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

70%

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/drug-design/SKILL.md

Quality

Content

68%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 body is highly actionable with executable commands and clear stage mappings, but it is padded with repeated mode tables and lacks explicit validation/feedback loops for its batch pipeline operations. Tightening the prose and surfacing validate-then-retry steps would materially raise the score.

Suggestions

Add explicit validation checkpoints for the batch pipeline (e.g. 'After docking, verify poses.sdf is non-empty and scores.csv parses before running scoring'), with a fix-and-retry loop, to lift workflow_clarity above the batch-operation cap.

Consolidate the five repeated mode stage tables into a single canonical stage reference, with per-mode subset annotations, to reduce redundant scaffolding and improve conciseness.

Trim the 'Why a script instead of manual chaining' rationale to one line or move it to a separate reference, since the rationale is largely self-evident to Claude.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with well-structured tables, but the five mode-specific stage tables and the 'Why a script instead of manual chaining' prose repeat scaffolding Claude largely already understands, leaving it tighter-than-anchor-3 but not yet lean.	3 / 5
Actionability	Copy-paste ready commands for every mode with concrete arguments, plus a full argument reference and executable diagnostic snippets ('python -c "from rdkit import Chem; ..."'), covering the common cases completely.	5 / 5
Workflow Clarity	Stage sequences are clearly tabulated per mode, but the markdown provides no explicit validation/feedback checkpoints for these batch pipeline operations; per the rubric, missing validation in batch operations caps workflow_clarity at 3.	3 / 5
Progressive Disclosure	Good structure with clearly signaled sections, real bundle file (scripts/pipeline.py), related-skills links, and references; the inlined multi-mode stage tables could arguably live in a dedicated reference file, leaving minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

71%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 distinctive, concretely enumerating the pipeline's chained stages, but it omits an explicit 'when to use' trigger clause, capping completeness. Adding a 'Use when...' sentence with natural user phrases would lift the description to a top-tier example.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when the user asks to find drugs for a target, screen a compound library, optimize a hit, or assess druggability.'

Add a few natural-language synonyms users would actually say ('find drugs', 'screen compounds', 'is this target druggable') alongside the technical terms to broaden trigger coverage.

Clarify distinction from the individual skills it wraps by noting it is the orchestration entry point when a full workflow rather than a single step is needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'structure prediction, pocket detection, de novo design, docking, scoring, and ADMET filtering' — giving comprehensive coverage of the pipeline's capabilities.	5 / 5
Completeness	The 'what' is clearly stated but there is no 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Strong domain keywords ('drug discovery pipeline', 'docking', 'ADMET', 'de novo design') but leans technical; a few natural user-facing synonyms are missing, so it sits just above the 'some relevant keywords' anchor rather than at full coverage.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (end-to-end drug discovery orchestration) with minimal overlap risk against adjacent single-purpose skills, though it borders on overlapping with the individual skills it chains.	4 / 5
	Total	16 / 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/drug-design/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.