diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/audio-track-production-enhanced-enhanced-enhanced/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and the multi-step workflow is exceptionally clear with strong verification checkpoints, but it is a long monolithic document with redundancy between overview and step bodies and no use of bundle files for progressive disclosure. Splitting reusable code into reference files and trimming repeated material would improve both conciseness and disclosure.

Suggestions

Move the large per-step code blocks (e.g., the diagnostic analysis and deliverable verification functions) into scripts/ or references/ files, keeping SKILL.md as a concise overview that links to them one level deep.

Collapse the redundant Overview and Key Principles lists into a single sequenced step list to remove repetition and reduce token cost.

Add an explicit re-verification of the mix (Step 6) before the final export, and trim inline comments that explain concepts Claude already knows (e.g., DC removal, RMS).

Dimension	Reasoning	Score
Conciseness	The ~630-line body is mostly efficient but padded: the Overview, Key Principles, and per-step headers repeat the same steps, and inline comments/docstrings explain basics Claude already knows (e.g., '# DC removal', RMS semantics); collapsing the redundant lists and trimming comments would tighten it.	2 / 3
Actionability	Every step ships fully executable, copy-paste-ready code using python-docx, soundfile, numpy, and librosa with concrete commands and parameters, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Steps 0-7 are strictly sequenced with per-step verification, fail-fast errors, re-validation feedback loops, and a final completion checklist, matching the explicit-validation anchor; the only minor gap is that the mix (Step 6) lacks an explicit re-verify before export, but deliverable verification in Step 7 covers end-to-end integrity.	3 / 3
Progressive Disclosure	The skill is a monolithic single file (~630 lines) with no references/, scripts/, or assets/ bundle files; large per-step code blocks that could live in separate reference files are all inline, even though sections are clearly labeled.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 occupies a distinct niche, but it omits any explicit 'Use when...' trigger guidance and only partially covers the natural keywords a user would say. Adding a trigger clause and common terms like 'mixing' or 'stems' would raise completeness and trigger quality.

Suggestions

Append a 'Use when...' clause naming the situations that should trigger this skill (e.g., producing audio stems, mixing tracks, editing audio at specific timecodes).

Add natural user-facing terms such as 'mixing', 'stems', 'music production', and 'audio editing' alongside the existing technical vocabulary.

Tighten 'verified export workflow' to a more concrete deliverable phrase like 'export and verify a final mixed WAV deliverable' to sharpen specificity further.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions ("diagnostic analysis", "timecode parsing from documents", "verified export workflow") rather than vague language, matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	It clearly states what the skill does but contains no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It includes relevant terms ("audio production", "timecode", "documents", "export") but misses common natural variations a user might say such as "mixing", "stems", or "music production", so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	Audio stem production with diagnostic analysis and timecode parsing is a clear niche unlikely to conflict with other skills, matching the distinct-triggers anchor.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (634 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/audio-track-production-enhanced-enhanced-enhanced/SKILL.md
Commit: c5a9c4b

Reviewed: 2 days 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.