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

96%

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

100%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 tight, highly actionable skill body with a clear multi-step workflow, executable code throughout, and explicit feedback/validation checkpoints. Structure and progressive disclosure are appropriate for a self-contained skill.

Dimension	Reasoning	Score
Conciseness	Lean and efficient; assumes Claude's competence with no 'what is Rerun' filler, and every section earns its place. The few explanatory passages (e.g. named coordinate frames) cover non-obvious knowledge rather than basics.	5 / 5
Actionability	Fully executable, copy-paste-ready Python blocks, a concrete archetype-to-view mapping table, explicit origin/name rules, and the include/exclude contents grammar cover the common cases directly.	5 / 5
Workflow Clarity	A clear five-step sequence (read -> map -> group -> construct -> iterate) with an explicit screenshot feedback loop (render, look, revise) and a Gotchas section providing error-recovery checkpoints (blank views, transform-path errors, timeline/settle bumps).	5 / 5
Progressive Disclosure	A single-file skill with no external bundle files; well-organized numbered sections plus a one-level-deep 'See also' pointer to sibling skills satisfies the bar for skills that need no separate reference files.	5 / 5
	Total	20 / 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, third-person description that clearly states what the skill does and when to invoke it, with concrete actions and natural trigger phrasings. The only minor gap is a few missing natural synonyms or file-extension cues in the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Design a Rerun blueprint from the data, then iterate on it from headless screenshots') and enumerates concrete sub-tasks ('archetype-to-view mapping, layout reasoning, the rrb construction API, the contents grammar, and the screenshot loop'), giving comprehensive coverage of the domain.	5 / 5
Completeness	Explicitly answers both 'what' (design and iterate on a blueprint, covering specific sub-topics) and 'when' ('Read this when laying out... designing... deciding...'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrasings a user would say are present ('laying out a recording or dataset in the viewer', 'designing a default blueprint', 'deciding which views show which entities'), with some synonym coverage; missing a few natural variants or file-extension cues, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche ('Rerun blueprint') with distinct, domain-specific triggers and minimal overlap risk 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: 3efde05

Reviewed: 3 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.