rerun-blueprint

Design a Rerun blueprint from the data, then iterate on it from headless screenshots. Read this when laying out a recording or dataset in the viewer, designing a default blueprint, or deciding which views show which entities. Covers archetype-to-view mapping, layout reasoning, the rrb construction API, the contents grammar, and the screenshot loop.

Quality

94%

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

Quality

Content

96%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.

An excellent, token-efficient skill body with executable code, a clear multi-step workflow, and built-in validation via the screenshot loop. The only minor gap is that progressive disclosure is purely single-file with no separate reference materials to offload detail into.

Suggestions

Consider moving the extended coordinate-frame troubleshooting (named frames, SpatialInformation targeting) into a short references file linked from section 4, leaving the core decision rule inline.

The archetype-to-view mapping table could live in a reference file if it grows, keeping SKILL.md focused on the design-and-iterate workflow.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout ('this skill covers what you can't guess'); it assumes Claude's competence, never explains what Rerun/archetypes are, and every section adds non-obvious rrb-specific knowledge that earns its tokens.	5 / 5
Actionability	Fully executable copy-paste-ready code for reading data, constructing a blueprint, and the screenshot loop, plus a concrete archetype-to-view mapping table covering the common cases.	5 / 5
Workflow Clarity	Clear numbered sequence (Read data → Map → Group → Construct → Iterate) with an explicit screenshot feedback loop ('Render, look, revise') and a Gotchas section providing error-recovery guidance for blank views and store-identity mismatches.	5 / 5
Progressive Disclosure	Well-organized single file with clearly signaled one-level 'See also' links to related skills, but all content lives inline with no file-level progressive disclosure, so it sits just below the split-across-files anchor at 5.	4 / 5
	Total	19 / 20 Passed

Description

92%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 strong, specific description that clearly states both the capability and explicit trigger conditions for a well-scoped niche. It could add a few more natural synonyms or file/extension terms to push trigger quality to the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Design a Rerun blueprint from the data, then iterate on it from headless screenshots') plus comprehensive coverage areas (archetype-to-view mapping, rrb construction API, contents grammar, screenshot loop), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what ('Design a Rerun blueprint... iterate... from headless screenshots', 'Covers...') and when ('Read this when laying out a recording or dataset in the viewer, designing a default blueprint, or deciding which views show which entities') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases ('laying out a recording or dataset in the viewer', 'designing a default blueprint', 'deciding which views show which entities') but lacks synonym/file-extension variants, so it sits just below the comprehensive-synonyms anchor at 5.	4 / 5
Distinctiveness Conflict Risk	Niche-specific terms ('Rerun blueprint', 'rrb construction API', 'headless screenshots', 'archetype-to-view mapping') define a clear niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	19 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: rerun-io/rerun
Path: skills/rerun-blueprint/SKILL.md
Commit: f30766b

Reviewed: ~7 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.