CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

medchem

Applies medicinal chemistry filters for compound triage, using drug-likeness rules (Lipinski, Veber, CNS), structural alert catalogs (PAINS, NIBR, ChEMBL), complexity metrics, and the medchem query language for library filtering.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A well-structured, highly actionable reference: executable code with expected outputs, three concrete workflow patterns with explicit batch-input validation, and clean progressive disclosure to verified bundle files. The only trimming opportunities are the pinned version strings and a few dense caveat paragraphs.

DimensionReasoningScore

Conciseness

Mostly lean: code examples dominate, annotations are terse and non-obvious (e.g. the bredt_filter kekulization caveat, severity semantics), and no space is spent explaining concepts Claude already knows. Not anchor 5 because pinned time-sensitive version numbers ('medchem 2.1.1', 'RDKit 2026.3.6') sit in the body rather than a deprecated/old-patterns section, and a few dense caveat paragraphs (the scripts/filter_molecules.py prose block) could be tightened.

4 / 5

Actionability

Fully executable, copy-paste-ready guidance: a pinned install command, snippets showing expected outputs ('# ['rule_of_five', ...]', 'df columns: mol, pass_filter, status, reasons'), a complete Pattern 1 flow from pd.read_csv to filtered_compounds.csv, query-language syntax with concrete examples, and a runnable CLI script with an invocation line — covering the common cases per anchor 5.

5 / 5

Workflow Clarity

Three clearly sequenced workflow patterns, and batch validation is explicitly addressed — Pattern 1 requires 'assign stable source-row IDs and separate failed SMILES/SDF parses' and 'report input, parsed, rule-failed, and retained counts', and best practices mandate 'Prevalidate inputs' and validating finite complexity scores. Anchor 4 rather than 5 because there is no explicit validate→fix→retry feedback loop or error-recovery steps for failed parses.

4 / 5

Progressive Disclosure

A clear overview body with key inline examples, and a Resources section that well-signals one-level-deep references ('references/api_guide.md — Module-by-module API reference', 'references/rules_catalog.md — Catalog of available rules...') plus scripts/filter_molecules.py with usage; all referenced files exist and match their descriptions, with bulk signature/catalog detail correctly split into the reference files — matching anchor 5.

5 / 5

Total

18

/

20

Passed

Description

70%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.

A specific, distinctive, third-person description that names concrete capabilities with well-chosen examples (Lipinski, PAINS, NIBR, ChEMBL). Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness, and a few missing natural synonyms.

Suggestions

Append an explicit trigger clause, e.g. 'Use when triaging compound libraries, applying Lipinski/Ro5 or Veber drug-likeness rules, removing PAINS or structural alerts, or filtering screening decks / hit-to-lead candidates.'

Add missing natural trigger synonyms such as 'Ro5'/'rule of five', 'structural alerts', and 'hit-to-lead' so users' phrasing matches the description.

Mention chemical-group/functional-group detection and scaffold constraints to close the coverage gap with the body's capability sections.

DimensionReasoningScore

Specificity

Lists several specific concrete capabilities with named examples — 'Applies medicinal chemistry filters for compound triage', 'drug-likeness rules (Lipinski, Veber, CNS)', 'structural alert catalogs (PAINS, NIBR, ChEMBL)', 'complexity metrics', 'the medchem query language' — but omits chemical-group detection and scaffold constraints that the body covers, which is a minor coverage gap matching anchor 4 rather than the comprehensive coverage of anchor 5.

4 / 5

Completeness

The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance; per the rubric this caps completeness at 3. It is above anchor 2 because the what is specific rather than vague, and below anchor 4 because the 'when' is only weakly implied from the capability list.

3 / 5

Trigger Term Quality

Good natural keyword coverage ('medicinal chemistry filters', 'Lipinski', 'PAINS', 'drug-likeness', 'compound triage', 'library filtering') but a few natural terms users would say are missing, such as 'Ro5'/'rule of five', 'structural alerts' alone, 'hit-to-lead', or 'screening deck' — anchor 4, short of anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

'medicinal chemistry filters', 'PAINS', 'NIBR', 'Veber', and 'the medchem query language' carve out a clear niche with distinct domain-specific triggers; minimal conflict risk with other skills.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

K-Dense-AI/scientific-agent-skills

Path

skills/medchem/SKILL.md

Reviewed

Table of Contents

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.