boltz-protein-design

Design new protein binders with Boltz. Use when generating protein, peptide, antibody, nanobody, or custom binder candidates for a target. Not for screening existing proteins or small molecules.

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 executable commands, a well-sequenced validated workflow, and clean progressive disclosure into three real reference files. Its only weakness is redundancy: the download/background and spending-gate guidance is repeated in several sections.

Suggestions

Consolidate the download-results / background-mode guidance: it currently appears in step 10, step 11, Always Do This bullets 10-12, and the Command Pattern comments — keep one canonical version and cross-reference it.

State the spending gate once in Always Do This and reference it from step 8 rather than re-explaining the rule in both places.

Trim the repeated Claude-Code-vs-Codex background-mode instructions to a single short table or one canonical block.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no basic-concept padding) but restates the background/download and spending-gate guidance across step 10, step 11, the Always Do This bullets, and the Command Pattern comments, creating noticeable redundancy.	3 / 5
Actionability	It provides copy-paste-ready CLI commands, exact API field names, concrete DSL examples ("5..10", "ACDE8GHI"), and explicit valid ranges, covering the common cases fully executably.	5 / 5
Workflow Clarity	The numbered 11-step workflow has explicit validation checkpoints (target-exploration decision first, estimate-cost spending gate before every start, run-sizing enforcement) for a batch money-spending operation, matching the anchor for clear sequence with explicit validation and feedback loops.	5 / 5
Progressive Disclosure	The body is an overview pointing to three verified one-level-deep references (api.md, results.md, target-exploration.md) with content appropriately split, matching the anchor for a clear overview with well-signaled one-level-deep references.	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 concise yet comprehensive, naming the concrete action and enumerating the binder modalities users would name, with an explicit 'Use when' trigger and a clear negative boundary. It distinguishes itself well from screening and small-molecule skills.

Dimension	Reasoning	Score
Specificity	"Design new protein binders with Boltz" plus "generating protein, peptide, antibody, nanobody, or custom binder candidates for a target" lists multiple concrete actions with comprehensive modality coverage, matching the anchor for multiple specific concrete actions.	5 / 5
Completeness	It explicitly states what ("Design new protein binders with Boltz") and when ("Use when generating ... candidates for a target"), plus a negative boundary ("Not for screening existing proteins or small molecules"), matching the anchor that clearly answers both what and when with concrete triggers.	5 / 5
Trigger Term Quality	"protein, peptide, antibody, nanobody, or custom binder candidates" gives comprehensive coverage of the natural terms and synonyms a user would say, matching the anchor for comprehensive natural-term coverage.	5 / 5
Distinctiveness Conflict Risk	The explicit "Not for screening existing proteins or small molecules" clause disambiguates from related skills, giving a clear de novo binder-design niche with minimal conflict risk.	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-protein-design/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.