Mr Scrna Research Planner
v0.1.0Generates complete Mendelian Randomization + single-cell transcriptomics (scRNA-seq) research designs from a user-provided direction. Always use this skill w...
⭐ 0· 202·1 current·1 all-time
byAIpoch@aipoch-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (MR + single-cell research planner) matches the provided instructions and reference documents. All referenced modules, data sources (IEU OpenGWAS, GTEx, GEO, etc.), and methods are expected for this type of study; nothing in the manifest asks for unrelated credentials, binaries, or system access.
Instruction Scope
SKILL.md contains prescriptive, domain-specific step-by-step planning instructions and templates; it does not instruct the agent to read local sensitive files, environment variables, or contact opaque external endpoints. It is narrowly scoped to producing study designs and explicitly excludes clinical trial/regulated protocol generation.
Install Mechanism
No install spec and no code files are present (instruction-only). Nothing is downloaded or written to disk by the skill itself, minimizing installation risk.
Credentials
The skill declares no required environment variables, credentials, or config paths. The methods it recommends (GWAS/eQTL resources, public datasets) normally require API keys only when the user chooses to fetch data, but the skill itself does not request them.
Persistence & Privilege
Flags show always:false and no special persistence or privilege escalation. The skill does not ask to modify other skills or system settings.
Assessment
This skill is instruction-only and coherent for producing MR + scRNA-seq study plans. Before using outputs: (1) treat the plan as advisory — have a domain expert/statistician verify details and assumptions (instrument selection, multiple-testing, population ancestry, etc.); (2) do not paste patient-level or controlled-access data into prompts; when you or the agent fetch public GWAS / eQTL / scRNA datasets, ensure you have the right access/permissions and follow IRB/data-use rules; (3) the skill recommends tools and data sources but does not run analyses — executing the plan will require installing third-party software and possible API keys (those should be provided only to trusted tooling); (4) check the suggested language rules and evidence tiers carefully — wording around 'causal' claims must match the level of evidence; and (5) if you need the agent to actually retrieve data or run code, consider the additional risks of granting network or execution privileges and review those actions separately.Like a lobster shell, security has layers — review code before you run it.
latestvk976jpka09k4scs6mkametsve182vxev
License
MIT-0
Free to use, modify, and redistribute. No attribution required.