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

68%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/nsfc-length-aligner/SKILL.md

Quality

Content

73%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-sequenced, actionable workflow with an explicit re-check feedback loop and real bundle artifacts, scoring high on workflow clarity and actionability. Its main weakness is repetition of the output-directory convention and some boilerplate constraints that hurt conciseness, plus one unlinked reference file.

Suggestions

Consolidate the --out-dir / task-directory convention into a single statement; remove its repetition across 输出, 输出管理, and 公共硬约束 to improve conciseness.

Add an explicit link to references/DEFAULT_STANDARD_NOTES.md where the 示例口径 is discussed, and clarify where config.yaml lives, so all bundle references are signaled from the body.

Trim the boilerplate 公共硬约束 block to only the skill-relevant subset, or move the full canonical constraints to a referenced file to reduce token weight.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (no explainer on what NSFC/PDF is), but the --out-dir / task-directory convention is repeated across 流程, 输出, 输出管理, and 公共硬约束, and some boilerplate constraints pad the tail, so it could be tightened.	3 / 5
Actionability	Provides concrete, mostly copy-paste-ready commands (python3 scripts/check_length.py --input ... --config config.yaml [--pdf] [--out-dir ...]) backed by a real script and reference files, plus concrete 该瘦/该厚 rewrite strategies; only minor gaps remain from placeholder paths like <目标标书路径>.	4 / 5
Workflow Clarity	Clear sequenced workflow (需求确认 → 运行检查 → 解读差距 → 扩写/压缩 → 复检闭环 → 输出) with an explicit validation feedback loop ('改完必须再次运行脚本', '未复检视为未完成') and an action checklist, matching the explicit-checkpoint anchor.	5 / 5
Progressive Disclosure	Good structure with one-level-deep references to scripts/check_length.py and references/MEANING_PRESERVING_REWRITE_RUBRIC.md, and content appropriately split; however references/DEFAULT_STANDARD_NOTES.md is not explicitly linked from the body and config.yaml is referenced but absent from the bundle, leaving minor navigation gaps.	4 / 5
	Total	16 / 20 Passed

Description

62%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 clearly conveys a specific, distinctive niche and concrete actions, but lacks an explicit 'Use when...' trigger clause and natural-term synonyms, capping completeness and trigger-term quality. It is strong on distinctiveness but only adequate on trigger guidance.

Suggestions

Add an explicit 'Use when...' (适用当...) trigger clause naming concrete user phrases such as '国自然标书篇幅超了/不够' or '检查标书页数/字数'.

Include natural synonyms and file cues users actually say (页数, 字数, 超页, 字数不够, main.tex) to broaden trigger-term coverage.

Tighten '篇幅预算标准' to a more concrete action phrasing (e.g. '按 2026 篇幅预算校对标书页数与字符数') to lift specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain (国自然标书篇幅预算) and lists several concrete actions — 检查篇幅并总结差距, 给出针对性优化建议, 扩写/压缩到达标 — but '预算标准' is somewhat abstract, leaving minor coverage gaps versus a fully comprehensive action list.	4 / 5
Completeness	The 'what' is clear and multi-part (check, summarize gaps, advise, rewrite to standard), but there is no 'Use when...' clause or equivalent explicit 'when' guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant domain terms (国自然标书, 篇幅, 预算, 扩写/压缩) are present and would be said by target users, but common synonyms and explicit 'Use when...' trigger phrasing are missing, so coverage is only partial.	3 / 5
Distinctiveness Conflict Risk	The NSFC-proposal length-alignment niche is highly specific with distinct triggers (国自然标书篇幅/预算/扩写压缩), giving minimal overlap risk with other skills.	5 / 5
	Total	15 / 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-length-aligner/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.