rerun-mcap

Ingest MCAP files into Rerun chunk streams with rerun.chunk.McapReader. Read when converting an MCAP recording, selecting topics or decoders, decoding custom protobuf messages, or when an MCAP-derived stream comes out empty. Builds on rerun-chunk-processing (stream mechanics) and rerun-data-model (what the topics should become).

Quality

85%

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

82%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 well-crafted, token-efficient reference skill with concrete executable guidance and strong diagnostic gotchas. Its main limitation is that most detail lives inline in SKILL.md rather than being progressively disclosed into bundled reference files.

Suggestions

Move the schema→archetype mapping table and/or the six gotchas into a bundled reference file (e.g. references/decoders.md and references/gotchas.md), keeping only a concise summary and clearly signaled links in SKILL.md, to push progressive_disclosure toward a 5.

Replace the 'mcap_path' placeholder in the API snippet with a concrete example path or a one-line note on how to obtain it, making the lead snippet fully copy-paste ready.

Promote the empty-stream and missing-topic diagnostics from gotchas into a short numbered 'Diagnosing an empty stream' workflow with explicit validate→fix→retry checkpoints to lift workflow_clarity to a 5.

Dimension	Reasoning	Score
Conciseness	Lean and high-signal throughout: no beginner-concept padding (it never explains what MCAP or Rerun are), and every prose passage conveys non-obvious domain behavior such as the verified foxglove-on-protobuf decoder interaction. Not a 4 because there is no trimmable over-explanation.	5 / 5
Actionability	Provides executable snippets ('McapReader(path).stream()', '.filter(content="/sensors/**")', 'Selector(".joint_positions")') and concrete verification commands, but uses placeholders like 'mcap_path' and the fix-lens section is cautionary rather than copy-paste ready, leaving minor gaps.	4 / 5
Workflow Clarity	Diagnostic flow is clear with checkpoints ('Confirm on your file: McapReader(path).stream()... read McapSchema:name and a few Chunk.format()', 'retry with decoders=None'), and ingestion is read-only so the destructive-cap does not apply. Not a 5 because the workflow is embedded in prose/gotchas rather than an explicit validate-fix-retry sequence.	4 / 5
Progressive Disclosure	Well-organized into clear sections with one-level-deep, clearly signaled references to sibling skills (rerun-chunk-processing, rerun-urdf, rerun-data-model) and an external example URL, with no nested references. Not a 5 because substantial detail (the schema→archetype table and six gotchas) is inlined rather than split into reference files.	4 / 5
	Total	17 / 20 Passed

Description

87%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 capability and trigger conditions with concrete, natural-language terms. It carves out a well-distinguished niche and correctly scopes itself against sibling skills.

Dimension	Reasoning	Score
Specificity	Names the core action and concrete API ('Ingest MCAP files into Rerun chunk streams with rerun.chunk.McapReader') plus several specific sub-actions (selecting topics/decoders, decoding custom protobuf), but the remaining clauses read more as trigger scenarios than distinct actions, keeping it just below comprehensive.	4 / 5
Completeness	Explicitly answers both 'what' ('Ingest MCAP files into Rerun chunk streams') and 'when' ('Read when converting an MCAP recording, selecting topics or decoders, decoding custom protobuf messages, or when an MCAP-derived stream comes out empty') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases a user would say ('converting an MCAP recording', 'selecting topics or decoders', 'decoding custom protobuf messages', 'MCAP-derived stream comes out empty') are present with some synonym variation, though a few common variants like the '.mcap' extension are absent.	4 / 5
Distinctiveness Conflict Risk	A clear MCAP-ingestion niche with distinct triggers, and it explicitly delegates stream mechanics and modeling to sibling skills ('Builds on rerun-chunk-processing ... and rerun-data-model'), minimizing overlap risk.	5 / 5
	Total	18 / 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-mcap/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.