boltz-structure-and-binding

Predict structures and binding for one defined complex with Boltz. Use when folding a protein, RNA, DNA, or ligand complex, docking one ligand, predicting an interface, or scoring binding. Not for screening libraries or design.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, actionable skill body with a well-sequenced, validated workflow and clean one-level-deep references. The main weakness is redundancy: the runtime-specific download/heartbeat guidance is repeated in both the workflow and the 'Always Do This' section.

Suggestions

Consolidate the Codex/Claude Code download-results and heartbeat instructions so they appear once — either in workflow step 6 or in 'Always Do This' — rather than restated across both (lines 41, 81, 83).

Move the runtime-specific foreground-vs-background dispatch matrix into references/api.md or a small references/runtime.md, keeping the workflow step to a single 'launch download in background/non-blocking mode' pointer.

Trim overlapping bullets in 'Always Do This' that restate the idempotency-key==name and absolute-path guidance already implied by the Command Pattern comments.

Dimension	Reasoning	Score
Conciseness	Mostly lean and operational (no explaining of basic concepts), but the Codex/Claude Code download-results and heartbeat guidance is restated across workflow step 6 and the 'Always Do This' bullets (lines 81, 83), which could be consolidated.	2 / 3
Actionability	The Command Pattern block gives fully executable boltz-api invocations with concrete flags and clearly marked placeholders; payload/binding shapes are shown as copy-paste-ready JSON/YAML.	3 / 3
Workflow Clarity	A numbered 1-6 sequence with an explicit validation checkpoint (estimate-cost → show USD → wait for confirmation), error-recovery guidance (auth, SAB 400 quirk, detached-download restart), and terminal-state handling for a long-running batch operation.	3 / 3
Progressive Disclosure	SKILL.md is an overview that points one level deep to references/api.md and references/results.md via clearly signaled links; both referenced files exist, and detailed API/result shapes are appropriately split out of the main body.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 tight, third-person description that concretely enumerates capabilities, gives explicit trigger phrasing, and bounds scope with a 'Not for...' clause. It hits all four dimension anchors at the top level.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Predict structures and binding', 'folding a protein, RNA, DNA, or ligand complex, docking one ligand, predicting an interface, or scoring binding' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Predict structures and binding for one defined complex with Boltz') and when ('Use when folding... docking... predicting an interface... scoring binding'), plus an explicit 'Not for...' exclusion.	3 / 3
Trigger Term Quality	Covers natural phrasings a user would actually say (folding a protein, docking one ligand, predicting an interface, scoring binding) across protein/RNA/DNA/ligand variants.	3 / 3
Distinctiveness Conflict Risk	Clear niche (Boltz structure-and-binding for one defined complex) with distinct triggers and an explicit out-of-scope clause ('Not for screening libraries or design'), minimizing conflicts.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/boltz-api-cli/skills/boltz-structure-and-binding/SKILL.md
Commit: 11c74d6

Reviewed: about 10 hours 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.