Install any skill in seconds. Free to start, no credit card required.
Get Started Free →huangwb8/nsfc-justification-writer
当用户明确要求"写/改 NSFC 立项依据""立项依据写作/重构"时使用。基于最小信息表输出价值与必要性、现状不足、科学问题/假说与项目切入点,并保持模板结构不被破坏。适用于 NSFC 及各类科研基金申请书的立项依据写作场景。
Passed 13 of 18 test cases with the skill, and 6 of 18 without it.
and 10 more in the full report
10 fixed7 passed either way6 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
When reporting semantic issues identified during Tier2 review of a grant justification, what specific 4-part structure must be used to describe each finding?
| Checked | Without skill | With skill |
|---|---|---|
| Formats Tier2 findings using location, obstacle, impact, and faithful modification. | Missed | Passed |
The instructions your model reads when the skill loads.
按用户请求和配置文件提供必要输入;缺失信息应明确列出并停止依赖该输入的步骤。
bensz-collect-bugs 记录到 ~/.bensz-skills/bugs/,不要改用户本地已安装 skill;可用 workaround 时先记录再继续。gh 通过该 skill 上传新增 bug 到 huangwb8/bensz-bugs;不 pull/clone 整仓库。references/tier2_semantic_review.md,由当前宿主 AI 直接执行 Tier2 语义检查。由宿主 AI 自主规划术语、论证维度和可读性,输出“位置/障碍/影响/保真改法”。检查长句层级、指代、缩写/新概念、抽象名词、衔接和无效修饰;不科普化或因必要限定强改。措辞边界:吹牛式、绝对化或无依据夸大由宿主 AI 按 references/boastful_expression_guidelines.md 语义复核并归入逻辑/表达建议;Python 只做路径、结构命令、引用 key 等确定性检查,不用固定词表判定。
main.tex,按确定性优先级选择候选,必要时创建白名单内的默认正文文件。polish 先在内部锁定事实/逻辑/引用,再做受约束精修,不向用户提问。scripts/run.py preview:自动生成 diff 并按 guardrails.output_mode 写入;需要只读检查时显式加 --dry-run。refs、wordcount:独立引用/字数工具;术语、论证维度和可读性由 Tier2 宿主 AI 规划。diagnose:仅执行 Tier1 确定性诊断,并提示宿主 AI 读取 references/tier2_semantic_review.md;不主动调用模型、不生成 Tier2 fallback 结论。coach、review:主流程必须包含由宿主 AI 直接执行的 Tier2 语义检查。吹牛式/绝对化风险按参考准则由 AI 判断,脚本不做固定短语命中。apply-section:legacy 标题替换写入;新流程优先使用完整正文提案自动写入,不依赖 \\subsubsection。diff、rollback:查看或回滚自动写入变更;回滚命令仍需显式 --yes 以避免误操作。按任务先阅读 references/tier2_semantic_review.md,再按其中需要阅读 references/scientific_question_guidelines.md、references/scientific_hypothesis_guidelines.md、references/professional_readability_guidelines.md 和 references/boastful_expression_guidelines.md。用户流程、脚本用法和架构边界见 README.md;检查维度由宿主 AI 自主规划,不依赖固定术语矩阵或四维度门槛。
test cases passed, vs 6 / 18 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.