drug-design

End-to-end drug discovery pipeline orchestration. Deterministic Python script that auto-chains structure prediction, pocket detection, de novo design, docking, scoring, and ADMET filtering into reproducible workflows.

Quality

83%

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

Quality

Content

100%

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

The body is an actionable, well-organized operational reference: executable commands for each mode, explicit I/O contracts with validation guidance, and error-recovery feedback, with implementation appropriately delegated to the bundled script.

Dimension	Reasoning	Score
Conciseness	The body is dense, navigable reference material — commands, stage tables, I/O schemas, and an error table — with virtually no prose explaining concepts Claude already knows; every section earns its place.	3 / 3
Actionability	Provides fully executable copy-paste commands for every mode, a complete argument reference table, concrete JSON I/O schemas, and specific error fixes — all copy-paste ready.	3 / 3
Workflow Clarity	Multi-stage processes are explicitly sequenced per mode with per-stage input/output contracts, cross-stage schema validation ('catches schema mismatches early', 'Stops on first failure'), and a feedback-oriented error-recovery table.	3 / 3
Progressive Disclosure	SKILL.md is a clear, well-sectioned overview and pushes the heavy implementation one level deep into the bundled scripts/pipeline.py (a real, correctly-referenced file); references are one level deep with no nested pointer chains.	3 / 3
	Total	12 / 12 Passed

Description

67%

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 occupies a clear niche, but it omits any explicit 'when to use this skill' trigger guidance and leans on technical jargon over natural user phrasing.

Suggestions

Add a 'Use when...' clause naming natural trigger phrases (e.g., 'Use when the user asks to run a drug discovery pipeline, find/screen drugs for a target, or assess druggability').

Soften jargon like 'deterministic Python script' and 'auto-chains' in favor of user-facing phrasing to improve trigger-term quality.

Include common user variations such as 'virtual screening', 'lead optimization', and 'druggability assessment' as explicit keywords.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete, specific actions — 'structure prediction, pocket detection, de novo design, docking, scoring, and ADMET filtering' — matching the anchor for naming several specific concrete actions.	3 / 3
Completeness	Clearly answers 'what' (orchestrates a multi-stage drug-discovery pipeline) but provides no 'Use when...' or equivalent explicit 'when' trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	Contains some natural terms ('drug discovery', 'de novo design') but is dominated by technical jargon ('deterministic Python script', 'auto-chains') and lacks common user-spoken variations; not a 1 because real keywords are present.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear, narrow niche (end-to-end drug-discovery pipeline orchestration) with domain-specific vocabulary, making it unlikely to trigger for or conflict with unrelated skills.	3 / 3
	Total	10 / 12 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/drug-design/SKILL.md
Commit: 52845c3

Reviewed: about 11 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.