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 chip-atlas-diff-analysisgit 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/chip-atlas-diff-analysis)<a href="https://agentmods.dev/skills/ggbond-bo/memomics-agent/chip-atlas-diff-analysis"><img src="https://agentmods.dev/badge/skills/ggbond-bo/memomics-agent/chip-atlas-diff-analysis/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/chip-atlas-diff-analysis"><img src="https://agentmods.dev/badge/skills/ggbond-bo/memomics-agent/chip-atlas-diff-analysis.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 | $0.00006 | $0.06564 |
| Opus 5 | $0.00003 | $0.03282 |
| Sonnet 5 | $0.00001 | $0.01313 |
| Haiku 4.5 | $0.00001 | $0.00656 |
Grade A, and why
chip-atlas-diff-analysis 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 5d 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.
This is a copy
92% identical to ChIP-Atlas Diff Analysis — 610 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 384 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。以下规则覆盖所有 Biomni 默认行为。
规则1: 拿到数据 → 必须调 search_knowledge
- 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2: 7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. check_env 检查环境
3. rail_review(pre) 前置审查
4. source/import 预写脚本(禁止 inline 代码)
5. terminal 执行(分步执行,禁止 && 连接多步骤)
6. debate_analysis 多方辩论(正方/反方切断上下文独立生成 + LLM裁决)
7. rail_review(post) 后置审查
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:正方(支持当前参数)vs 反方(质疑+替代方案)→ 裁判决断
- 不确定的参数就辩论,不要自己拍脑袋
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"
- 图片检查:
- 图有没有生成?没生成 → 强制重新执行
- 图片是否空白(全白/全黑/全单一色)?空白 → 强制重新出图
- 图片是否有 NA/缺失值(>10% 像素是 NA)?有 NA → 强制重新出图
- 图片大小是否过小(<5KB)?过小 → 强制重新出图
- 图片数量是否足够?(每步至少 1 张图,关键步骤至少 2-3 张)
- 代码质量检查:
- 代码行数是否合理?(过短可能偷懒,过长可能未分段)
- 代码是否有注释?
- 代码是否分段执行(禁止 && 连接多步骤)?
- 结果合理性:
- 数值范围是否合理?
- 跟知识库对应吗?
- 参数和结论辩论:
- 有参数的选择 → 必须调 debate_analysis 辩论
- 有结论输出 → 必须调 debate_analysis 辩论
- 不通过 → 修复重跑
- 通过 → 必须调 skill_evolution(action="record_run") 记录成功经验(skill_name/script_name/species/tissue/direction/params_used/result_summary/quality_score/notes) → 创建目录存储(figures/results/scripts/data) → 下一步
- 不通过 → 修复后重跑 → 成功后调 skill_evolution(action="record_run");如果是脚本报错 → 调 skill_evolution(action="record_error") 记录根因+修复方案
- 图片检查:
规则6: 结果存储结构
results/<模块>/<方法>/
├── scripts/ # 分析脚本
├── figures/ # PNG + SVG 图表
├── data/ # RDS/H5AD 中间数据
└── results/ # CSV/TSV 结果表
What ships with it
16 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.
- references/chipatlas_diff_api_format.md 3.1 KB
- references/diff_analysis_methods.md 3.1 KB
- references/output_format.md 3.0 KB
- scripts/__init__.py 2.2 KB runs code
- scripts/annotate_genes.py 6.5 KB runs code
- scripts/export_all.py 26 KB runs code
- scripts/filter_regions.py 8.0 KB runs code
- scripts/generate_all_plots.py 13 KB runs code
- scripts/load_example_data.py 8.3 KB runs code
- scripts/load_user_data.py 9.0 KB runs code
- scripts/parse_bed_results.py 10 KB runs code
- scripts/qc_checks.py 26 KB runs code
- scripts/query_chipatlas_api.py 13 KB runs code
- scripts/run_diff_workflow.py 11 KB runs code
- scripts/run.py 3.3 KB runs code
- skill.json 1.1 KB
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.
- 5d ago First seen · 384 lines · 6 tokens per session scan A 64d6770108b2
chip-atlas-diff-analysis is a skill published in the GitHub repository GGbond-bo/MemOmics-Agent (19 stars, last pushed 6d ago), licensed MIT. It adds 6 tokens to every session and 6,564 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to ChIP-Atlas Diff Analysis, differing in 610 lines, and is treated as a copy.
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…
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…
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…
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.
evo2
Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…