Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

NSFC 标书专家评审模拟器 · huangwb8 | DecimalAI

researchby huangwb8

NSFC 标书专家评审模拟器

huangwb8/nsfc-reviewers

Source huangwb8/chineseresearchlatex ↗License MIT

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。

SkillScore77Maintained

Automatic

Research pack

Last verified 9/9/2026

What it changes

Passed 13 of 17 test cases with the skill, and 5 of 17 without it.

Without skill27%

With skill77%

Checks it passed that the model alone missed

Orders output issues strictly from P0 to P1 to P2.
Restricts confidence level annotations to 高, 中, or 低.
Enforces strict binary labels of 给过 or 不给过 for stage decisions.

and 10 more in the full report

13 fixed4 passed either way3 still failing2 broke

Pass-rate lift: +50 pp
Tokens: +32%
Agent turns: 0%
Response time: -42%

Model gemini-3.6-flashMeasured 9/9/2026v217 of 22 cases passed with skill · 17 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/huangwb8-nsfc-reviewers/SKILL.md https://app.decimal.ai/s/huangwb8-nsfc-reviewers/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add huangwb8-nsfc-reviewers, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/huangwb8-nsfc-reviewers/ and pins it in .decimal/skills.lock

decimalai skills add huangwb8-nsfc-reviewers

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/huangwb8-nsfc-reviewers/SKILL.md https://app.decimal.ai/s/huangwb8-nsfc-reviewers/SKILL.md

Raw file: /s/huangwb8-nsfc-reviewers/SKILL.md ↗ · machine-readable summary at /s/huangwb8-nsfc-reviewers.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

在查询或更新本评审工具的版本号时，唯一被认可的权威版本信息存储在哪个文件的哪个字段中？

What was checked, without and with the skill
Checked	Without skill	With skill
Designates `config.yaml:skill_info.version` as the single source of truth for version numbers.	Missed	Passed

case-20 · gemini-3.6-flash · 9/9/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md166 lines15 filesincludes scripts

NSFC 标书专家评审模拟器

用于“当前版本如果今天送审，风险在哪里、先改什么”的专家式评审。
默认优先并行多组独立评审；若 parallel-vibe 不可用、被禁用或 panel_count=1，自动降级为单组模式。
本技能只做读取、分析和汇总，不默认编译、不修改标书源文件。

输入

至少提供其一：

proposal_path
proposal_file
proposal_zip

可选：

focus
output_path
style
grant_type
funding_amount
panel_count

配置口径以 config.yaml 为准，尤其是：

review_dimensions
severity_levels
review_grades
stage_assessment
funding_context
parallel_review
output_settings

非目标

不负责改正文。
不负责模板、排版或编译问题。
不负责生成新的研究设计，只负责指出现有稿件的风险、优先级和修改方向。

流程

Track record

Benchmark

13 / 17

test cases passed, vs 5 / 17 without

Adoption

Users: 1
Times used: 8

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/9/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

huangwb8 / chineseresearchlatex

skills/nsfc-reviewers/SKILL.md

View on GitHub ↗

License MITImported 9/9/2026Version v2Bundled 14 files · scripts

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

huangwb8/nsfc-qc当用户明确要求"标书QC/质量控制/润色前质检/引用真伪核查/篇幅与结构检查"时使用。对 NSFC 标书进行只读质量控制：并行多线程独立检查文风生硬、引用假引/错引风险、篇幅与章节分布、逻辑清晰度等，最终输出标准化 QC 报告；中间文件默认归档到 `project_root/.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/nsfc-qc/{yyyy-mm-dd-hh-mm}/`，并兼容 legacy `.nsfc-qc/` 读取/清理。Close match+48 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

NSFC 标书专家评审模拟器

输入

非目标

流程

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills