smiles-validation

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

Quality

78%

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

87%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 concise, actionable, and well-structured with a real referenced script, but the batch and comparison workflows lack validation checkpoints and feedback loops for acting on failures. Adding an explicit "review the report / handle invalid entries" step would raise workflow clarity.

Suggestions

Add a validation checkpoint to the batch workflow, e.g. "After running, review validation_report.json; re-run failed entries after correcting SMILES."

For the comparison workflow, add a step interpreting the similarity/modification result and what to do when a claimed modification is not confirmed.

Optionally surface the change-classification thresholds (>0.6 / 0.4-0.6 / <0.4) inside the workflow rather than only in the overview so the decision step is explicit.

Dimension	Reasoning	Score
Conciseness	The body is lean: a brief problem statement, a tight key-checks list, one-line install, and concrete commands, assuming Claude's competence without explaining what SMILES or RDKit are; every token earns its place.	5 / 5
Actionability	Three copy-paste-ready bash commands cover the common cases (single validation, original-vs-proposed comparison, batch CSV→JSON) and the script-reference table names exact outputs, matching the fully-executable anchor.	5 / 5
Workflow Clarity	The three workflows are clearly numbered and sequenced, but the batch operation has no validation/verification step or feedback loop for handling invalid molecules, so per the judging guidelines workflow clarity is capped at 3.	3 / 5
Progressive Disclosure	For a sub-50-line single-task skill, the content is well-organized into clear sections and the one bundle file (scripts/validate.py) is correctly referenced via the script table, satisfying the simple-skill exception for a top score.	5 / 5
	Total	18 / 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 occupies a clearly distinct niche, but it lacks an explicit "Use when..." trigger clause, capping completeness. Adding concrete trigger phrasing would lift the completeness and trigger-term scores.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when validating LLM-generated SMILES, verifying a proposed molecular modification, or batch-checking a molecule library."

Include a few natural synonyms a user might say (e.g. "molecular structures", "chemistry", "check molecules") to broaden trigger-term coverage.

Make the actions slightly more granular (e.g. name Tanimoto similarity / scaffold checks) to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	"Strict SMILES validation, structural comparison, and modification verification" lists three concrete actions in a specific domain, matching the anchor that lists several specific actions with minor coverage gaps; not a 5 because the actions are somewhat high-level rather than fully granular.	4 / 5
Completeness	The "what" is clear (validation, comparison, modification verification), but the "when" is only weakly implied by "Catches invalid LLM-generated molecules" with no explicit "Use when..." clause, so per the judging guidelines completeness is capped at 3.	3 / 5
Trigger Term Quality	Natural terms like "SMILES validation", "molecules", and "modification" appear and would be said by users, giving good keyword coverage; not a 5 because it lacks common synonyms or chemistry phrasings users might also say.	4 / 5
Distinctiveness Conflict Risk	SMILES validation is a clear, narrow niche with distinct triggers and minimal overlap risk with other skills, matching the anchor for a clear niche with distinct triggers.	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: 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.