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 du-par/pharma-invest-skills --skill pharma-evalgit clone --depth 1 https://github.com/du-par/pharma-invest-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/du-par/pharma-invest-skills/pharma-eval)<a href="https://agentmods.dev/skills/du-par/pharma-invest-skills/pharma-eval"><img src="https://agentmods.dev/badge/skills/du-par/pharma-invest-skills/pharma-eval/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/du-par/pharma-invest-skills/pharma-eval"><img src="https://agentmods.dev/badge/skills/du-par/pharma-invest-skills/pharma-eval.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 | $0.00144 | $0.00808 |
| Opus 5 | $0.00072 | $0.00404 |
| Sonnet 5 | $0.00029 | $0.00162 |
| Haiku 4.5 | $0.00014 | $0.00081 |
Grade A, and why
pharma-eval 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 12d 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
医药项目评估
使用 GPT 最新模型（gpt 别名） 对生物医药项目进行完整投资分析。
触发条件
用户输入 @项目评估 或 项目评估，同时：
- 上传了项目材料（BP、尽调报告、临床数据、财务模型等），或
- 提供了项目名称（触发网络搜索兜底）
执行步骤
Step 1：信息收集
若有上传文件：
- 读取所有附件内容（docx/pdf/图片均可）
- 快速梳理：公司名、管线、阶段、团队、融资情况
若只有项目名称：
- 先检查
Projects/本地目录是否有相关文件 - 无本地文件则用 Tavily / web_search 搜索该项目近期信息（融资、临床进展、团队背景等）
Step 2：组合筛查（必须执行）
检查 PORTFOLIO.md，判断是否为怀格资本已投项目：
- ✅ 命中 → 在回答开头醒目标注
🏷️【怀格资本已投项目】，附注投资成本/MOIC/持股比例 - ❌ 未命中 → 继续分析
Step 3：调用 GPT 执行深度分析
模型：使用 gpt 别名（对应 gpt-5.4，最新 GPT 模型）
方式：将收集到的所有项目信息 + references/eval-prompt.md 中的完整评估框架，交给 GPT 进行分析。
具体做法：
- 读取
references/eval-prompt.md获取完整的15章节评估框架 - 将项目材料内容 + 评估框架 Prompt 组合，通过
sessions_spawn调用 GPT 子智能体完成分析：
sessions_spawn(
task = "<项目材料全文>\n\n---\n\n<eval-prompt.md全文>",
model = "gpt",
runtime = "subagent",
mode = "run"
)
- 等待子智能体返回结果，转发给用户
Step 4：输出格式
直接输出 GPT 返回的完整分析报告，格式为：
- 15个章节完整呈现（一、项目核心结论 → 十五、最终投资建议）
- 若报告过长，先发送一、二、三章摘要，告知用户可请求完整版
注意事项
- 模型必须是 GPT：不允许用 Claude/Kimi 替代，这是杜Par的明确要求
- 不要截断报告：GPT 返回多长就呈现多长
- 材料不足时：明确列出"资料未提供"的字段，并提出追问清单，不要因信息缺失而跳过章节
- 识别包装痕迹：提醒 GPT 识别BP中的夸大表述、逻辑漏洞、跳步推理
What ships with it
1 file 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.
- 12d ago First seen · 67 lines · 144 tokens per session scan A 5a5301e0498b
pharma-eval is a skill published in the GitHub repository du-par/pharma-invest-skills (10 stars, last pushed 4mo ago), licensed MIT. It adds 144 tokens to every session and 808 once invoked, about $0.0007 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
monte-carlo
Use when the user wants Monte Carlo simulation of a PlanExe model — sampling from bounds to produce output distributions (mean/std/percentiles), threshold pass probabilities, and Pearson-correlation sensitivity rankings — given an extract-parameters-from-full JSON, a generate-bounds JSON, a generate-calculations…
cointegration-analysis
Cointegration testing for pairs trading using Engle-Granger, Johansen, and rolling stability analysis.
fin-paper-figure
Generate academic-quality figures (>=300 DPI) for economics and finance papers.
quant-experiment-runtime
Quant research experiment executor: discover an offline source database under the workdir's code-repo, build a panel, run a Research Artifact's entry point to compute research-object values, and evaluate IC/ICIR/RANKIC/coverage metrics. Runtime = Experiment Executor; it runs a Research Artifact via a Python-native…
fin-paper-writing
A workflow for turning a research outline and study design into a complete economics or finance paper. It coordinates drafting, figure creation, consistency checks, review rounds, LaTeX compilation, and submission checks.
fin-viz-launch
A tool for turning research data and a written description into academic charts. It can choose a suitable chart type, create plotting code with matplotlib or seaborn, and save the result as a high-resolution PDF, SVG, or PNG.