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。

70

Quality

87%

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

75%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 content is a well-structured, mostly executable review workflow with clear sequencing, validation/recovery checkpoints, and well-signaled one-level-deep references to real bundle files. The main gap is a few inline policy blocks and high-level prose steps that could be tightened or externalized.

Suggestions

Move the 公共硬约束 block (lines 159-168) into a shared reference file and link to it, reducing inline SKILL.md weight for the conciseness and progressive_disclosure dimensions.

Add an explicit copy-paste re-validation command in the 校验 section (e.g. the exact `python3 scripts/validate_skill.py` invocation) so the validation checkpoint is concrete rather than descriptive.

Tighten prose steps like 通读与结构化理解 into concrete sub-actions or point to a checklist reference, lifting actionability from mostly-executable to fully copy-paste-ready.

DimensionReasoningScore

Conciseness

The body is dense and operational with no concept-explanation padding, assuming Claude's competence; minor inline policy blocks (the long 公共硬约束 and Skill 专属约束 sections) could be trimmed or factored out, keeping it just above the lean 5-anchor.

4 / 5

Actionability

It provides concrete executable commands like `python3 <nsfc_reviewers_path>/scripts/list_proposal_files.py --proposal-path <proposal_root>` and names specific scripts and references, but several steps (e.g. 通读与结构化理解) remain high-level prose rather than copy-paste instructions.

4 / 5

Workflow Clarity

Phases are clearly sequenced (前置检查 → 通读 → 并行评审 → 聚合 → 阶段判断 → 输出整理 → 校验 → 失败与恢复) with explicit validation checkpoints and a retry-from-last-failed-step feedback loop; the validation is somewhat implicit in places rather than a hard re-run command.

4 / 5

Progressive Disclosure

References are clearly signaled and one level deep — the body explicitly lists 'scripts/...' and 'references/...' paths (lines 122-127) pointing to real bundled files — but some content that could live in a reference (e.g. the inline 公共硬约束 block) is inlined in SKILL.md.

4 / 5

Total

16

/

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.

This is an exemplary description: it states concrete capabilities, lists natural trigger phrases, explicitly answers what and when, and adds boundary guidance to avoid triggering for adjacent writing or informational tasks. No fluff or over-claims are present.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — '模拟领域专家视角对 NSFC 标书进行多维度评审' and '输出分级问题与可执行修改建议' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

It explicitly answers both 'what' (multi-dimensional expert review producing graded problems and actionable suggestions) and 'when' ('当用户明确要求…时使用') with concrete trigger phrases.

5 / 5

Trigger Term Quality

It enumerates natural user phrases a user would actually say — '评审国自然标书', '模拟专家评审', '审阅 NSFC 申请书' — including synonyms and the NSFC acronym.

5 / 5

Distinctiveness Conflict Risk

The '⚠️ 不适用' clause carves out adjacent skills (nsfc-*-writer, general review-standard questions) and requires explicit review intent, giving a clear niche with minimal conflict risk.

5 / 5

Total

20

/

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

referenced_paths_exist

Referenced path issues: 2 missing

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.