
NSFC Proposal QC
FreeStreamline quality control for NSFC proposals.
Free · Opens the source repo
What NSFC Proposal QC does
The NSFC Proposal QC skill provides a robust framework for conducting quality control on National Natural Science Foundation (NSFC) proposals. It operates in a read-only mode, ensuring that the original .tex, .bib, .cls, and .sty files remain untouched. The skill focuses on generating a standardized QC report that highlights issues such as writing style, citation accuracy, structural integrity, and logical coherence. By leveraging multi-threading capabilities, it can efficiently process multiple aspects of the proposal simultaneously, resulting in a comprehensive quality check.
Designed for researchers and grant writers, this skill is particularly valuable for those preparing NSFC proposals who need to ensure compliance with rigorous quality standards. The skill's output includes detailed reports and metrics that help users understand the strengths and weaknesses of their submissions. The QC process is systematic, starting with a pre-check that identifies potential citation issues and structural problems before diving into more in-depth analysis.
The skill archives intermediate files in a designated workspace, allowing users to manage their projects effectively. It supports a variety of input configurations, making it adaptable to different project structures. The output consists of a final QC report along with several pre-check artifacts, providing a thorough overview of the proposal's quality. Users can run the skill through simple command-line scripts, making it accessible even for those with limited technical expertise.
Overall, the NSFC Proposal QC skill is an essential tool for anyone involved in the preparation of NSFC proposals, ensuring that submissions meet the necessary quality benchmarks without altering the original documents.
When to use it
Use this skill when you need a comprehensive quality check on NSFC proposals before submission.
When not to use it
This skill is not suitable for modifying proposal content or for general document compilation checks.
What you can build with it
Pre-Submission Quality Check
Before submitting an NSFC proposal, run this skill to ensure all quality standards are met.
Citation Verification
Use the skill to verify the accuracy and authenticity of citations in your proposal.
Structural Analysis
Check the structure and logical flow of your proposal with the skill's multi-threaded QC process.
How to install NSFC Proposal QC
View source1. Install with the skills CLI
npx skills add huangwb8/chineseresearchlatex/nsfc-qc --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by huangwb8NSFC 标书质量控制
BenszAPI 任务工作区
本 Skill 的新任务中间文件统一写入 ./.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/{skill名}/input|output|log/。同一任务复用一个任务根目录;多 Skill 协作才创建 shared/。正式交付物不写入该目录,历史隐藏目录只允许显式兼容读取、迁移或清理。
与 bensz-collect-bugs 的协作约定
- 当用户环境中出现因本 skill 设计缺陷导致的 bug 时,优先使用
bensz-collect-bugs按规范记录到~/.bensz-skills/bugs/,严禁直接修改用户本地 Claude Code / Codex 中已安装的 skill 源码。 - 若 AI 仍可通过 workaround 继续完成用户任务,应先记录 bug,再继续完成当前任务。
- 当用户明确要求“report bensz skills bugs”等公开上报动作时,调用本地
gh与bensz-collect-bugs,仅上传新增 bug 到huangwb8/bensz-bugs;不要 pull / clone 整个 bug 仓库。
定位
- 只读 QC:不修改
.tex/.bib/.cls/.sty - 目标是产出标准化 QC 报告,而不是“顺手帮用户改文”
- 推荐布局:
deliver_dir/放交付物,project_root/.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/nsfc-qc/{run_id}/放工作区
输入
最少需要:
project_root
建议同时提供:
main_tex,默认main.texthreads,默认读config.yamlexecution,默认serialdeliver_dir,推荐显式给,便于实例隔离
输出
标准交付物:
{run_dir}/final/nsfc-qc_report.md{run_dir}/final/nsfc-qc_metrics.json{run_dir}/final/nsfc-qc_findings.json{run_dir}/final/validation.json
常见预检产物:
precheck.jsoncitations_index.csvtex_lengths.csvreference_evidence.jsonlreference_evidence_summary.json
硬规则
- 禁止写入标书源文件。
- 文献真实性检查必须有证据链;不确定时标记
uncertain。 - 元数据获取是必选项:引用真伪核查必须联网抓取论文 metadata 并做 URL/title 比对。
nsfc-qc不负责正文改写;只负责发现问题与给出建议。
主流程
1. 定位 run 目录
- 优先用实例隔离布局:
deliver_dirworkspace_dir=project_root/.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/nsfc-qc/{run_id}run_dir={workspace_dir}
- 只有用户明确要求 legacy 或处理旧产物时才读取
project_root/.nsfc-qc/
2. 只读预检
- 自动检测主 tex
- 检查引用 key 是否存在
- 检查
.bib字段完整性 - 生成引用证据包:Crossref / arXiv / Unpaywall 等 metadata + URL 可访问性 + title 比对
- 输出篇幅分布、引号问题、缩略语与术语一致性初筛
3. 多线程独立 QC
- 优先用
parallel-vibe,并把.parallel-vibe/放到当前 run 内部 - snapshot 只包含最小必要副本:
*.tex/*.bib+ 预检证据包 - 每个 thread 至少覆盖:
- 文风与可读性
- 引用真伪与错引风险
- 篇幅与结构分布
- 逻辑与论证闭环
- 缩略语规范
- 术语一致性
- 至少 2 类其它 QC
4. 汇总聚合
- 主线程合并 threads 的
RESULT.md - 去重、冲突处理、按
P0/P1/P2排序 - 输出最小可执行修改路线
5. 标准化报告
最终报告必须包含:
- 执行摘要
- 范围与只读声明
- 硬性问题(P0)
- 重要建议(P1)
- 可选优化(P2)
- 引用核查清单
- 篇幅与结构分布
- 建议的最小修改路线图
- 附录:复现信息
常用脚本
# 一键运行
python3 skills/nsfc-qc/scripts/nsfc_qc_run.py \
--project-root projects/NSFC_Young \
--main-tex main.tex \
--deliver-dir projects/NSFC_Young/QC/vYYYYMMDDHHMMSS \
--threads 5 \
--execution serial
# 预检
python3 skills/nsfc-qc/scripts/nsfc_qc_precheck.py --project-root projects/NSFC_Young --main-tex main.tex --out <artifacts_dir> --resolve-refs
# 并行 QC
python3 skills/nsfc-qc/scripts/run_parallel_qc.py --project-root projects/NSFC_Young --run-id vYYYYMMDDHHMMSS --threads 5 --execution serial
# 物化 final 输出
python3 skills/nsfc-qc/scripts/materialize_final_outputs.py --project-root projects/NSFC_Young --run-id vYYYYMMDDHHMMSS
降级策略
- 若
parallel-vibe不可用,仍需完成同一套 QC 清单。 - 仍要输出标准化报告与 JSON。
- 在附录中说明未启用并行的原因。
非目标
nsfc-qc不是编译检查工具。- PDF 能否编译成功属于环境/工程质量,不是本技能的核心交付。
Frequently asked questions about NSFC Proposal QC
Similar skills
Scientific Problem Selection
Streamline your research problem selection process.
Nextflow Development
Run nf-core bioinformatics pipelines with ease.
Nature Reviewer Assessment
Simulate peer review for scientific manuscripts.
Research Writing Pipeline
Streamline your scientific writing with structured proposal-first methodologies.
Nature Literature Downloader
Efficiently download academic literature from various sources.
Auto Research
Streamline your NeMo-RL experiments with automated workflows.
