structure-prediction

Protein structure prediction from sequence. ESMFold-based, single GPU, no MSA needed. Predicts 3D structures with pLDDT confidence scores for drug discovery targets.

Quality

69%

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/structure-prediction/SKILL.md

Quality

Content

68%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 concrete, existing scripts and well-structured one-level references, but it is held back by mild prose restatement and a missing validation checkpoint in the batch workflow.

Suggestions

Tighten the Overview and 'Key advantages' sections to avoid restating the description, and move the CASP15 GDT-TS comparison detail out of the main limitations list or trim it.

Add an explicit validation checkpoint to the batch/predict workflows (e.g., 'Review summary.csv for mean pLDDT < 50 and run scripts/evaluate.py on low-confidence structures before using them for docking or dynamics') to lift workflow clarity above the batch cap.

Move the bulk of the inline pLDDT interpretation table into references/confidence_metrics.md, keeping only a one-line pointer inline, to push progressive disclosure toward 5.

Dimension	Reasoning	Score
Conciseness	The bulk is lean executable commands and output specs, but the Overview paragraph and 'Key advantages' restate the description, and Limitations #3 includes excessive CASP15 GDT-TS detail that could be trimmed.	3 / 5
Actionability	Fully executable, copy-paste-ready commands across all four workflows with real script paths and concrete flags (--device cpu/auto/cuda, --output-dir, --predicted, --reference), plus a pip install line and named output columns.	5 / 5
Workflow Clarity	The four workflows are clearly sequenced, but batch prediction is a batch operation with no explicit validation checkpoint (e.g., review summary.csv for low pLDDT or run evaluate.py before downstream use), which caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references to real files ('See: scripts/predict.py', 'see: references/confidence_metrics.md'); minor gap is the inline 'Output Interpretation' table overlapping the dedicated reference file.	4 / 5
	Total	15 / 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 technically well-scoped with strong distinctiveness, but it omits an explicit 'when to use' trigger clause, which caps its completeness. Trigger-term coverage is good but lacks common synonyms.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases (e.g., 'Use when predicting or folding a protein structure from a sequence, screening structures in batch, or evaluating pLDDT confidence') to lift completeness above 3.

Include natural synonyms and file extensions users actually say ('fold protein', 'protein folding', 'PDB', '.pdb') to broaden trigger-term coverage toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions/constraints ('Predicts 3D structures with pLDDT confidence scores', 'ESMFold-based, single GPU, no MSA needed'), with only minor coverage gaps relative to the full capability set.	4 / 5
Completeness	Has a clear 'what' but no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Good keyword coverage ('protein structure prediction', '3D structures', 'pLDDT', 'ESMFold', 'sequence') but missing natural synonyms users say such as 'fold protein', 'protein folding', and 'PDB'.	4 / 5
Distinctiveness Conflict Risk	The 'ESMFold-based, single sequence, no MSA, single GPU' framing carves a clear niche distinct from MSA-based AlphaFold and generative esm skills, with 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/structure-prediction/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.