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

75%

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

76%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 highly actionable with executable examples and good bundle-file structure, but it lacks explicit validation checkpoints for its batch generation operations, capping workflow clarity.

Suggestions

Add explicit validation checkpoints to the batch workflows, e.g. 'Verify the output CSV is non-empty and SMILES are canonical/deduplicated before running optimize.py.'

Trim the Overview paragraph to avoid restating the strategy list already present in the table and section headers.

Consider a short 'Verify' step in the Tips pipeline (generate → validate → filter → optimize) with concrete commands or checks between stages.

Dimension	Reasoning	Score
Conciseness	The body is largely lean with copy-paste commands and brief strategy bullets, but the Overview paragraph restates the strategy list already shown in the table and section headers, a minor instance of over-explanation.	4 / 5
Actionability	Every workflow provides copy-paste-ready bash commands with real SMILES/PDB examples, documented flags, specified output CSV columns, and concrete filter thresholds.	5 / 5
Workflow Clarity	Workflows and an end-to-end pipeline are sequenced, but these are batch generation operations with no explicit validation/verification checkpoints, which per the guidelines caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Five real bundle scripts in ./scripts/ are surfaced via a scenario→script table and per-workflow commands, giving good one-level-deep structure, though references are invoked-by-command rather than navigable doc pointers.	4 / 5
	Total	16 / 20 Passed

Description

75%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 with strong capability coverage, but it omits any explicit trigger guidance for when to use the skill, capping completeness at 3.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when generating novel molecules for drug discovery, enumerating analogs, or filtering compound libraries for drug-likeness.'

Add common user-facing synonyms and file extensions to trigger term coverage, such as 'generate molecules', 'design ligands', 'analog enumeration', '.sdf', '.smi'.

Lead with the action verb (third person) to mirror the strong example style, e.g. 'Generates novel molecules...'.

Dimension	Reasoning	Score
Specificity	Lists five concrete capabilities ('Scaffold-based analog enumeration, fragment growing/linking, structure-based design, multi-objective optimization, and drug-likeness filtering'), giving comprehensive coverage of the skill's surface.	5 / 5
Completeness	The 'what' is clearly stated, but there is no explicit 'Use when...' or 'when' clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Natural domain terms like 'de novo molecule generation', 'drug discovery', and 'drug-likeness filtering' are present, but common user synonyms and file-type triggers (e.g. 'generate molecules', '.sdf/.smi') are missing.	4 / 5
Distinctiveness Conflict Risk	'De novo molecule generation for drug discovery' carves out a clear specialized niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	17 / 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/denovo-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.