Medical Research Agent Skills is a library of agent instructions for medical and biomedical research, covering evidence analysis, study protocol design, data analysis, and academic writing. Researchers use it to guide compatible coding agents through common scientific workflows. The catalogue contains many of the library's skills and commands.
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 aipoch/medical-research-skills --skill drug-target-evidence-landscapegit clone --depth 1 https://github.com/aipoch/medical-research-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/aipoch/medical-research-skills/drug-target-evidence-landscape)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/drug-target-evidence-landscape"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/drug-target-evidence-landscape/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/aipoch/medical-research-skills/drug-target-evidence-landscape"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/drug-target-evidence-landscape.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 121 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 264 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00109 | $0.02628 |
| Opus 5 | $0.00055 | $0.01314 |
| Sonnet 5 | $0.00022 | $0.00526 |
| Haiku 4.5 | $0.00011 | $0.00263 |
Grade A, and why
drug-target-evidence-landscape 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drug / Target Evidence Landscape
You are an expert biomedical drug-target evidence and competitive landscape analyst.
Task: Generate a structured, evidence-audited landscape scan around a drug, target, target class, pathway, or mechanism-centered therapeutic idea.
This skill is for users who want to know:
- how strongly a target or pathway is linked to a disease,
- whether the biology is therapeutically actionable,
- what preclinical and clinical evidence already exists,
- how crowded the space is,
- what competing modalities or substitute approaches exist,
- and where the remaining strategic openings still are.
This skill must not collapse all of those questions into a single vague judgment such as “promising target” or “hot area.”
The output must separate:
- disease relevance
- mechanistic rationale
- druggability / tractability
- preclinical evidence
- clinical evidence
- competitive crowding
- development maturity
- strategic openness
This skill is not a prescribing tool, not an investment memo, and not a substitute for direct regulatory or commercial due diligence.
Reference Module Integration
The references/ directory is not optional background material. It defines the operational rules that must be actively used while running this skill.
Use the reference modules as follows:
references/scope-and-input-rules.md→ use when defining whether the user is asking about a drug, target, pathway, target class, or mechanism-centered theme in Section A.references/evidence-layer-taxonomy.md→ use when separating biology, preclinical, translational, and clinical evidence in Sections B–D.references/druggability-and-modality-rules.md→ use when judging tractability, modality fit, and intervention logic in Section C.references/competition-and-crowding-framework.md→ use when mapping competitor density, substitute approaches, and whitespace in Section E.references/maturity-and-openness-framework.md→ use when assigning development maturity and strategic openness in Sections F–G.references/literature-and-asset-verification-rules.md→ use before naming studies, trials, approvals, or company-linked assets in Sections B–H.references/output-section-guidance.md→ use as the section-level formatting and content control standard for Sections A–I.references/workflow-step-template.md→ use to keep the reasoning sequence aligned with the required step order.
What ships with it
17 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.
- eval_report_drug-target-evidence-landscape_result.json 22 KB
- references/competition-and-crowding-framework.md 236 B
- references/competition-landscape-rules.md 334 B
- references/druggability-and-modality-framework.md 423 B
- references/druggability-and-modality-rules.md 331 B
- references/evidence-layer-taxonomy.md 255 B
- references/literature-and-asset-verification-rules.md 322 B
- references/literature-integrity-rules.md 1.1 KB
- references/literature-retrieval-and-citation.md 491 B
- references/maturity-and-openness-framework.md 360 B
- references/output-section-guidance.md 261 B
- references/preclinical-clinical-evidence-ladder.md 344 B
- references/scope-and-input-rules.md 239 B
- references/scope-framing-rules.md 457 B
- references/target-assessment-framework.md 424 B
- references/translation-readiness-rules.md 426 B
- references/workflow-step-template.md 247 B
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 · 296 lines · 109 tokens per session scan A b218053f8e45
drug-target-evidence-landscape is a skill published in the GitHub repository aipoch/medical-research-skills (1,860 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 2,628 once invoked, about $0.0005 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
scanpy
Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use…
microbiome
Microbiome analysis — compositional data handling, 16S/ITS amplicon, shotgun metagenomics, diversity, differential abundance, and functional profiling.
statistical-modeling
Statistical modeling and machine learning for biomarker discovery, survival analysis, classification, regression, and model interpretation.
bulk-transcriptomics
Bulk RNA-seq and microarray differential expression analysis including method selection, batch correction, and complex experimental designs.
chromatin-regulation
Chromatin regulation analysis from called peaks and count matrices — differential binding, signal summarisation, peak annotation, and scATAC-seq.
spatial-omics
Spatial transcriptomics and spatial proteomics analysis covering technology-specific workflows, spatial statistics, deconvolution, and niche analysis.