CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

audio-track-production

End-to-end audio production workflow with stems, effects, archiving, and verification

Quality

67%

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 ./openspace/benchmarks/gdpval/skills/audio-track-production/SKILL.md

The canonical home for this skill is audio-track-production in HKUDS/OpenSpace

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 strongly actionable, well-sequenced workflow with genuine validation at each stage — clearly above the rubric's bad examples. Its weaknesses are duplication (the complete-workflow section repeats the seven steps), placeholder/undefined-variable details in the code, no error-recovery guidance, and a monolithic single-file structure with no progressive disclosure for a 340-line skill.

Suggestions

Remove or drastically trim the 'Complete Workflow Example' section — it duplicates Steps 1–7 and adds ~60 lines of token cost without new information.

Split the full workflow script and the detailed verification specifications into references/ files (e.g. references/workflow.py, references/verification.md), keeping SKILL.md as a lean overview with clearly signaled links.

Add an error-recovery loop after verification: what to inspect and fix when `verify_outputs` reports a sample-rate, subtype, or duration mismatch, instead of a bare assert.

Fix the undefined `stem_audio` variable in Step 5 and note where placeholder sine-tone content should be replaced with real synthesis/processing.

DimensionReasoningScore

Conciseness

The step-by-step code is purposeful and free of concept explanations Claude already knows, but the ~60-line 'Complete Workflow Example' largely re-runs Steps 1–7 in condensed form, and the opening paragraph ('This skill provides a reusable pattern for executing audio production tasks that require...') is padding. This is noticeable duplication, but since the per-step sections themselves are efficient, it fits the 3 anchor (mostly efficient, some content that could be tightened) better than 2.

3 / 5

Actionability

Concrete, mostly executable Python for every step (soundfile verification, timing math, stem generation with explicit subtype, scipy.signal filters, zip archiving, spec verification). Minor gaps keep it from 5: Step 5 references an undefined `stem_audio` variable, code blocks depend on imports/definitions from earlier sections (e.g. the complete example calls `apply_lowpass_filter` and `verify_outputs` without defining them), and the example content is placeholder sine tones requiring substitution.

4 / 5

Workflow Clarity

Seven steps are clearly sequenced with explicit validation checkpoints: per-export asserts on sample rate and subtype, archive content verification, and a final `verify_outputs` pass with per-file error details and a hard assert. It falls short of the 5 anchor because there is no error-recovery feedback loop — verification failures assert/abort rather than instructing how to diagnose and fix — and no checklist despite this being a batch operation over 4 stems.

4 / 5

Progressive Disclosure

Sections are well-organized with one header per step, but at ~340 lines everything lives in SKILL.md with no bundle files or one-level-deep references: the full standalone workflow script and the detailed verification specs are content that would fit better in references/ files. This matches the 3 anchor (some structure, content that should be separate is inline); the under-50-line exception for scoring 5 on sections alone clearly does not apply.

3 / 5

Total

14

/

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 identifies a specific niche and enumerates concrete deliverable components, but it is purely a 'what' statement: no verbs describing actions, no 'when to use' guidance, and no synonyms like mixing/mastering. It is serviceable but below the quality of the rubric's good examples, which all pair a what-clause with an explicit Use-when clause.

Suggestions

Add an explicit trigger clause, e.g. 'Use when generating a master track and stems from audio, applying effects like reverb or filtering, or when the user asks for mixing/mastering deliverables.'

Convert the component list into concrete actions: 'Generate stems and a master track, apply effects (filtering, reverb), archive deliverables as zip, and verify output specs.'

Include natural synonyms and formats users would say — mixing, mastering, track, WAV — to improve trigger term coverage.

DimensionReasoningScore

Specificity

"End-to-end audio production workflow with stems, effects, archiving, and verification" names the domain and enumerates several concrete components (stems, effects, archiving, verification), but they are noun phrases with no explicit actions (no verbs like generate, apply, export), and coverage is incomplete relative to the body's actual steps. It sits between the 3 anchor (domain + 1-2 concrete actions, not comprehensive) and the 4 anchor (several specific actions); the absence of explicit verbs keeps it at 3.

3 / 5

Completeness

The description clearly answers 'what' (audio production workflow with stems, effects, archiving, verification) but contains no 'Use when...' clause or equivalent trigger guidance. Per the rubric guideline, a missing 'Use when' clause caps completeness at 3; it is not lower because the 'what' is concrete and multi-part.

3 / 5

Trigger Term Quality

"audio production" and "stems" are terms users would naturally say, but common variations and synonyms are missing: "mixing", "mastering", "track", and file formats like "WAV". This matches the 3 anchor (some relevant keywords but missing common variations) rather than 4, which requires good keyword coverage with only a few natural terms missing.

3 / 5

Distinctiveness Conflict Risk

"audio production workflow with stems" carves out a fairly distinct niche that would rarely trigger for unrelated skills, with only minor overlap risk against closely related audio-manipulation skills. It falls short of the 5 anchor, whose example includes explicit distinct trigger phrases, because this description offers no trigger phrasing at all.

4 / 5

Total

13

/

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

HKUDS/OpenSpace

Path

openspace/benchmarks/gdpval/skills/audio-track-production/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.