diagnostic-stem-delivery

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

Quality

55%

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

58%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 skill excels at workflow clarity with a strict, fully-verified pipeline and a mandatory deliverable check, and its code is largely executable. Its weaknesses are conciseness (heavy inline verbosity and over-explained concepts) and progressive disclosure (no reference files, everything inlined), which together bloat the token footprint.

Suggestions

Move the long diagnostic-analysis, stem-generation, and deliverable-verification functions into reference files (e.g. references/diagnostics.py, references/export.py) and keep SKILL.md as an overview that calls them, to fix progressive disclosure and cut tokens.

Trim explanatory docstrings and restatements of well-known DSP concepts (autocorrelation pitch detection, FFT band power) — keep only the skill-specific decision logic.

Replace placeholder sine-wave stem generation with a brief note that stem content is project-specific, or move it to an example file, so the inline code reflects real usage.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose — ~600 lines with extensive inline functions and explanatory docstrings/comments restating concepts Claude already knows (autocorrelation pitch detection, FFT bands, click detection), much of which could be trimmed or moved to a reference file.	2 / 5
Actionability	Guidance is mostly executable: copy-paste-ready Python with real imports (soundfile, librosa, python-docx) and concrete file paths, with only minor gaps (e.g. some stem-content generation is placeholder sine waves).	4 / 5
Workflow Clarity	Steps are strictly sequenced (Step 0–7) with per-step verification, fail-fast raises, incremental stem verification, and a MANDATORY deliverable-verification step with a completion checklist — explicit checkpoints and feedback loops throughout.	5 / 5
Progressive Disclosure	No bundle files exist and all diagnostic/mix/export logic is inlined as a monolithic block in SKILL.md rather than split into reference files; section headers give minimal structure but content that belongs in separate files is inlined.	2 / 5
	Total	13 / 20 Passed

Description

51%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 third-person with a distinct audio-production niche, but it omits any "Use when..." trigger guidance, which caps completeness and weakens trigger-term quality. Adding explicit trigger phrases and natural user keywords would lift it to the top band.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when producing audio stems, parsing edit timecodes from DOCX/TXT files, or delivering a verified final mix.'

Include natural user keywords and file extensions users would say — stems, mixing, .wav, BPM, edit spots — to improve trigger-term coverage.

Clarify the output format (e.g. 'export verified 48k/24b WAV') so the deliverable expectation is explicit in the description.

Dimension	Reasoning	Score
Specificity	Names the audio domain and several concrete actions — "diagnostic analysis", "timecode parsing from documents", and "verified export workflow" — with only minor coverage gaps (mixing/editing not explicitly enumerated).	4 / 5
Completeness	It clearly states what the skill does but provides no "Use when..." clause or equivalent trigger guidance, so the "when" is missing; per rubric a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Only generic domain terms ("audio production", "timecode", "export") appear; it lacks the natural phrases and file extensions users would say (e.g., stems, mixing, .wav, stems delivery).	2 / 5
Distinctiveness Conflict Risk	The diagnostic-analysis-plus-timecode-parsing-plus-verified-export framing is a fairly distinct niche within audio skills, with only minor overlap risk against generic audio-production skills.	4 / 5
	Total	13 / 20 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: 3827781

Reviewed: 25 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.