CtrlK
BlogDocsLog inGet started
Tessl Logo

nsfc-humanization

去除 NSFC 标书中的 AI 机器味,尤其适用于“不是…而是…”式伪对立、模板化转折、抽象概念堆叠、边界声明过重、研究动作不清的标书段落,使文本读起来像资深领域专家亲笔撰写(不适用:非标书内容/需修改格式/需补充新内容)

67

Quality

81%

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

85%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-structured, actionable instruction-only skill with a clear validated workflow and appropriate offloading of detailed examples to one reference. The only weaknesses are minor redundancy between the 硬规则 and 受保护片段 sections and the lack of inline before/after examples.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (no explanation of NSFC/LaTeX), but 硬规则 and 受保护片段 repeat overlapping protection lists (LaTeX commands, math, citations, numbers), a minor redundancy that could be tightened.

4 / 5

Actionability

Concrete rewriting directives (e.g. "把 B 放入句子主干,必要时把 A 改成前置边界或背景从句") and a 9-step workflow give actionable guidance, but common before/after examples are delegated to the reference rather than shown inline.

4 / 5

Workflow Clarity

A clear 9-step sequence with explicit validation checkpoints (step 7 structure/protected-fragment check, step 8 self-eval rounds) and a feedback loop prioritizing zero-loss; the destructive/batch cap does not apply because validation is present.

5 / 5

Progressive Disclosure

Well-organized sections (定位, 可选参数, 硬规则, 风格目标, 工作流, 参考) with a single clearly-signaled one-level-deep reference to references/machine-patterns.md, which exists as a real file.

5 / 5

Total

18

/

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 specific, well-scoped, and gives clear trigger and exclusion guidance for a well-defined niche. It is slightly short of top marks because the "when" phrasing is implicit rather than a crisp "Use when…" clause and a few natural synonyms are absent.

DimensionReasoningScore

Specificity

Names the domain (NSFC 标书, AI 机器味) and lists several concrete target patterns ("不是…而是…"式伪对立、模板化转折、抽象概念堆叠、边界声明过重、研究动作不清), though the core action is a single humanization verb rather than multiple distinct actions.

4 / 5

Completeness

Explicitly states what (去除 NSFC 标书中的 AI 机器味) and provides trigger guidance via "尤其适用于…" plus a 不适用 boundary; the "when" is present and reasonably explicit but not phrased as a clean "Use when" trigger, so not a 5.

4 / 5

Trigger Term Quality

Includes natural niche phrases a user would say ("NSFC 标书", "AI 机器味", "不是…而是…"), but misses common synonyms like "润色标书" or "AI 味".

4 / 5

Distinctiveness Conflict Risk

Clear narrow niche (NSFC 标书 humanization) with distinct triggers and an explicit 不适用 boundary, giving minimal conflict risk with other skills.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
huangwb8/ChineseResearchLaTeX
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.