CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mcap-format

MCAP file format specification knowledge: binary structure, record types, indexing strategies, compression options, and best practices for creating MCAP files that optimize Lichtblick reading performance.

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/mcap-format/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 body is a dense, well-organized, and actionable MCAP reference that respects Claude's competence, but it is monolithic (no progressive disclosure to separate files) and presents reference material rather than a sequenced workflow with validation checkpoints.

Suggestions

Move the field-level Record Types reference and the Lichtblick Code Mapping table into separate reference files (e.g., references/record-types.md, references/code-mapping.md) and link to them from SKILL.md to enable progressive disclosure.

Add an explicit create/validate workflow (e.g., write chunks -> emit Summary with ChunkIndex records -> verify seeking works) with a validation checkpoint to raise workflow_clarity.

Trim the per-field record-type listings to the subset needed for optimizing Lichtblick reading, leaving exhaustive field documentation to the external spec link.

DimensionReasoningScore

Conciseness

The body is information-dense — bullet points, tables, and a structure diagram with minimal prose padding and almost no explanation of concepts Claude already knows — matching 'efficient; minor instances of over-explanation that could be trimmed'; the full field-level record-type listing keeps it just below the lean 5.

4 / 5

Actionability

Concrete, specific guidance throughout — numeric targets (~4MB chunks, <100KB/>50MB bounds), per-use-case compression picks (zstd for remote, lz4 for local/real-time), and exact Lichtblick class/file paths — giving 'mostly executable guidance with minor gaps'; no copy-paste code, but the scoring note allows that for instruction-only skills.

4 / 5

Workflow Clarity

Content is well-organized and the indexed-reading flow plus numbered best practices give a loose sequence, but there is no explicit multi-step procedural workflow with validation checkpoints or a validate->fix->retry feedback loop, matching 'steps listed but checkpoints missing or implicit'.

3 / 5

Progressive Disclosure

Within-file structure is clean (clear headers, tables, logical sections), but the skill is a monolithic single file with no bundle references, and the detailed record-type reference and Lichtblick code-mapping table are inline content that could be split into separate reference files, matching 'some structure but content that should be separate is inline'.

3 / 5

Total

14

/

20

Passed

Description

57%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 specific and highly distinct, but it is framed as a knowledge catalog rather than an action list and lacks an explicit 'Use when...' trigger clause, capping completeness at 3.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when creating, inspecting, or optimizing MCAP files for Lichtblick playback, or when the user mentions MCAP, .mcap files, or Lichtblick recordings').

Reframe the topic catalog as concrete actions (e.g., 'Inspect MCAP binary structure, configure chunk indexing and compression, and write MCAP files tuned for Lichtblick reading performance') to lift specificity.

Include the natural file extension '.mcap' as a trigger term for broader keyword coverage.

DimensionReasoningScore

Specificity

Names the MCAP domain plus several concrete sub-topics (binary structure, record types, indexing strategies, compression options) and one action ('creating MCAP files that optimize Lichtblick reading performance'), but the framing is a knowledge catalog rather than a comprehensive list of actions, so it sits at the anchor for 'names domain and 1-2 concrete actions, not comprehensive' rather than the more action-rich 4.

3 / 5

Completeness

The 'what' is clear (MCAP format knowledge and best practices for optimized file creation), but there is no 'Use when...' clause or equivalent explicit trigger guidance, so per the cap rule completeness cannot exceed 3.

3 / 5

Trigger Term Quality

The natural term 'MCAP' / 'MCAP files' is present, but the remaining phrases (binary structure, record types, indexing strategies) are technical internals a user would rarely say as a trigger, and there are no synonyms or extensions, matching 'some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

'MCAP file format' and 'Lichtblick reading performance' name a highly specific niche with a distinct trigger ('MCAP') and minimal overlap with other skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

14

/

20

Passed

Validation

100%

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

lichtblick-suite/lichtblick

Path

.github/skills/mcap-format/SKILL.md

Reviewed

Table of Contents

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.