smiles-validation

Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.

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/smiles-validation/SKILL.md

Quality

Content

80%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 an efficient, well-structured, actionable overview: three executable workflows, a verified script reference, and no padding. The two real weaknesses are the batch workflow's missing feedback loop (what to do with invalid molecules) and an undeclared pandas dependency for the batch path.

Suggestions

Add a feedback step to the batch workflow, e.g., "After batch validation, review the report; regenerate or discard invalid entries before reporting results" — this would lift workflow clarity above the batch-operation cap.

Declare pandas (or remove the pandas import) and state the expected CSV column convention ('SMILES' by default, --smiles-col to override) in the batch workflow section.

Optionally show a snippet of the JSON report schema or example output so Claude knows how to interpret validity, similarity, and modification-verification results.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence: it never explains what SMILES or RDKit are, and every section (Overview, When to Use, Installation, three workflows, reference table) earns its place. It matches anchor 5's 'every token earns its place'.	5 / 5
Actionability	All three core workflows give concrete, copy-paste-ready commands with realistic arguments, plus a script reference table with key outputs. Minor gaps remain: the batch workflow requires pandas (not in Installation or the declared dependencies) and does not state the expected CSV column convention ('SMILES' by default, overridable via --smiles-col).	4 / 5
Workflow Clarity	The single-validation and comparison workflows are unambiguous commands, but the batch validation workflow (workflow 3) provides no feedback loop — no guidance on what to do with invalid results (regenerate, discard, review issues). The rubric explicitly caps workflow clarity at 3 for batch operations lacking validation/feedback steps, and this cap takes precedence over the simple-skill exception.	3 / 5
Progressive Disclosure	The skill is ~50 lines with well-organized sections and a single real bundle script (scripts/validate.py, verified to exist) correctly surfaced via a reference table. Per the rubric's simple-skill guidance, well-organized sections with no need for external references warrant a 5.	5 / 5
	Total	17 / 20 Passed

Description

70%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 distinct, correctly naming three concrete capabilities in the cheminformatics niche. Its main weakness is the complete absence of a "Use when..." trigger clause, which caps completeness and limits how reliably a user or Claude would know when to invoke it.

Suggestions

Add an explicit trigger clause, e.g., "Use when validating SMILES strings, verifying molecular modifications, or checking LLM-generated molecules before reporting results."

Include a few natural synonyms or file/context cues (e.g., "molecular structures", "validity check", "generated molecule libraries") to broaden trigger-term coverage.

Optionally mention the batch/library validation capability to round out coverage of what the skill does.

Dimension	Reasoning	Score
Specificity	"Strict SMILES validation, structural comparison, and modification verification" lists several concrete actions on a named domain, with minor gaps (no mention of batch checking or similarity metrics). It is above anchor 3 (which expects only 1-2 concrete actions) but not anchor 5's comprehensive coverage.	4 / 5
Completeness	The "what" is clear (validation, structural comparison, modification verification), but there is no "Use when..." clause or equivalent explicit trigger guidance; "Catches invalid LLM-generated molecules" is part of the what and only weakly implies when. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Natural keywords like "SMILES", "molecules", "invalid", and "LLM-generated" would match real user phrasing. A few common variations are missing (e.g., "chemical structure", "molecular design", "validity check"), so it falls short of anchor 5's comprehensive synonym/extension coverage.	4 / 5
Distinctiveness Conflict Risk	"SMILES validation" occupies a clear niche with distinct technical vocabulary (SMILES, molecules, structural comparison) that virtually no other skill would trigger on, matching anchor 5's minimal conflict risk.	5 / 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/smiles-validation/SKILL.md
Commit: 4082a2e

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.