ClawHub

Pre-clinical PK/PD Analyst

v1.0.0

Use preclinical pkpd analyst for data analysis workflows that need structured execution, explicit assumptions, and clear output boundaries.

⭐ 0· 58·0 current·0 all-time
byAIpoch@aipoch-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The packaged script (scripts/main.py) implements PK parameter estimation (one-compartment model, AUC, Cmax, Tmax, t1/2, clearance), matching the skill name and description. Declared dependencies (numpy, scipy) are appropriate for this purpose.
✓
Instruction Scope
SKILL.md instructs validating inputs, running the packaged script, and returning bounded deliverables. Runtime instructions and the script operate on local input files only; they do not read unrelated system files, environment variables, or send data externally.
✓
Install Mechanism
No install spec is present (instruction-only with an included script). Dependencies are declared in requirements.txt (numpy, scipy) — standard Python packages from PyPI; nothing is downloaded from arbitrary URLs or written to unexpected locations.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. The script reads an explicit input CSV if provided and otherwise runs demo data — no secret access is required.
✓
Persistence & Privilege
always is false and the skill does not request any persistent or system-wide privileges. It does not modify other skills or agent configurations.
Assessment
This skill appears internally consistent and appropriate for local PK analysis. Before installing/run: 1) run the provided demo (--demo) in an isolated or sandboxed environment to verify behavior; 2) install numpy and scipy in a controlled virtualenv so dependencies don't affect your system; 3) ensure input CSV files are well-formed (time,concentration) and validate units/dose assumptions (the script assumes dose=1 when computing Clearance); 4) be aware the script performs numeric model fitting (curve_fit) which can produce unstable parameter estimates for poor data — review outputs and assumptions before using results for decisions. If you need regulatory-grade results, perform additional validation and code review for edge cases (e.g., very small ke leading to large t1/2, or model fit failures).

Like a lobster shell, security has layers — review code before you run it.

latestvk97300p07pftf595qg9ykr5eyn83xr19

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments