CtrlK
BlogDocsLog inGet started
Tessl Logo

molecular-docking

End-to-end molecular docking pipeline. Target preparation, pocket detection, protein-ligand docking (DiffDock/Vina), scoring, interaction analysis, and pose ranking.

63

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/chemistry/molecular-docking/SKILL.md
SKILL.md
Quality
Evals
Security

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 body is highly actionable with executable, multi-workflow command blocks and good file structure, but inline validation checkpoints are missing for batch operations, slightly capping workflow clarity. Conciseness and progressive disclosure are solid with minor room to tighten and add more signaled references.

Suggestions

Insert explicit validation checkpoints between workflow steps (e.g. verify the prepared PDB and confirm poses.sdf is non-empty before scoring, and validate the ranked output) to add the missing feedback loops for batch operations.

Trim the restated pipeline-stage overview that duplicates the frontmatter description to tighten conciseness.

Signal additional reference docs explicitly (e.g. link to a deeper interaction-analysis or DiffDock-configuration reference) to strengthen progressive disclosure beyond the single pocket-detection reference.

DimensionReasoningScore

Conciseness

Mostly efficient — command-based workflows, a compact script-reference table, and terse domain-specific output interpretation with no padding about what docking is; minor repetition of pipeline stages already in the frontmatter keeps it just short of lean.

4 / 5

Actionability

Fully executable copy-paste bash blocks with real flags and file paths across multiple common workflows (single-ligand, virtual screening, rescoring, auto-pocket), plus a script input/output table and specific troubleshooting commands.

5 / 5

Workflow Clarity

Steps are clearly numbered and sequenced, but validation/verification checkpoints are absent inside the workflows despite batch operations (virtual screening) and re-ranking, which caps workflow clarity at 3 per the feedback-loop guidance.

3 / 5

Progressive Disclosure

Well-organized sections with a clearly signaled one-level reference to references/pocket_detection.md (a real file) and detail split into five real scripts; just short of a 5 because only one external reference is explicitly signaled.

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, comprehensive, and clearly distinct, but it omits any explicit 'when to use' trigger guidance, which limits its completeness. Adding a 'Use when...' clause would raise the score.

Suggestions

Append a 'Use when ...' clause listing natural user phrasings (e.g. 'Use when docking a ligand to a protein, predicting binding poses, or running virtual screening').

Include the colloquial trigger terms users actually say ('dock this ligand', 'predict how a molecule binds', 'find the best binders') and relevant file extensions (.pdb, .sdf).

DimensionReasoningScore

Specificity

Lists multiple concrete pipeline actions — target preparation, pocket detection, protein-ligand docking (DiffDock/Vina), scoring, interaction analysis, and pose ranking — giving comprehensive coverage.

5 / 5

Completeness

The 'what' is clearly and comprehensively stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Strong domain keyword coverage with synonyms ('molecular docking', 'protein-ligand docking', DiffDock/Vina), but lacks the natural colloquial phrasings a user would say ('dock this ligand') and any file extensions.

4 / 5

Distinctiveness Conflict Risk

A clearly defined molecular-docking niche with named engines (DiffDock/Vina) gives distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.