nsfc-abstract

当用户明确要求"写/润色 NSFC 标书摘要""生成中文摘要和英文摘要""把中文摘要翻译成英文摘要"时使用。输出中文、英文两个版本（英文必须是中文的忠实翻译版），同时输出标题建议（1个推荐标题+5个候选标题及理由）。中文摘要默认≤400字符，英文摘要默认≤4000字符。输出方式：将结果写入工作目录下的 `NSFC-ABSTRACTS.md`。⚠️ 不适用：用户只想翻译一段与标书无关的通用文本（应直接翻译）；用户只想写立项依据/研究内容/研究基础正文（应使用对应 nsfc 系列 skill）。

Quality

96%

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

92%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.

A dense, highly actionable skill body with an excellent validation-driven closed-loop workflow and well-structured references. Its only weakness is conciseness: shared-infra boilerplate and a bug-collection workflow sit inline alongside the core abstract guidance.

Suggestions

Move the bensz-collect-bugs workflow and the canonical 公共硬约束 block out of the main flow (e.g., into a shared constraints reference) so the body stays focused on abstract generation.

Trim the repeated 输入 sub-section (lines 22-24 duplicate the earlier 输入 block at lines 9-18) to remove redundant tokens.

Dimension	Reasoning	Score
Conciseness	The core abstract-writing guidance is lean and assumes Claude's competence, but tangential boilerplate — the bensz-collect-bugs workflow (lines 28-30) and the canonical 公共硬约束 block (lines 134-142) — adds tokens not specific to producing abstracts. Fits 'efficient; minor instances that could be trimmed' rather than the fully-lean 5 anchor.	4 / 5
Actionability	Provides copy-paste-ready commands ('python3 skills/nsfc-abstract/scripts/validate_abstract.py - --json --diff --strict'), a concrete output template with exact heading structure, and precise formatting rules (quote glyphs, no thousands separators), covering the common cases fully.	5 / 5
Workflow Clarity	The hard-limit path is an explicit closed loop — '先检测，再压缩，再检测，合格后再写入' with up to 3 retry rounds, P0/P1/P2 compression priority, and a validation script checkpoint, then escalation to the user — matching the explicit-validation-with-feedback-loops anchor.	5 / 5
Progressive Disclosure	Body points to real one-level-deep bundle files (references/info_form.md, references/title-rules.md, scripts/validate_abstract.py, scripts/write_abstracts_md.py) that exist on disk, with bulk detail (title rules, validation logic) correctly split out and clearly signaled.	5 / 5
	Total	19 / 20 Passed

Description

100%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.

An unusually complete description: it states concrete outputs, names natural trigger phrases, and draws explicit boundaries against adjacent skills. Token-efficient and third-person in voice, with no fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '输出中文、英文两个版本（英文必须是中文的忠实翻译版）', '输出标题建议（1个推荐标题+5个候选标题及理由）', '写入工作目录下的 NSFC-ABSTRACTS.md', with explicit char limits — giving comprehensive coverage of what the skill produces.	5 / 5
Completeness	Explicitly answers both 'what' (output ZH+EN versions + title suggestions, write to file) and 'when' ('当用户明确要求…时使用'), and adds an explicit 不适用 boundary section, matching the anchor that clearly answers both with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrasings as triggers — '写/润色 NSFC 标书摘要', '生成中文摘要和英文摘要', '把中文摘要翻译成英文摘要' — covering synonyms (写/润色/生成/翻译) a user would actually say, matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear NSFC-abstract niche and explicitly redirects non-matching cases to other skills ('应使用对应 nsfc 系列 skill'), minimizing conflict risk as in the clear-niche anchor.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: huangwb8/ChineseResearchLaTeX
Path: skills/nsfc-abstract/SKILL.md
Commit: dd19421

Reviewed: 4 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.