nsfc-justification-writer

当用户要求写作、重构、审查或润色 NSFC/科研基金申请书的立项依据、研究意义、国内外现状、科学问题或科学假设时使用。以语义论证和可核验性为核心，支持任意文件名、标题命令和 LaTeX 结构；默认全自动完成诊断、成稿、校正、备份和写入，不向用户发起中途确认或审核问题。

Quality

81%

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

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 body is a compact, well-structured workflow with concrete subcommands, mandatory validation gates, and clear one-level reference navigation. It is held back from top marks by abstractly described validation loops, an unresolved root README.md reference, and some inlineable density.

Suggestions

Make the validate→fix→retry feedback loop explicit as concrete commands (e.g., run diagnose, review Tier2 output, fix, re-run) for the destructive write path to lift workflow_clarity.

Resolve the root README.md reference: either add a top-level README.md or point to scripts/README.md / assets/README.md so navigation links are not broken.

Move the dense process narration (steps 1-6 and the bullet list) into a referenced reference file, keeping SKILL.md as a leaner overview, to improve progressive_disclosure and conciseness.

Dimension	Reasoning	Score
Conciseness	Dense, terse prose that assumes Claude's competence and avoids explaining LaTeX/NSFC basics; a few constraint sections could be tightened further, placing it just below the lean anchor.	4 / 5
Actionability	Provides concrete executable commands (scripts/run.py preview, --dry-run, diagnose, coach, review, apply-section, diff, rollback --yes) and named reference files, with only minor gaps in full invocation examples.	4 / 5
Workflow Clarity	Multi-step flow with explicit checkpoints (mandatory Tier2 review, backup-before-write, whitelist/bibkey gating, rollback entry, retry from last failed step); not quite a 5 because some validation feedback loops are described abstractly rather than as concrete validate→fix→retry commands.	4 / 5
Progressive Disclosure	Well-organized into 流程/约束 sections with one-level-deep references to real files under references/; held below 5 because the body inlines substantial process detail and references a root README.md that is not present in the bundle.	4 / 5
	Total	16 / 20 Passed

Description

87%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 is third-person, trigger-explicit, and concretely scoped to NSFC grant justification writing with both a clear what and when. It is strong across all dimensions, with only minor room to broaden trigger synonym coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (NSFC/科研基金申请书立项依据) and several concrete actions — 写作、重构、审查、润色 plus 自动诊断、成稿、校正、备份和写入 — giving multiple specific capabilities, though coverage is action-verb driven rather than exhaustively enumerated.	4 / 5
Completeness	Explicitly answers both what (semantic argument and verifiability core, auto diagnostic/draft/correction/backup/write) and when (explicit "当用户要求...时使用" trigger clause with concrete trigger phrases), satisfying the top anchor.	5 / 5
Trigger Term Quality	Includes natural user phrasing ("当用户要求写作、重构、审查或润色 NSFC/科研基金申请书的立项依据、研究意义、国内外现状、科学问题或科学假设时使用") with good keyword coverage and several object variations, though it lacks file-extension-style synonyms.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — NSFC justification writing — with distinct triggers (立项依据、科学问题/假设) and minimal overlap risk with other skills.	5 / 5
	Total	18 / 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-justification-writer/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.