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%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 content is highly actionable with an explicit, validated workflow and clean progressive disclosure to real reference files. Its main weakness is repetition of the Codex/heartbeat guidance across multiple sections, which inflates token cost without adding information.

Suggestions

Consolidate the Codex foreground/yield_time_ms=1000, no-&/no-nohup, and session_id guidance into a single canonical statement; reference it from step 6 and the Command Pattern comments instead of restating it verbatim in the "Always Do This" bullets.

Merge the heartbeat-automation guidance (currently split across step 6, bullet 7, and bullet 8) into one place, since the same scheduling instructions appear three times.

Consider moving the runtime-specific (Claude Code vs Codex vs app/desktop) background-mode branching into references/api.md or a short runtime matrix to keep the main workflow lean.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence with no concept padding, but the Codex foreground/yield_time_ms=1000/no-&/no-nohup and heartbeat-scheduling guidance is repeated near-verbatim across step 6, the Command Pattern comments, and the "Always Do This" bullets, which could be tightened into one canonical statement.	3 / 5
Actionability	Copy-paste-ready commands (estimate-cost, start with --raw-output --transform id, download-results with --poll-interval-seconds 10) and concrete JSON/YAML payload examples fully cover the common cases, with placeholders explicitly flagged for replacement.	5 / 5
Workflow Clarity	A clear six-step sequence (normalize inputs, add binding, optional features, estimate-cost + explicit user confirmation, start, download) includes validation checkpoints before the cost-incurring submit and feedback loops for the 400 validation quirk and detached-download restart.	5 / 5
Progressive Disclosure	The body is a lean overview with well-signaled, one-level-deep references to the real bundle files references/api.md (entity shapes, binding variants, bonds, constraints) and references/results.md (metrics, validation quirks), keeping detail appropriately split with easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

100%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 third-person, concise, and explicitly answers both what the skill does and when to use it, with concrete trigger phrases and a clear negative boundary. It is a strong, low-conflict description.

Dimension	Reasoning	Score
Specificity	"Predict structures and binding" plus "folding a protein, RNA, DNA, or ligand complex, docking one ligand, predicting an interface, or scoring binding" lists multiple concrete actions with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	"Predict structures and binding for one defined complex with Boltz" states the what, "Use when folding... docking... predicting an interface, or scoring binding" states the when with concrete triggers, and "Not for screening libraries or design" adds an explicit negative boundary.	5 / 5
Trigger Term Quality	Natural user phrases like "folding a protein", "docking one ligand", "predicting an interface", and "scoring binding" give comprehensive coverage of the terms a user would actually say, including synonyms across protein/RNA/DNA/ligand complexes.	5 / 5
Distinctiveness Conflict Risk	The Boltz-specific niche ("one defined complex with Boltz") plus the explicit exclusion ("Not for screening libraries or design") gives a clear niche with minimal conflict risk against neighboring skills.	5 / 5
	Total	20 / 20 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: 1e28582

Reviewed: 6 days 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.