binding-affinity

Hybrid ML + physics binding affinity prediction. Empirical scoring, MM/GBSA rescoring, multi-method consensus, and batch virtual screening for protein-ligand complexes.

Quality

73%

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/binding-affinity/SKILL.md

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.

A highly actionable, well-structured body with copy-paste commands and clear output specs; main weaknesses are the absence of inline validation checkpoints in the batch/pipeline workflows and an unlinked reference file.

Suggestions

Add explicit validation/verification checkpoints inside Workflow 4 (batch) and Workflow 5 (pipeline), e.g. check the output JSON/CSV is non-empty and well-formed before proceeding to the next step.

Link references/scoring_methods.md from the body (e.g. under a 'Scoring methods' section) so the existing reference file is discoverable.

Consider moving the full JSON output-format examples and interpretation tables into the reference file to slim SKILL.md toward an overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes competence (no boilerplate explaining RDKit or docking), with minor trimmable detail in the interpretation and troubleshooting tables; fits the 'efficient, minor over-explanation' anchor.	4 / 5
Actionability	Workflows give complete copy-paste-ready bash commands with all flags, plus full JSON output examples and a script reference table covering the common cases.	5 / 5
Workflow Clarity	Workflows are clearly sequenced with concrete commands, but batch virtual screening (Workflow 4) and the 6-step pipeline lack inline validation checkpoints; the manifest-based tracing is external rather than a per-step feedback loop, so the batch-operation cap applies.	3 / 5
Progressive Disclosure	Good section hierarchy with scripts properly referenced and present in the bundle; minor gap is that references/scoring_methods.md exists but is not linked or signaled from the body.	4 / 5
	Total	16 / 20 Passed

Description

71%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 specific, capability-rich description that names four concrete actions and a clear domain niche, but it omits an explicit 'when to use' trigger clause, which the rubric caps at completeness 3.

Suggestions

Add an explicit trigger clause, e.g. 'Use when ranking docked poses by binding affinity, rescoring with MM/GBSA, or running virtual screening on a compound library.'

Include natural synonyms users say, such as 'predict Kd/pKd' and 'rescore docking poses', to broaden trigger-term coverage.

Sharpen distinctiveness by contrasting with related skills, e.g. 'scores docked poses (does not dock or detect pockets)'.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions — 'Empirical scoring, MM/GBSA rescoring, multi-method consensus, and batch virtual screening' — matching the anchor for multiple specific concrete actions with comprehensive coverage.	5 / 5
Completeness	The 'what' is clear, but there is no 'Use when…' or equivalent explicit trigger guidance, which the rubric caps at 3 even though the capability list is strong.	3 / 5
Trigger Term Quality	Strong natural domain keywords ('binding affinity', 'MM/GBSA', 'virtual screening', 'consensus') but missing common synonyms a user might say (Kd/pKd, docking score), so it sits above anchor 3 but below the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche (binding affinity / MM/GBSA / virtual screening for protein-ligand complexes) with minimal conflict risk, though generic 'scoring' could lightly overlap with molecular-docking skills.	4 / 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/binding-affinity/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.