molecular-optimization

Iterative lead optimization with analyze-reason-generate-verify-evaluate loop. Paper-backed (MT-Mol, DrugR, MultiMol).

Quality

71%

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/molecular-optimization/SKILL.md

Quality

Content

85%Weight 40%Scale 1-3

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

The body is a strong, actionable skill document with executable commands, a clearly sequenced and validated optimization protocol, and well-organized sections referencing real scripts. Its main weakness is promotional paper-benchmark prose in the Overview that adds tokens without aiding execution.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes competence (no basic-concept explanations), but the Overview's paper benchmark claims ('SOTA on 17/23 PMO tasks', '18x improvement', '82.3% success rate') are promotional padding Claude does not need, matching 'mostly efficient but includes some unnecessary explanation'.	2 / 3
Actionability	Workflows give fully executable, copy-paste bash commands with concrete arguments, a script reference table, and the referenced scripts (optimize.py, verify_smiles.py, compare_candidates.py) are real and syntactically valid, matching the 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	The six-step protocol is explicitly sequenced with a dedicated VERIFY step (discard if None, scaffold match, Tanimoto flag, structural check) and an iterate-or-honestly-report feedback loop, matching 'clear sequence with explicit validation steps; feedback loops for error recovery'.	3 / 3
Progressive Disclosure	Content is well-organized into clear sections, and the only bundle files (scripts/*) are one-level-deep, real, and clearly signaled via the Script Reference table and workflow commands with no nested-reference chains, matching the well-organized overview anchor.	3 / 3
	Total	11 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 names a specific niche and process but lacks explicit use-when triggers and leans on obscure paper names instead of natural user terms. It is specific enough to avoid conflicts but incomplete on when-to-use guidance.

Suggestions

Add an explicit 'Use when ...' clause listing natural triggers such as 'lead optimization', 'ADMET optimization', 'scaffold hopping', or 'improving potency/selectivity of a hit'.

Replace or supplement the paper-citation shorthand ('MT-Mol, DrugR, MultiMol') with capability language users would actually say.

Spell out concrete actions (e.g. 'generate analogs, verify SMILES, rank by ADMET improvement') instead of only naming the loop.

Dimension	Reasoning	Score
Specificity	Names the domain ('lead optimization') and the loop steps ('analyze-reason-generate-verify-evaluate') but these are abstract process labels rather than a comprehensive list of concrete capability actions, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It answers 'what' (iterative lead optimization with a named loop) but provides no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	'lead optimization' is a natural user term, but coverage is thin and dominated by jargon ('analyze-reason-generate-verify-evaluate loop', 'MT-Mol, DrugR, MultiMol') that users would almost never say, missing common variations like 'ADMET', 'scaffold hopping', or 'molecular optimization'.	2 / 3
Distinctiveness Conflict Risk	'Lead optimization' is a clear, narrow niche distinct from de novo design or pure ADMET prediction, and the named protocol makes it unlikely to trigger for the wrong skill.	3 / 3
	Total	9 / 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/molecular-optimization/SKILL.md
Commit: dc00e07

Reviewed: 9 days 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.