preclinical-pkpd-analyst

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

Quality

45%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/preclinical-pkpd-analyst/SKILL.md

Quality

Content

52%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured with validation checkpoints and concrete compile/help commands, but it suffers from verbatim description repetition and boilerplate padding, and it never demonstrates the actual PK analysis invocation with data. Tightening the redundancy and adding a real usage example would lift the weaker dimensions.

Suggestions

Remove the verbatim repetition of the frontmatter description in the 'When to Use' and 'Key Features' sections.

Add a complete, copy-paste-ready analysis command with sample input (e.g. a concentration-time CSV) showing the AUC/Cmax output.

Provide or remove the referenced requirements.txt so declared dependencies resolve to a real bundle file.

Dimension	Reasoning	Score
Conciseness	The description is repeated verbatim in both 'When to Use' and 'Key Features', and several sections are templated boilerplate ('See Prerequisites above', 'See Workflow above') that pad the body without adding skill-specific value.	2 / 5
Actionability	Concrete validation commands are present ('python -m py_compile scripts/main.py', 'python scripts/main.py --help'), but the actual analysis invocation with real inputs is never shown, leaving the core executable guidance incomplete.	3 / 5
Workflow Clarity	The numbered Workflow has explicit validation checkpoints (scope check, stop-early) and a feedback loop (fallback path on failure), plus a Security Checklist, but the steps remain somewhat abstract rather than command-anchored, so it stops short of a 5.	4 / 5
Progressive Disclosure	The single SKILL.md plus scripts/main.py is well sectioned and the referenced script path is real, but cross-references like 'See Prerequisites above' and a declared-but-absent requirements.txt introduce minor organization gaps.	4 / 5
	Total	13 / 20 Passed

Description

37%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description identifies a real niche but relies on generic process language instead of concrete PK/PD actions or natural user trigger terms. It is distinguishable only because of the domain name, not because of how the trigger is phrased.

Suggestions

Replace abstract process phrases with concrete capabilities, e.g. 'Calculate PK parameters (AUC, Cmax, Tmax, T1/2, clearance) from concentration-time data'.

Add natural trigger terms users actually say, such as 'pharmacokinetic analysis', 'non-compartmental analysis', or 'NCA'.

State an explicit 'Use when ...' clause tied to the PK/PD task rather than to generic workflow structure.

Dimension	Reasoning	Score
Specificity	Names the domain ('preclinical pkpd analyst') but the actions are generic process qualities ('structured execution, explicit assumptions, clear output boundaries') rather than concrete PK/PD operations like AUC or NCA calculation.	2 / 5
Completeness	A 'Use ... for' trigger clause is present and a vague 'what' is implied via 'data analysis workflows', but neither the what nor the when is concrete, so it sits at the weak-when/weak-what midpoint rather than a clear 4.	3 / 5
Trigger Term Quality	Beyond the skill name, the trigger language ('data analysis workflows that need structured execution') is process jargon rather than natural user phrasing; natural terms like 'pharmacokinetic', 'AUC', or 'Cmax' are absent.	2 / 5
Distinctiveness Conflict Risk	The 'preclinical pkpd' niche is somewhat specific, but the surrounding generic 'data analysis workflows that need structured execution' language could still overlap with many analysis skills, capping it below 4.	3 / 5
	Total	10 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/preclinical-pkpd-analyst/SKILL.md
Commit: 63c61d3

Reviewed: 9 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.