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 GGbond-bo/MemOmics-Agent --skill analysis-summary-reportgit clone --depth 1 https://github.com/GGbond-bo/MemOmics-AgentWrote 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/ggbond-bo/memomics-agent/analysis-summary-report)<a href="https://agentmods.dev/skills/ggbond-bo/memomics-agent/analysis-summary-report"><img src="https://agentmods.dev/badge/skills/ggbond-bo/memomics-agent/analysis-summary-report/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/ggbond-bo/memomics-agent/analysis-summary-report"><img src="https://agentmods.dev/badge/skills/ggbond-bo/memomics-agent/analysis-summary-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00009 | $0.02841 |
| Opus 5 | $0.00005 | $0.01421 |
| Sonnet 5 | $0.00002 | $0.00568 |
| Haiku 4.5 | $0.00001 | $0.00284 |
Grade A, and why
Analysis Summary Report 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analysis Summary Report — 分析后总结报告
🔒 报告完整性铁律(禁止偷懒)
- 只要检查到有分析结果,所有分析辩论、图片都要加入报告,不许漏。
- 如果有图才几十 KB,那就是有问题的——必须报告并重新生成。
- 不特定说明的情况下,报告必须覆盖本次分析的所有模块和所有图片。
- 每张图的 4 个面板(method/result/bio/param_source)全部必填,传空直接报错。
- 报告中每张图的解读结论必须经过
debate_figure_conclusions辩论。 - 报告中每个分析模块的总结论必须经过
debate_figure_conclusions辩论。
🔒 报告语言铁律
- 检测用户交互语言:用户用中文 → 报告全程中文;用户用英文 → 报告全英文。
- 无论重新生成多少次,语言必须与用户首次交互语言一致。
🔒 图片健康度铁律
- 放入 HTML 的每张图片必须检查(rail_review POST 审查会自动检测):
- 文件大小 < 5KB → 强制重新生成
- 全白/全黑/全单一色 → 强制重新生成
- 含大量 NA 值 → 画图不全,强制重新生成
- 文件损坏 → 强制重新生成
- 不允许跳过任何问题图。
触发场景
触发条件(必须全部满足):
- 已经完成真实分析(有 terminal 执行结果 + 生成了 figures)
- 用户要求总结/报告/归纳
不触发:
- 没有做过分析,只是文献综述/整理结果
- 只有个别步骤完成,没有系统分析
- 概念咨询、闲聊
报告 7 模块结构
模块 1:📊 数据概览
- 数据来源(文件路径、格式)
- 细胞数、基因数
- 物种、组织、测序方法
- 硬件环境(CPU/内存/GPU/磁盘,来自 scan_data)
模块 2:🔬 分析流程
- 每步分析用了什么 skill
- 每步的参数(归一化方法、聚类分辨率、PC数等)
- 每步的执行时间
- 每步的 rail_review 结果(通过/不通过)
模块 3:📚 知识库来源
- 每个参数推荐来自哪条知识库记录
- 知识库类目(标准化/批次校正/聚类/注释/DEG等)
- 匹配的文献引用
模块 4:🗣️ 辩论记录
- 每轮 debate_analysis 的完整记录
- 正方论点(生物学/统计学/生信角度)
- 反方论点(同样角度 + 历史经验/报错记录)
- 裁决结果、分数、行动项
模块 5:📈 图表结果
- 每张图带 4 个面板:
- 方法:用了什么方法生成
- 结果:图展示了什么
- 生物学意义:图说明了什么生物学发现
- 参数来源:参数来自知识库/文献/辩论/经验
- 图片按分析模块排列(QC图 → PCA → UMAP → 标记基因 → DEG → 通路等)
模块 6:🧬 生物结论
- 结论辩论(必须):
- 正方:从生物学(marker gene验证、已知生物学知识)、统计学(显著性、效应量)、生信(质量指标)角度支持结论
- 反方:从同样角度 + 历史经验记录 + 报错记录质疑结论
- 裁判:综合裁决,给出置信度(高/中/低)
- 不互通上下文:正方不知道反方说了什么
- 结论必须根据真实结果总结,不能凭空编造
- 每条结论标注证据来源(哪张图、哪个分析、哪个辩论)
模块 7:⚠️ 质量评估
- QC 指标:nFeature、nCount、percent.mt 分布
- 双胞率
- 污染率(如果做了去污染)
- 线粒体阈值
- 细胞过滤前后数量对比
技术实现
基于 bioinformatics-html-report 的 ReportBuilder API:
import sys
sys.path.insert(0, "hermes_home/skills/bioinformatics/bioinformatics-html-report")
from html_report_builder import ReportBuilder
rb = ReportBuilder(
title="MemOmics Analysis Summary",
subtitle="scRNA-seq Analysis Report",
stats=[("细胞数", "30,000"), ("基因数", "20,000"), ("聚类数", "12")],
key_findings=["发现 X 个主要细胞群", "衰老相关基因在 Type II 纤维中上调"]
)
# 模块 1-7 分别用 section
with rb.section("overview", "Data Overview", "数据概览"):
...
with rb.section("pipeline", "Analysis Pipeline", "分析流程"):
...
# 每张图用 add_figure(4面板)
rb.add_figure(
fig_path="figures/umap.png",
caption_en="UMAP Visualization",
method_zh="Seurat UMAP 降维可视化",
result_zh="12个细胞群清晰分离",
bio_zh="Type II 纤维细胞是最大群体,符合骨骼肌组织特征",
param_source_zh="聚类分辨率0.5来自知识库推荐(139条匹配)"
)
# 辩论记录用 add_debate
rb.add_debate(topic="聚类分辨率选择", rounds=[...])
rb.save("analysis_summary_report.html")
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.
- 7d ago First seen · 221 lines · 9 tokens per session scan A 2c1311e841ea
Analysis Summary Report is a skill published in the GitHub repository GGbond-bo/MemOmics-Agent (19 stars, last pushed 8d ago), licensed MIT. It adds 9 tokens to every session and 2,841 once invoked, about $0.0000 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 2026-09-03.
Other skills, from other repositories
report-generator
Generate professional drug discovery reports including target dossiers, competitive briefs, and Go/No-Go decision summaries. Use this skill when you need formatted reports for presentations, decision meetings, or documentation. Supports multiple output formats. Keywords: report, dossier, decision, go-no-go, brief…
clinical-case-report
Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds"…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
nature-experiment-log
A workflow for turning experiment notes, images, audio, or text into structured Markdown laboratory logs with YAML metadata. It can also organize raw attachments and optionally connect the logs to Feishu or Obsidian.
doc-kami-parchment
Warm parchment canvas (#f5f4ed), monochrome ink-blue accent (#1B365D), one serif family, and editorial-grade typography.