rerun-urdf

Drive the Rerun URDF API (rerun.urdf.UrdfTree) to ingest a URDF as a Transform3D layer on a robot recording. Read when logging a robot model, running forward kinematics from joint states, composing a fixed chain for sensor extrinsics, or when the transform tree will not connect from the data alone. Builds on rerun-chunk-processing (stream/lens mechanics) and rerun-data-model (entity paths, timeline, base-vs-layer).

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%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 high-quality, actionable skill body with executable code, strong workflow sequencing, and real validation feedback loops. The two weaker spots are minor over-explanation that could be trimmed (conciseness) and inlined reference-grade content that could be extracted into bundle files (progressive disclosure).

Suggestions

Trim explanatory bridge prose around code blocks (e.g. 'You will almost always run this inside a stream...') to lift conciseness toward the lean anchor.

Extract the robot-source lookup table (SO-100 through Unitree) into a references/ file and link to it, keeping SKILL.md as a leaner overview.

Consider moving the full Minimal-shape pipeline into a references/ example file, leaving a trimmed skeleton inline with a pointer.

Dimension	Reasoning	Score
Conciseness	Dense and assumes Claude's competence throughout (no basic-concept padding), but at ~340 lines there is explanatory prose ('You will almost always run this inside a stream...', 'The only URDF-specific part is...') that could be trimmed, matching the efficient-with-minor-overexplanation anchor.	4 / 5
Actionability	Provides fully executable, copy-paste-ready code covering the common cases (UrdfTree.from_file_path, urdf.stream, compute_joint_transform_batches, the complete Minimal-shape pipeline, the edge Chunk.from_columns snippet) plus a runnable script invocation; the few placeholders (read_names/read_values) are explicitly justified as the only data-specific pieces.	5 / 5
Workflow Clarity	Clear end-to-end sequence with explicit validation checkpoints and feedback loops: a 6-step transform-forest resolution checklist ('stop and say so', 'fail loudly'), a graph check before writing the RRD, joint-mapping/limits verification with candidate-correction feedback, and a 9-item gotchas error-recovery list.	5 / 5
Progressive Disclosure	Well-organized sections, a clear References list, and a real, well-signaled bundle script (scripts/check_joint_mapping.py, verified present) split out at one level deep; however the body inlines reference-grade material (the robot-source lookup table, the full pipeline code) rather than splitting it into references/, leaving minor organization gaps.	4 / 5
	Total	18 / 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 the trigger conditions, with a distinct niche and low conflict risk. The only gap is slightly thinner keyword variation (no synonyms or .urdf extension), which keeps trigger term quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names the concrete API surface (rerun.urdf.UrdfTree, Transform3D layer) and lists multiple specific actions — ingest a URDF, log a robot model, run forward kinematics from joint states, compose a fixed chain for sensor extrinsics — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers 'what' ('Drive the Rerun URDF API ... to ingest a URDF as a Transform3D layer') and 'when' via the concrete 'Read when logging a robot model, running forward kinematics ..., or when the transform tree will not connect from the data alone' trigger clause.	5 / 5
Trigger Term Quality	Good, natural keyword coverage for the audience (URDF, forward kinematics, joint states, robot model, transform tree, sensor extrinsics), but lacks synonyms and file-extension variants (.urdf), so it falls short of the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Rerun URDF ingestion) with distinct triggers and explicit dependencies on rerun-chunk-processing and rerun-data-model, making conflict with unrelated skills minimal.	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-urdf/SKILL.md
Commit: 3efde05

Reviewed: 2 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.