Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Amalia6767/curator-skills --skill proposal-designgit clone --depth 1 https://github.com/Amalia6767/curator-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/amalia6767/curator-skills/proposal-design)<a href="https://agentmods.dev/skills/amalia6767/curator-skills/proposal-design"><img src="https://agentmods.dev/badge/skills/amalia6767/curator-skills/proposal-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/amalia6767/curator-skills/proposal-design"><img src="https://agentmods.dev/badge/skills/amalia6767/curator-skills/proposal-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.01228 |
| Opus 5 | $0.00023 | $0.00614 |
| Sonnet 5 | $0.00009 | $0.00246 |
| Haiku 4.5 | $0.00005 | $0.00123 |
Grade A, and why
proposal-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
方案设计与投标输出
核心思维模型：策展五力 (Curation Five Forces)
所有方案必须在构思阶段优先满足以下模型（详见 DNA.md）：
- 价值闭环力：从陈列转向闭环，关注“离馆体验”与“数据进化”。
- 精准角色力：实现“千人千面千线”，提供不同角色的参观脚本。
- 分层叙事力：L1震撼/L2认知/L3交互分层，专家组联合体架构。
- 场域应变力：一厅多用Transformer，物理限制的艺术化解决。
- 进化工具力：交付拖拽式平台等“进化武器”，确保低成本迭代。
目标
将“招标要求”转化为“可交付的投标方案”，并确保：
- 逐条响应：对招标关键条款（★必须项）点对点应答，不漏项。
- 可落地：方案中的工期、资源、界面、交付物、验收口径可执行。
- 可得分：显式对齐评分表，写出“得分证据点”。
- 可报价：方案结构能支撑清单拆分与报价解释。
输入
必需输入
tender-analysis的分析报告：项目基本信息/工期/付款/评分/风险等tender-analysis的对内问题池（类别+职能）：用于确认已澄清/未澄清/待风险兜底项
可选输入（推荐）
- 会议纪要（口头答疑总结）
- 录音文稿/逐字稿（甲方原始表述的文字稿；用于提炼口径、补充细节，但最终以书面澄清为准）
- 甲方书面答疑（SRM澄清、邮件、纪要附件）
- 甲方新增需求（范围、面积、预算、风格、界面）
- 图纸/清单补充、品牌限定/材料设备标准更新
工作流程
阶段0：建立“最新口径基线”
- 汇总所有输入文件，按时间排序
- 形成“口径优先级”：
- 书面澄清/合同/招标文件补遗 > SRM公告 > 会议纪要（口头） > 初版招标文件
- 输出《口径变更表》：每一项变更记录来源、影响、是否需要再次提问
阶段1：需求与评分对齐
- 抽取“★必须满足/废标点/硬性门槛”
- 抽取评分表的每一项，写出“我们如何得分”的证据结构：
- 方案内容（写什么）
- 证明材料（附什么）
- 可视化表达（图/表/流程图/页面示意）
阶段2：形成方案母版（Markdown）
使用 templates/proposal-outline.md 生成完整母版：
- 项目理解（背景、目标、范围、边界、关键挑战）
- 总体方案（空间/内容/系统/运营）
- 关键系统设计（内容平台、中控、交互、数据对接、运维）
- 实施计划（阶段、里程碑、交付物、验收口径）
- 团队与组织（角色、驻场、协作机制）
- 质量与安全（施工/消防/创优/成品保护/文档）
- 风险与澄清（未澄清项的兜底写法）
- 证据清单（评分项→证据材料映射表）
阶段3：裁剪成对外交付形态
从母版裁剪/改写为：
- Word：
templates/proposal-word-outline.md - PPT：
templates/proposal-ppt-outline.md - 网页：
templates/proposal-web-outline.md
阶段4：一致性检查（必须做）
- 招标要求覆盖率：所有★必须项均有对应章节/段落
- 评分对齐：每个评分点都有“可识别证据”
- 工期/付款/交付物一致：计划、里程碑、报价口径不矛盾
- 风险兜底：未澄清项有保护性表述或假设前提
输出要求（最低标准）
至少输出：
投标方案_母版.md投标方案_对外版.md（或 docx/pptx/html）评分点→证据材料映射表.md（可作为母版的附录）
写作与表达原则
- 用“甲方语言”写：少泛化科技感，多写可验收的指标与流程
- 用“结构化证据”写：表格/清单/流程图胜过长段落
- 对不确定项明确“假设前提”：并标记为需答疑或风险项
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 88 lines · 46 tokens per session scan A 231a294540ab
proposal-design is a skill published in the GitHub repository Amalia6767/curator-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 1,228 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
chinese-typography
A Chinese typography guide for websites, articles, social-media posts, PDFs, Word documents, and presentations. It explains spacing, fonts, line height, punctuation, and line breaking for Chinese text.
chinese-web-themes
A collection of eight CSS themes for giving websites a Chinese-inspired visual style, with typography rules for Chinese text.
chinese-design-md
A collection of eight Chinese-inspired design-system documents for AI coding tools. A design system is a set of rules for colours, fonts, layout, shapes, and components that an interface should follow.
wps-ppt-polish
A PowerPoint cleanup tool that checks slides for layout and style problems, then can apply consistent fonts, colors, alignment, spacing, and other formatting changes across the presentation.
product-architecture
A product-analysis method that reverse-engineers how a product is organised, rather than mapping its technical services or page structure. It represents the product with four layers—touchpoints, user situations, capabilities, and data—and produces an HTML architecture diagram.
curatorial-narrative-modules
A planning guide for turning curatorial writing into the structure of a digital or online exhibition. It defines page types, content sections, fields, navigation, and levels of interaction.