admet-reasoning

Interpretable ADMET analysis with mechanistic reasoning. Maps liabilities to structural causes and biological pathways. Based on CoTox (Park 2025) and DrugR (Liu 2026).

Quality

62%

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 ./backend/cli/skills/chemistry/admet-reasoning/SKILL.md

Quality

Content

66%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 content is concise, actionable, and well-structured with executable CLI examples and a clear script reference. Its main weakness is the absence of validation/verification checkpoints for batch and targeted workflows, which the rubric caps at workflow_clarity 3.

Suggestions

Add validation checkpoints to the batch workflow, e.g. verify the CSV was parsed, confirm expected endpoint columns exist, and report counts of flagged liabilities before writing the output.

Show a minimal example of the report.json output structure so users know what fields (liabilities, causes, mechanisms, fixes) to expect and verify.

Add a brief error-recovery note for when the script fails or returns no liabilities for a given SMILES.

Dimension	Reasoning	Score
Conciseness	The body is efficient and well-organized with minimal padding; the Overview and reference citations are tight, though the 'Based on' research summaries add a small amount of explanatory context that could be trimmed.	4 / 5
Actionability	Provides three concrete, copy-pasteable CLI invocations and a script reference table with key outputs, but lacks inline examples of the JSON/CSV output structure a user would inspect.	4 / 5
Workflow Clarity	Batch and targeted workflows involve potentially destructive or bulk operations yet include no validation or verification checkpoints (e.g. confirming the report parsed, checking for empty endpoints); the rubric caps batch/destructive skills without validation at 3.	3 / 5
Progressive Disclosure	Structure is clean with a concise overview, when-to-use guidance, related-skills links, and a single one-level-deep script reference; the bundle is minimal (one script) and appropriately signaled, with only minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

58%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 specific and distinct, naming concrete mechanistic reasoning actions, but it omits an explicit 'Use when...' trigger clause and relies on technical phrasing over natural user keywords. Adding trigger conditions and common synonyms would lift completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when interpreting ADMET liability scores, planning lead optimization, or generating toxicity reports for medicinal chemistry teams.'

Include natural trigger terms and synonyms users would say, such as 'ADMET scores', 'toxicity interpretation', 'hERG liability', or 'drug safety profile'.

Clarify distinction from sibling skills inline, e.g. 'Use admet-prediction for raw scores and molecular-optimization for structure changes; this skill explains why.'

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Interpretable ADMET analysis', 'Maps liabilities to structural causes and biological pathways'), but does not enumerate the full set of operations the script supports, leaving minor gaps in coverage.	4 / 5
Completeness	It clearly states what the skill does (interpretable ADMET analysis with mechanistic reasoning) but provides no explicit 'Use when...' clause or concrete trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes relevant terms like 'ADMET', 'liabilities', 'structural causes', and 'biological pathways', but lacks common synonyms or file extensions a user would naturally say; the phrasing leans technical rather than natural user language.	3 / 5
Distinctiveness Conflict Risk	The 'interpretable ADMET analysis with mechanistic reasoning' framing carves a clear niche distinct from raw score prediction or optimization, with only minor overlap risk against the related admet-prediction and molecular-optimization skills.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/chemistry/admet-reasoning/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day 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.