drug-discovery

Drug discovery: ChEMBL search, drug-likeness, interactions.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/research/drug-discovery/SKILL.md

Quality

Content

82%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 body is highly actionable with five complete, executable API workflows and a useful quick-reference table, supported by a well-organized ADMET reference file. Main gaps are the unreferenced scripts bundle and the absence of explicit validation/retry checkpoints.

Suggestions

Reference the bundled scripts from the relevant workflows (e.g., "For batch screening, run scripts/ro5_screen.py aspirin ibuprofen paracetamol") so the scripts/ bundle is discoverable.

Add explicit validation/retry checkpoints for batch and rate-limited calls (e.g., check HTTP status, retry on 429, confirm non-empty results before proceeding).

Trim the persona preamble and database descriptions to assume Claude's domain competence and save tokens.

Dimension	Reasoning	Score
Conciseness	The body is dominated by tight, executable snippets with little padding, but the opening persona preamble ("You are an expert pharmaceutical scientist...") and a few descriptive asides ("the world's largest open bioactivity database") are minor over-explanation that could be trimmed.	4 / 5
Actionability	Every workflow is a copy-paste-ready bash+python curl pipeline hitting real endpoints, with concrete example IDs in comments (e.g., CHEMBL203, CHEMBL25) covering the common cases.	5 / 5
Workflow Clarity	Five numbered, self-contained workflows plus a sequenced Reasoning Guidelines checklist give a clear sequence, and snippets include inline empty-result guards; however, there are no explicit validate→fix→retry feedback loops (rate-limit handling is only mentioned in notes).	4 / 5
Progressive Disclosure	Good section structure with one clearly signaled one-level-deep reference ("See references/ADMET_REFERENCE.md"), but the provided scripts/chembl_target.py and scripts/ro5_screen.py are never referenced from the body, leaving the bundle partly unnavigable.	4 / 5
	Total	17 / 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 concise and names a clear, niche domain with a few concrete actions, but it lacks any explicit "Use when..." trigger guidance and some action labels are terse. Adding trigger phrases and tightening the action wording would raise it.

Suggestions

Append a "Use when..." clause listing concrete trigger phrases (e.g., "Use when searching ChEMBL for bioactive compounds, assessing drug-likeness, or checking drug interactions").

Expand terse labels ("drug-likeness", "interactions") into concrete actions like "calculates Lipinski/Veber drug-likeness" and "looks up drug interactions and adverse events".

Add common synonyms such as "pharmacology", "medicinal chemistry", and "ADMET" to broaden natural-term coverage.

Dimension	Reasoning	Score
Specificity	Names the drug-discovery domain plus a few actions ("ChEMBL search, drug-likeness, interactions"), but "drug-likeness" and "interactions" are terse property labels rather than fully concrete actions, so coverage is not comprehensive.	3 / 5
Completeness	Provides a clear "what" but no "Use when..." clause or explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Includes natural terms a researcher would say ("Drug discovery", "ChEMBL search", "interactions", "drug-likeness"), but omits common synonyms such as "pharmacology", "medicinal chemistry", or "ADMET".	4 / 5
Distinctiveness Conflict Risk	The ChEMBL-specific framing carves a clear niche with low conflict risk, though it could still overlap slightly with a generic chemistry/research skill.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

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

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/research/drug-discovery/SKILL.md
Commit: 145c713

Reviewed: 1 hour 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.