CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

aligned-stem-workflow

Incremental audio production with duration alignment handling, per-stem verification, and adaptive extension strategies

Quality

71%

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/SKILL.md

The canonical home for this skill is aligned-stem-workflow in HKUDS/OpenSpace

SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

A strongly actionable, well-sequenced workflow with exemplary per-step verification and error handling — the code is complete and executable throughout. Its weaknesses are length (duplicated overview material and placeholder code) and a monolithic structure that inlines what should be split into scripts/references.

Suggestions

Move the full align_stem_duration and stem-generation implementations into a scripts/ file and keep only usage examples in SKILL.md, adding one-level-deep references.

Merge the 'Key Differences from Standard Workflow' section into the Overview to remove duplication, and replace the placeholder sine-wave branches in generate_stem with a brief note on customizing per stem type.

Trim inline comments restating what the code does (e.g. '# Append zeros', '# Extract loop segment') since Claude can read the code directly.

DimensionReasoningScore

Conciseness

The prose is lean, but at ~680 lines the body carries more than minor bloat: the Overview and 'Key Differences from Standard Workflow' sections duplicate each other, and the placeholder sine-wave generation code in generate_stem is generic filler. This exceeds anchor 4's 'minor instances of over-explanation that could be trimmed'.

3 / 5

Actionability

Every step ships complete, copy-paste-ready executable Python covering timing calculation, verification, generation, alignment, effects, mixing, and archiving, with concrete configuration values (BPM=120, 48000Hz, FLOAT subtype) covering the common cases.

5 / 5

Workflow Clarity

Eight strictly ordered steps each with explicit validation ('Verify immediately', fail-fast RuntimeError raises on failure), plus a troubleshooting section with problem/solution pairs — exactly the explicit-checkpoint, error-recovery pattern the top anchor describes. Validation is abundant, so the batch-operation cap does not apply.

5 / 5

Progressive Disclosure

Section headers, a strategy-selection table, and a troubleshooting section give it real structure, but no bundle files exist and all implementation is inlined: the ~160-line align_stem_duration function and full generation/effect code clearly belong in separate scripts/references files. This matches 'some structure... content that should be separate is inline' rather than the minimal-structure anchor 2.

3 / 5

Total

16

/

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 is domain-specific and avoids fluff, but it reads as a feature list rather than an action statement: it never says what the skill produces or when to invoke it. Adding an explicit trigger clause and concrete deliverables would move it up substantially.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when generating multi-stem audio tracks that must match a reference track's duration.'

State concrete actions and deliverables (generate individual stems, align durations, mix, export and archive a master track) instead of feature nouns like 'adaptive extension strategies'.

Include natural trigger terms and synonyms users would actually say: stems, multitrack, duration mismatch, mixing, WAV.

DimensionReasoningScore

Specificity

The description names the domain and 2-3 specific feature phrases ("per-stem verification", "duration alignment handling", "adaptive extension strategies"), but these are capability nouns around an unspecified production process — core actions like stem generation, mixing, and master export are never stated. Coverage gaps are larger than the 'minor gaps' required for a 4.

3 / 5

Completeness

It conveys a 'what' (incremental audio production with verification and alignment) but contains no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

It includes some relevant keywords a user might say ("audio production", "stem", "duration alignment") but misses common variations and synonyms such as "mixing", "multitrack", "duration mismatch", or audio file formats, matching the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The niche focus on stem duration alignment and per-stem verification is mostly distinct from other skills with only minor overlap risk against generic audio-generation skills; it lacks the explicit distinct trigger phrases needed for a 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 (684 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/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.