CtrlK
BlogDocsLog inGet started
Tessl Logo

nsfc-reviewers

当用户明确要求"评审国自然标书"、"模拟专家评审"、"审阅 NSFC 申请书"时使用。模拟领域专家视角对 NSFC 标书进行多维度评审,输出分级问题与可执行修改建议。⚠️ 不适用:用户只是想写/改标书某个章节(应使用 nsfc-*-writer 系列技能)、只是想了解评审标准(应直接回答)、没有明确"评审/审阅"意图。

68

Quality

85%

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

70%

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, read-only review workflow with clear sequencing, validation checkpoints, and proper progressive disclosure to real bundle files. Its main weaknesses are minor cross-section redundancy and several steps that stay at an abstract rather than fully executable level.

Suggestions

Consolidate the P0→P1→P2 ordering rule into a single 硬规则 statement and reference it from 输出/聚合 instead of restating it three times to improve conciseness.

Make the parallel-vibe invocation step actionable by adding the concrete command/template (e.g., the build_parallel_vibe_plan.py invocation and the parallel-vibe call form) rather than describing it abstractly.

Merge the duplicate 资助额度约束 guidance that appears in both the 资助额度约束识别 workflow step and any overlapping 硬规则 language.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes Claude's knowledge (no concept padding), but contains redundancy — the P0→P1→P2 ordering rule is restated across 输出, 硬规则, and 聚合, and the 资助受限 rule effectively appears twice. It could be tightened, so it sits at score-2 rather than the lean score-3.

2 / 3

Actionability

It provides a concrete runnable command (list_proposal_files.py with flags) and specific config keys, but several workflow steps (generate master prompt, invoke parallel-vibe, aggregate) are described abstractly without copy-paste-ready commands, landing between score-2 and score-3.

2 / 3

Workflow Clarity

A clear numbered 7-step sequence with explicit validation/failure checkpoints (".tex 数量为 0 时直接失败", clamping effective_panel_count) and a defined parallel→single degradation path, matching the score-3 anchor with explicit checkpoints.

3 / 3

Progressive Disclosure

The body is an overview that points one level deep to clearly signaled, verified-real references (references/expert_*.md, aggregation_rules.md, master_prompt_template.md, scripts/*.py) via a dedicated 关键脚本与参考 section, matching the score-3 anchor.

3 / 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, third-person voiced, and explicitly states both capability and trigger conditions with a useful non-applicability clause. It is concise yet complete, distinguishing it cleanly from sibling writing skills.

DimensionReasoningScore

Specificity

Names a concrete domain (NSFC 标书) and several specific actions — "多维度评审", "输出分级问题", "可执行修改建议" — matching the multi-action score-3 anchor rather than the single-domain score-2 anchor.

3 / 3

Completeness

Explicitly answers both what (multi-dimensional review, graded problems, actionable suggestions) and when ("当用户明确要求...时使用"), plus a clear 不适用 clause; not merely implied.

3 / 3

Trigger Term Quality

Quotes natural user phrasings ("评审国自然标书", "模拟专家评审", "审阅 NSFC 申请书") that a user would actually say, giving good coverage rather than just one keyword.

3 / 3

Distinctiveness Conflict Risk

Has a clear niche (NSFC proposal review) with distinct triggers and explicit disambiguation against the nsfc-*-writer skills, making wrong-skill conflicts unlikely.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation13 / 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

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

13

/

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.