denovo-design

De novo molecule generation for drug discovery. Scaffold-based analog enumeration, fragment growing/linking, structure-based design, multi-objective optimization, and drug-likeness filtering.

Quality

77%

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/denovo-design/SKILL.md

Quality

Content

87%

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

The content is highly actionable and concise, with executable commands throughout and clean one-level-deep references to the bundled scripts; the main gap is the absence of explicit validation/verification checkpoints for batch generation workflows.

Suggestions

Add explicit verification checkpoints after batch generation steps (e.g., "After generating, inspect the property-distribution summary; if bimodal or out-of-range, adjust strategy and regenerate"), turning the existing Tips into inline validate→fix→retry loops.

Surface the recommended cross-script pipeline (analogs → filter → optimize) as a numbered workflow with intermediate validation rather than only as a prose tip.

Dimension	Reasoning	Score
Conciseness	The body is lean and dominated by executable commands with real example SMILES and flags; prose is minimal and purposeful (decision table, filter thresholds, tips) rather than padded with concepts Claude already knows.	3 / 3
Actionability	Every workflow provides copy-paste-ready bash commands with concrete arguments (e.g., `--smiles "c1ccc(NC(=O)c2ccccc2)cc1" --strategy all`) plus documented output columns and filter thresholds.	3 / 3
Workflow Clarity	Sequencing is clear via the scenario→script decision table and the "Start broad, then narrow" pipeline tip, but batch generation operations lack explicit validate→fix→retry checkpoints, capping workflow clarity at 2.	2 / 3
Progressive Disclosure	All five bundle scripts in scripts/ are referenced one level deep with correct paths, the SKILL.md stays an organized overview, and the decision table provides easy navigation — no nested/deep references.	3 / 3
	Total	11 / 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 distinct, naming five concrete capabilities in a clear niche, but it omits an explicit "Use when..." trigger clause so the completeness and trigger-term quality are not maximal.

Suggestions

Add an explicit "Use when..." clause naming natural user triggers (e.g., "Use when generating novel drug candidates, enumerating analogs of a lead, or designing molecules from fragments or a protein pocket").

Include colloquial trigger variations users would actually say (e.g., "design new molecules", "make analogs", "build a compound library") alongside the technical terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Scaffold-based analog enumeration, fragment growing/linking, structure-based design, multi-objective optimization, and drug-likeness filtering" — rather than vague language.	3 / 3
Completeness	Clearly states what the skill does, but the "when" is only implied — there is no "Use when..." clause, which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Contains relevant domain keywords ("molecule generation", "drug discovery", "drug-likeness filtering") but lacks common colloquial variations and explicit "Use when" trigger phrasing users would naturally say.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (de novo molecule design for drug discovery) with distinct triggers unlikely to conflict with other 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/denovo-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.