nsfc-length-aligner

基于国自然标书篇幅预算标准；检查目标标书篇幅并总结差距；给出针对性优化建议；在尽量不改变原意的前提下扩写/压缩到达标。

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

85%

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 a clear, validated workflow and well-structured one-level references; its main weakness is repetition of workspace-path and page-convention guidance that could be consolidated for token efficiency.

Suggestions

Consolidate the repeated `.bensz-api/task-.../nsfc-length-aligner/` path convention into a single stated-once rule to save tokens.

State the "≤28 页 / 不缩小字体行距" format red line once in the dedicated 格式红线 section and reference it instead of repeating inline.

Dimension	Reasoning	Score
Conciseness	Content is task-specific and avoids explaining concepts Claude already knows, but repeats conventions — the `.bensz-api/task-.../nsfc-length-aligner/` path and the "≤28 页 / 不缩小字体挤页数" rule each appear multiple times — so it could be tightened; not the lean 3.	2 / 3
Actionability	Provides copy-paste-ready executable commands such as `python3 scripts/check_length.py --input <目标标书路径> --config config.yaml` with real `--pdf`/`--out-dir` flags backed by an existing script, matching the fully-executable anchor.	3 / 3
Workflow Clarity	A clearly sequenced 0–5 workflow with an explicit recheck feedback loop ("改完必须再次运行脚本" / step 5 复检闭环) and an enforcement note ("未复检视为未完成"), matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	Overview points to real one-level-deep materials — `references/MEANING_PRESERVING_REWRITE_RUBRIC.md` and `scripts/check_length.py` both exist and are signaled in the body — with content appropriately split rather than monolithic.	3 / 3
	Total	11 / 12 Passed

Description

82%

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 and distinct, naming concrete actions in third person with natural domain trigger terms, but it omits an explicit "Use when..." clause, which caps completeness at 2.

Suggestions

Append an explicit trigger clause, e.g. "Use when aligning an NSFC proposal to length/page budgets, or when the user says the proposal is too long/short."

Surface common user phrasings like "标书太长/太短", "页数超标", "字数统计" to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person — "检查目标标书篇幅并总结差距；给出针对性优化建议；...扩写/压缩到达标" — comparable to the anchor listing several specific actions; no first/second person to penalize.	3 / 3
Completeness	Clearly answers "what" (check gaps, suggest, expand/compress) but provides no explicit "Use when..." trigger clause; per the guideline a missing explicit trigger caps completeness at 2, so it is not 3.	2 / 3
Trigger Term Quality	Contains natural niche terms a user would say — "国自然标书篇幅预算", "扩写/压缩", "优化建议" — giving good coverage of the trigger vocabulary for this domain.	3 / 3
Distinctiveness Conflict Risk	The NSFC proposal length-alignment niche is specific with distinct triggers, unlikely to fire for unrelated skills; matches the clear-niche anchor.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Path: skills/nsfc-length-aligner/SKILL.md
Commit: 01044a6

Reviewed: 3 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.