CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

trackdub-media-cleanup

Diagnose and verify media cleanup in Trackdub projects.

Quality

70%

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 ./.claude/skills/trackdub-media-cleanup/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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 procedure body is a strong agent workflow: explicitly sequenced steps with per-step completion checkpoints, concrete CLI commands, honest boundaries around unavailable operations, and a rigorous verification section. Its main weaknesses are the three relative links that resolve to no bundle files and a few measurement steps stated as goals without commands.

Suggestions

Ship the referenced files in the bundle (templates/cleanup-report.md, ATTRIBUTION.md, LICENSE) or remove the links — currently all three resolve to nothing.

Provide concrete commands or tool invocations for the measurements named in section 3 (peaks/clipping, silence detection, left/right balance), paralleling the given ebur128 example.

Consolidate the consent/authorization rules (Prerequisites item 6, section 1, and Pitfalls) into one place to trim repeated caveats.

DimensionReasoningScore

Conciseness

The body is dense and project-specific with inline executable commands and no padding explaining known concepts. Minor trimming is possible: consent rules recur in Prerequisites item 6, section 1, and Pitfalls, and the 'check actual artifacts, not claimed success' point is repeated several times, keeping it below the lean level-5 anchor.

4 / 5

Actionability

Quick reference provides eight copy-paste `dotnet run` commands and section 3 adds concrete ffprobe/ffmpeg invocations and real file paths, which is mostly executable guidance. It stays below level 5 because measurement steps (peaks/clipping, silence, left/right balance) have no commands, 'Inspect SpeechAudioEnhancementStageHandler' gives no how, and the report template link is not backed by a file.

4 / 5

Workflow Clarity

Six numbered steps in dependency order, each ending with a bolded 'Completion:' checkpoint, a dedicated preflight section, and a final verification pass (re-measure loudness, recompute source hash, check prior artifacts) with prescribed error paths (record fallback, deliver diagnosis and the execution blocker). This matches the anchor for clear sequencing with explicit validation steps, error recovery, and checklists.

5 / 5

Progressive Disclosure

Section structure is well organized (When to use, Prerequisites, Quick reference, Procedure, Pitfalls), but the body's three relative links — ATTRIBUTION.md, LICENSE, and templates/cleanup-report.md — point to files that are not present in the bundle, so navigation fails exactly where content was split out. Broken references are a real organization gap, below the 'references mostly clear, minor gaps' level-4 anchor.

3 / 5

Total

16

/

20

Passed

Description

53%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 short, accurate, and clearly niche-scoped, but it is minimal: it answers "what" with only two verbs and gives no trigger guidance at all. Adding a "Use when..." clause with the natural problem vocabulary (noise, echo, speech cleanup before dubbing) would substantially raise completeness and trigger-term quality.

Suggestions

Add an explicit 'when' clause, e.g. 'Use when source speech is noisy, echoey, quiet, clipped, or uneven, or before transcription/diarization/dubbing in a Trackdub project.'

Include natural user vocabulary such as 'noisy audio', 'background noise', 'echo', 'speech enhancement', and 'audio cleanup' so the description matches what users actually say.

Consider naming one or two more concrete operations (e.g. 'measure loudness and verify enhanced artifacts') to strengthen capability specificity.

DimensionReasoningScore

Specificity

The description names its domain ("media cleanup in Trackdub projects") and two concrete actions ("Diagnose and verify"), matching the 1-2-actions anchor. It does not list several specific operations, so it falls short of level 4.

3 / 5

Completeness

The "what" is stated clearly (diagnose and verify media cleanup in Trackdub projects), but there is no "Use when..." clause or equivalent trigger guidance, capping completeness at 3. The neighboring anchors don't fit: level 4 requires an explicit "when", and level 2 requires a vague "what".

3 / 5

Trigger Term Quality

Relevant keywords like "Trackdub", "media cleanup", and "diagnose" are present, but the natural phrases a user would say ("noisy audio", "remove background noise", "echo", "clean up speech") are missing. This matches the anchor for some relevant keywords missing common variations or synonyms.

3 / 5

Distinctiveness Conflict Risk

"in Trackdub projects" establishes a clear niche with minimal conflict outside that ecosystem, but "media cleanup" overlaps with closely related Trackdub skills (transcription, dubbing, visual cleanup) the body itself distinguishes. Mostly distinct with minor overlap risk matches level 4; level 5 would require no such overlap.

4 / 5

Total

13

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 3 missing

Warning

Total

13

/

16

Passed

Repository

MesilimLLC/Trackdub

Path

.claude/skills/trackdub-media-cleanup/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.