CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

adaptive-stem-alignment

Incremental audio production with duration mismatch handling, adaptive stem extension, and pre-mix alignment verification

Quality

68%

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-enhanced-b8f537/SKILL.md

The canonical home for this skill is adaptive-stem-alignment in HKUDS/OpenSpace

SKILL.md
Quality
Evals
Security

Quality

Content

70%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 delivers an exceptionally clear, verified workflow with fully executable code at every step — its workflow clarity and actionability are top-tier. Its main costs are token weight from inlined boilerplate DSP code and a monolithic structure that should offload implementations to scripts/ and reference files.

Suggestions

Move the align_stem_duration implementation and stem/drum generation code into scripts/ files, keeping only the strategy-selection table, usage examples, and verification checklist in SKILL.md.

Cut the placeholder sine-wave stem examples and generic filter code — Claude can write trivial DSP; keep only the strategy logic and verification patterns that are genuinely skill-specific.

Fix the garbled library reference 'librubberband, elasticsearch' (likely 'librosa, rubberband') to keep the time-stretch guidance actionable.

DimensionReasoningScore

Conciseness

Hundreds of lines of generic DSP code Claude could write unaided (sine-wave stem examples, kick/snare synthesis, Butterworth filtering, fade-curve math) pad the file, making it noticeably verbose even though the prose itself is spare.

2 / 5

Actionability

Every step ships complete, copy-paste-ready Python covering the common cases — all four alignment strategies (zero-pad, loop, crossfade, truncate-with-fade) are fully implemented, with per-step verification helpers included.

5 / 5

Workflow Clarity

Eight strictly ordered steps each end in explicit verification with fail-fast RuntimeError feedback loops, and the file closes with a troubleshooting section and a final verification checklist — a textbook match for the top anchor.

5 / 5

Progressive Disclosure

Section headers and numbered steps make the file navigable, but ~600 lines of implementation are inlined in SKILL.md with no references or scripts/ files; the strategy implementations clearly belong in separate bundle files.

3 / 5

Total

15

/

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 communicates a clear, distinctive niche in audio production, but it reads as a feature list rather than an action-oriented statement and entirely lacks 'when to use' trigger guidance. Adding an explicit 'Use when...' clause with natural user phrases would address its main weaknesses.

Suggestions

Add an explicit trigger clause, e.g. 'Use when generating multi-stem audio tracks whose durations don't match, or when stems need extension/alignment before mixing.'

Lead with concrete third-person verbs and objects, e.g. 'Generates, aligns, and mixes audio stems...' instead of nominal phrases like 'adaptive stem extension'.

Include natural synonyms users would say — 'mixing', 'music production', 'multitrack', 'stems of different lengths', 'WAV' — to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the audio domain and three capability areas ('duration mismatch handling, adaptive stem extension, and pre-mix alignment verification'), but these are nominal phrases rather than concrete actions, and coverage of the actual workflow (stem generation, effects, mixing, export) is partial.

3 / 5

Completeness

The 'what' is clear (incremental audio production with duration handling, stem extension, alignment verification), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3.

3 / 5

Trigger Term Quality

'audio production', 'stem', and 'duration mismatch' are relevant keywords, but common variations a user would naturally say — 'mixing', 'music production', 'multitrack', 'WAV' — and any file extensions are missing.

3 / 5

Distinctiveness Conflict Risk

Niche phrases like 'adaptive stem extension' and 'pre-mix alignment verification' carve a distinct niche with minimal conflict risk; only the broad 'audio production' lead-in creates minor overlap with a generic audio skill.

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 (739 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

HKUDS/OpenSpace

Path

openspace/benchmarks/gdpval/skills/audio-track-production-enhanced-enhanced-b8f537/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.