CtrlK
BlogDocsLog inGet started
Tessl Logo

rdkit

Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.

63

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/rdkit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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.

Well-structured overview that uses progressive disclosure effectively, offloading detail to real bundled references and scripts. Its weakness is that the body itself lacks executable worked examples and an explicit sequenced workflow with validation checkpoints.

Suggestions

Add one short copy-paste worked example in the body (e.g., parse SMILES, compute MW/LogP, run a SMARTS filter) so the skill is actionable without opening a reference.

Include an explicit numbered workflow with a validation checkpoint (e.g., parse -> validate not None -> AddHs -> compute descriptors) to support batch/destructive operations safely.

Trim the duplicated version narrative between the frontmatter compatibility field and the Overview baseline note to tighten token use.

DimensionReasoningScore

Conciseness

Mostly efficient: the capability table compactly summarizes 12 areas and points to references, but the Overview duplicates frontmatter content and the version/baseline notes plus the package-naming caveat add mild padding that could be trimmed.

4 / 5

Actionability

Concrete install commands and named APIs (AddHs, DetectChemistryProblems, rdFingerprintGenerator) appear, but the body delegates nearly all executable workflow code to referenced files and scripts, leaving the body itself without complete worked examples.

3 / 5

Workflow Clarity

Sections are organized (Install, Capabilities, Pitfalls) but there is no sequenced multi-step workflow with explicit validation checkpoints in the body; the Common Pitfalls list gives implicit checks rather than a validate-fix-retry loop, and batch operations are covered only in referenced files.

3 / 5

Progressive Disclosure

Clear overview with well-signaled, one-level-deep references (core_capabilities.md, workflows_and_best_practices.md) and a Resources section listing all real bundled reference and script files with descriptive blurbs; all referenced paths verified to exist.

5 / 5

Total

15

/

20

Passed

Description

83%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.

A strong, specific description that names concrete capabilities and distinguishes rdkit from the datamol wrapper. It would reach the top anchor with more explicit, user-facing 'Use when...' trigger phrasing.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases (e.g., 'Use when calculating molecular descriptors, running substructure/SMARTS searches, or generating 2D/3D coordinates') to lift completeness.

Include a couple of lay synonyms alongside the technical terms (e.g., 'molecular similarity', 'Tanimoto') to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions' plus 'custom sanitization, specialized algorithms' — comprehensive coverage matching the 5-anchor example.

5 / 5

Completeness

Clearly states what (toolkit + capability list) and gives explicit trigger guidance ('Use rdkit for advanced control, custom sanitization, specialized algorithms'), but the 'when' is framed comparatively against datamol rather than as concrete 'Use when...' trigger phrases.

4 / 5

Trigger Term Quality

Strong domain keywords (SMILES, SDF, LogP, TPSA, fingerprints, substructure search, sanitization) that target users naturally say, but coverage leans technical and omits some common variations/synonyms a general user might phrase.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers and explicit differentiation from the simpler datamol wrapper, keeping conflict risk minimal.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
K-Dense-AI/scientific-agent-skills
Reviewed

Table of Contents

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.