nsfc-grant-writer

Generate a complete NSFC (National Natural Science Foundation of China) General Program grant application in Chinese, following the 2026 official template. Use when the user provides a scientific hypothesis and wants to generate a full grant application document, including abs...

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%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.

A well-structured, actionable, and token-efficient skill body that keeps an overview inline while delegating detail to real one-level-deep reference files. The main gap is the absence of an explicit output/result verification step in the workflow.

Suggestions

Add an explicit validation checkpoint after the PubMed search (e.g. confirm 15-25 references were returned before generating the document) and after docx generation (e.g. verify the .docx opens and sections are present), which would lift workflow_clarity to 5.

Tighten the duplicated citation/consistency rules in Step 3 into a single concise list to remove the minor redundancy.

Move the per-section generation table's verbose cell text into writing-guide.md and keep only the action verb inline, further reducing body tokens.

Dimension	Reasoning	Score
Conciseness	The body is lean and uses tables, bullet lists, and code blocks without explaining concepts Claude already knows (e.g. it never defines PubMed or grants); a few minor parts (repeated citation/consistency rules and the dependency-check narrative) could be trimmed, keeping it just below anchor 5.	4 / 5
Actionability	Provides copy-paste-ready, executable guidance: real PubMed eutils URLs with parameters, the exact `python scripts/generate_docx.py ...` command, `pip install python-docx`, concrete folder/title formats with worked examples, and a per-section generation table covering the common cases.	5 / 5
Workflow Clarity	A clear 4-step sequence with real checkpoints (an Input Validation section, a dependency check with install-and-re-run feedback loop, and error-handling fallbacks), but it lacks an explicit verification of the PubMed results or the generated .docx output, so it does not reach anchor 5's full validation/checklist bar.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview that delegates detail to one-level-deep, well-signaled, verified bundle files (references/template.md, writing-guide.md, pubmed-guide.md and scripts/generate_docx.py), with a Resources section describing each — matching the anchor 5 structure.	5 / 5
	Total	18 / 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.

A strong, third-person description with an explicit trigger clause and a distinct niche, clearly answering both what and when. Its main weakness is the literal mid-word truncation ("including abs...") and the absence of synonyms/file extensions that would round out trigger coverage.

Suggestions

Fix the truncated description so it ends with a complete clause (e.g. finish "including abstract, research rationale, content, and feasibility sections") instead of cutting off at "abs...".

Add common synonyms and the output format to the trigger, such as "国家自然科学基金", "grant proposal", and ".docx", to broaden natural-term coverage.

Mention the Word/.docx export explicitly in the description so the deliverable format is clear at the trigger layer.

Dimension	Reasoning	Score
Specificity	Names the domain (NSFC General Program grant) and a concrete comprehensive action ("Generate a complete ... grant application in Chinese, following the 2026 official template"); it is essentially one primary action described with broad output scope rather than multiple distinct actions, so it sits above anchor 3 but below anchor 5.	4 / 5
Completeness	Explicitly answers both what (generate a complete NSFC grant application in Chinese following the 2026 template) and when ("Use when the user provides a scientific hypothesis and wants to generate a full grant application document") with concrete trigger phrases; the trailing "abs..." truncation only cuts an enumerated detail, not the what/when core.	5 / 5
Trigger Term Quality	Includes natural domain terms users would say ("grant application", "scientific hypothesis", "NSFC") with a concrete "Use when" clause, but lacks synonyms (e.g. "proposal", the Chinese name) and file extensions like .docx that anchor 5 expects.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (NSFC General Program, Chinese, 2026 template) with a distinctive trigger (user provides a scientific hypothesis to generate a grant), giving minimal overlap 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Academic Writing/nsfc-grant-writer/SKILL.md
Commit: f5ef65b

Reviewed: ~21 hours 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.