lipinski-rule-filter

Filter compound libraries based on Lipinski's Rule of Five for drug-likeness.

Quality

55%

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/lipinski-rule-filter/SKILL.md

Quality

Content

50%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 skill is actionable with concrete commands and a real bundle split, but the body is bloated with generic template boilerplate and lacks concrete validation for its batch-filtering operation, capping both conciseness and workflow clarity.

Suggestions

Remove or externalize the generic template sections (Risk Assessment, Security Checklist, Lifecycle Status, Response Template) that are not Lipinski-specific to cut padding.

Add a concrete validation checkpoint for the batch filter (e.g., compare input vs. output compound counts, spot-check violation tallies on a few examples) before declaring success.

Replace the generic 'references/' pointer with a named link such as [lipinski_references.md](references/lipinski_references.md) and delete the repeated 'See ## X above for related details' cross-pointers.

Dimension	Reasoning	Score
Conciseness	The ~196-line body is padded with generic template boilerplate (Risk Assessment, Security Checklist, Lifecycle Status, Response Template) and repeated 'See ## X above for related details' pointers that are not Lipinski-specific knowledge, matching 'noticeably verbose; several unnecessary explanations or padded sections'.	2 / 5
Actionability	Provides copy-paste-ready commands with real flags ('python scripts/main.py --input compounds.smi --output filtered.smi', '--smiles ... --check'), a concrete Parameters table, and the four Lipinski rules, which is mostly executable guidance with only minor gaps around showing the output artifacts.	4 / 5
Workflow Clarity	A clear 5-step sequence with an explicit fallback is present, but validation checkpoints are abstract rather than concrete output verification, and because this is a batch file-filtering operation the missing validation cap holds workflow clarity at 3.	3 / 5
Progressive Disclosure	Real section structure and a one-level-deep bundle exist (references/ and scripts/main.py), but the body inlines substantial generic template content and only references the bundle by the generic 'references/' path rather than a named file link, so structure is present but not clearly signaled or well organized.	3 / 5
	Total	12 / 20 Passed

Description

61%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 is domain-accurate and names the key framework, but it omits an explicit 'when to use' trigger, which caps completeness, and would benefit from a few more natural synonyms and a broader action list.

Suggestions

Add an explicit 'Use when...' clause naming the natural triggers (e.g., 'Use when filtering compound libraries, screening SMILES/SDF files, or checking Rule of Five / Ro5 drug-likeness').

Expand the action list to several concrete actions (e.g., compute MW/LogP/HBD/HBA, count violations, output passing compounds and a violation report) to lift specificity.

Include common synonyms and file extensions ('Rule of 5', 'Ro5', 'ADME', '.smi', '.sdf') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('Filter compound libraries') plus the governing framework ('Lipinski's Rule of Five'), but does not enumerate several distinct actions of the pipeline, so it sits between anchors 3 and 4 rather than reaching 'several specific actions'.	3 / 5
Completeness	Clearly states what the skill does but has no explicit 'Use when...' clause, so per the missing-trigger-guidance rule completeness is capped at 3 ('clear what, when missing or only weakly implied').	3 / 5
Trigger Term Quality	Includes the natural domain terms a user would say ('compound libraries', 'Lipinski's Rule of Five', 'drug-likeness') but omits common synonyms/extensions like 'Rule of 5', 'Ro5', 'ADME', or '.smi/.sdf', matching 'good keyword coverage; a few natural terms missing'.	4 / 5
Distinctiveness Conflict Risk	The Rule-of-Five/compound-library niche is specific with low conflict risk, but 'drug-likeness' is broad enough to allow slight overlap with general ADME/drug-likeness skills, placing it just below the fully-distinct anchor 5.	4 / 5
	Total	14 / 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/lipinski-rule-filter/SKILL.md
Commit: f5ef65b

Reviewed: ~3 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.