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 create_harmony_embeddings_scrnagit 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/create_harmony_embeddings_scrna)<a href="https://agentmods.dev/skills/ggbond-bo/memomics-agent/create_harmony_embeddings_scrna"><img src="https://agentmods.dev/badge/skills/ggbond-bo/memomics-agent/create_harmony_embeddings_scrna/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/create_harmony_embeddings_scrna"><img src="https://agentmods.dev/badge/skills/ggbond-bo/memomics-agent/create_harmony_embeddings_scrna.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 | $0.00055 | $0.02989 |
| Opus 5 | $0.00028 | $0.01494 |
| Sonnet 5 | $0.00011 | $0.00598 |
| Haiku 4.5 | $0.00006 | $0.00299 |
Grade A, and why
create_harmony_embeddings_scRNA 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 9d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⛔ MemOmics 强制规则(不可违反,优先级最高)
本 skill 已集成到 MemOmics-Agent 自进化生信分析平台。使用本 skill 前,必须先通过 skill_view 加载本文件。以下规则覆盖所有默认行为。
规则1: 写代码前 → 必须先 search_knowledge + skill_view
- 每个分析步骤写代码前,必须先调
search_knowledge(species=..., tissue=..., direction=..., query="<步骤名> 参数") - 知识库有匹配 → 用知识库的参数和模板
- 知识库无匹配 → 用 web 搜索文献,提取方法和参数,存入知识库
- 绝对不能跳过直接写代码
规则1a: batch_key 预检查(写代码前必须执行)
- 使用
batch_key前,必须先用 Python 检查唯一条目数:n_unique = adata.obs['<batch_key>'].nunique() print(f"batch_key 唯一条目数: {n_unique}") if n_unique > 100: print("⚠️ 警告:batch_key 有 {n_unique} 个唯一值,可能误用了 cells/barcode 列!") print(" 预期:sample/donor ID(通常 2-20 个)") print(" 如果不是 → 阻断,检查数据,修正 batch_key") - 如果
n_unique > 100且不是预期的样本数 → 阻断执行,提示用户在adata.obs.columns中找正确的分组列 - 参考 Common Issues → 已有
sample_id (16,003 unique)先例
规则2: 8步循环(每步必须走完整循环)
1. search_knowledge 查本步骤的方法和参数
2. skill_view 加载本 SKILL.md(获取脚本模板+审查规则+参数范围)
3. check_env 检查环境(缺包自动安装)
4. rail_review(pre) 前置审查(参数合理吗?包齐了吗?数据准备好了吗?)
5. 写这一步的代码(基于 skill 模板,只写这一步,不写后续步骤)
6. terminal 执行(分步执行,禁止 && 连接多步骤)
7. debate_analysis 多方辩论(正方/反方切断上下文独立生成 + LLM裁决)
8. rail_review(post) 后置审查(图有没有?结果合理吗?跟知识库对应吗?)
规则3: 代码分段执行 — 写一步跑一步
- ❌ 禁止一次性写完全部代码用 && 连接执行
- ✅ 必须分步:写一步 → 执行 → 检查结果 → 辩论 → 下一步
规则4: 关键参数多参数尝试 + 辩论
- 涉及数值参数时(如 resolution, n_pcs, min_features, FDR threshold 等),至少尝试 2-3 个值
- 每次参数变更后调
debate_analysis辩论"这个参数合理吗?结果有没有变好?" - 辩论格式(多角色对抗 v3):
- 正方 3 位专业编辑(各自独立,互相不知道):生物学编辑 / 统计学编辑 / 生信编辑
- 反方 4 位专业编辑(各自独立,互相不知道,也看不到正方):生物学编辑 / 统计学编辑 / 生信编辑 / 历史经验编辑
- 裁判编辑:看到所有 7 方论点,给出裁决 + 置信度(高/中/低)
- 上下文隔离:每个编辑独立 HTTP API 调用,messages 只有自己的 prompt
- 分科知识库:生物学编辑用 biology_kb / 统计学编辑用 statistics_kb / 生信编辑用 bioinfo_kb / 历史经验编辑用 history_errors
- 辩论结果自动归档到 results/.../log/debate_*.json
- 不确定的参数就辩论,不要自己拍脑袋
- 辩论最多 3 轮:3 轮后选最优参数结果
规则5: 执行后审查
规则N: 运行记录只是参考,不能跳过审查
- skill_evolution(action="query_logs") 返回的历史运行日志仅供参数参考
- 即使有 quality_score=9.0 的历史日志,仍必须执行 rail_review(pre)、debate_analysis、rail_review(post)
- 禁止因"之前跑过"而跳过任何审查步骤
- 禁止直接用历史日志里的脚本运行而不经本次审查
- 运行日志是"参考"不是"免审凭证"
What ships with it
3 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.
- 9d ago First seen · 217 lines · 55 tokens per session scan A 3fbca22003a0
create_harmony_embeddings_scRNA is a skill published in the GitHub repository GGbond-bo/MemOmics-Agent (19 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 2,989 once invoked, about $0.0003 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
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
pyhealth
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
pick-a-pii-model
Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.