材类型→文体 dispatch table and explicit self-check checklists serving as validation checkpoints; the destructive/batch cap does not apply to this text-rewriting skill.

3 / 3

Progressive Disclosure

The three core references (modern-terms.md, classical-chinese.md, style-features.md) are real, one level deep, and well-signaled with 🔊 links, but the body still carries substantial inline material that could be externalized and references a non-existent `evals/` directory, so structure is good but imperfect.

2 / 3

Total

10

/

12

Passed

Description

100%

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 specific, well-triggered, and complete, covering both what the skill does and when to use it with natural user-facing phrases. Its distinct niche keeps conflict risk low.

DimensionReasoningScore

Specificity

Names multiple concrete actions — '三层转换', '应用《史记》特有句式', '应用《史记》修辞', '可选输出太史公曰评论段' — paralleling the 'extract, fill, merge' style of the 3-anchor example rather than vague abstractions.

3 / 3

Completeness

Explicitly answers both 'what' (the 功能 list) and 'when' (a dedicated 触发场景 list with multiple triggers), matching the anchor that requires both an explicit what and explicit when.

3 / 3

Trigger Term Quality

Quotes natural user phrases such as '用太史公文笔改写', '以史记风格写...', '太史公曰', '列传体', and '司马迁会怎么写这件事', giving good coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (司马迁《史记》文笔改写) with distinctive triggers like '太史公曰' and '列传体', making it unlikely to fire for unrelated skills.

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

skill_md_line_count

SKILL.md is long (529 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
baojie/shiji-kb
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.