CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

incremental-audio-workflow

Step-by-step audio production with per-stem verification, timing alignment, and incremental quality gates

Quality

65%

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-enhanced/SKILL.md

The canonical home for this skill is incremental-audio-workflow in HKUDS/OpenSpace

SKILL.md
Quality
Evals
Security

Quality

Content

62%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's core strength is its exceptionally clear incremental workflow with validation after every step and strong fail-fast feedback loops. Its main weaknesses are severe duplication — the whole workflow appears twice — and the absence of any progressive disclosure, with roughly 300 lines of complete-script and reference material inlined in SKILL.md.

Suggestions

Remove the duplicated 'Complete Workflow Script' section (or the per-step code blocks) — keeping both doubles the token cost of the skill without adding information.

Move the complete workflow script into a scripts/ file and the troubleshooting material into a references/ file, keeping SKILL.md as a concise overview with one-level-deep, clearly signaled references.

Clean up dead code in Step 7 (the deliverables and first two deliverable_files assignments that are immediately overwritten) and make each code block self-contained with its own imports.

DimensionReasoningScore

Conciseness

The body implements the entire workflow twice — Steps 1-7 with full code blocks followed by a ~200-line 'Complete Workflow Script' that re-implements all of it — which is noticeably verbose with a large padded duplicate section, well below the mostly-efficient anchor 3.

2 / 5

Actionability

Code is concrete and near copy-paste ready (soundfile, numpy, scipy.signal.butter, zipfile) with real verification functions, but blocks depend on imports and variables from earlier blocks (sf, os, DURATION, timing) and Step 7 contains dead code (deliverables/deliverable_files computed then overwritten), leaving minor gaps below fully-executable.

4 / 5

Workflow Clarity

Seven strictly ordered steps each with explicit immediate verification, fail-fast RuntimeError/sys.exit(1) checkpoints, an overview checklist, and a Troubleshooting section with recovery guidance — this matches the anchor-5 pattern of clear sequencing with validation and error-recovery feedback loops.

5 / 5

Progressive Disclosure

Section structure and navigation are good, but all content — including the complete standalone script and troubleshooting reference — is inlined in a single ~620-line SKILL.md with no bundle files; content that clearly belongs in separate files (e.g., scripts/workflow.py) is inline, fitting anchor 3 rather than 4.

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 names a clear domain and a few concrete process attributes in third person, but it omits any 'when to use' trigger guidance and misses common natural synonyms like mixing, mastering, or .wav. It is adequately specific but not comprehensive about the workflow's actual capabilities.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases (e.g., 'Use when generating multi-stem music tracks, mixing, or mastering audio in .wav format').

Include natural trigger terms and synonyms users would say — mixing, mastering, music production, stems, .wav — to improve trigger_term_quality.

Mention the concrete deliverables and actions (stem generation, effects processing, master export, archiving) rather than only process attributes like 'quality gates'.

DimensionReasoningScore

Specificity

"Step-by-step audio production" names the domain and "per-stem verification, timing alignment, and incremental quality gates" are concrete process attributes, but the actual capability actions (generate stems, apply effects, mix, export, archive) are absent, which is more than minor coverage gaps.

3 / 5

Completeness

The description clearly answers 'what' but contains no 'Use when...' clause or equivalent trigger guidance; per the rubric guideline, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

"audio production" and "per-stem" are relevant natural keywords, but common variations users would actually say — mixing, mastering, music, song, .wav — are missing, matching 'some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

The stem-verification/timing-gate production niche is mostly distinct from other skills with only minor overlap risk against closely related audio skills; it is more specific than anchor 3 but lacks the explicit distinct triggers of anchor 5.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (648 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

HKUDS/OpenSpace

Path

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