CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

musescore

CLI for music notation — transpose, export PDF/audio/MIDI, extract parts, manage instruments

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

90%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 content is an exemplary lean command reference: fully executable copy-paste commands covering all subcommand groups with zero concept over-explanation. The only weaknesses are implicit multi-step sequencing and absent validation for destructive operations like instrument removal.

DimensionReasoningScore

Conciseness

The body is almost entirely copy-paste commands with brief inline comments and a one-sentence overview; it assumes Claude's competence and explains nothing Claude already knows ("Wraps MuseScore 4's `mscore` backend for music notation tasks" is the only prose). Every token earns its place, matching anchor 5.

5 / 5

Actionability

All commands are fully executable with real flags and arguments (e.g. "transpose by-key ... --target-key \"C major\" --direction closest", "export mp3 ... --bitrate 192") and cover the common cases for every subcommand group. This matches anchor 5: copy-paste ready with specific examples covering common cases; not 4 because there are no meaningful gaps.

5 / 5

Workflow Clarity

The Agent Guidance section provides explicit checkpoints — "Verify exports with `export verify` after rendering" and "Use `media probe` to inspect an unknown score before operating on it" — giving clear validation for the main export and unknown-score flows. Not 5 because multi-step sequences are implicit rather than laid out, and destructive operations (e.g. "instruments remove") and transposition results lack any verification guidance; not 3 because key checkpoints are explicitly present, not merely implicit.

4 / 5

Progressive Disclosure

The skill is a single well-organized file (~95 lines) with clear sections (Overview, Commands grouped by category, Input Formats, Key Names, Agent Guidance) and no bundle files to reference — appropriate for its size. Not 5 because the under-50-line simple-skill exception doesn't apply and the full command catalog could arguably live in a references/ file; not 3 because nothing is buried or misplaced — structure is clean and navigable.

4 / 5

Total

18

/

20

Passed

Description

66%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 concrete capabilities in third person with good domain-specific trigger words, but lacks any "Use when..." trigger guidance, capping completeness at 3. Adding explicit trigger conditions and file extensions (.mscz, sheet music, MuseScore) would raise both completeness and trigger term quality.

Suggestions

Add a 'Use when...' clause, e.g. "Use when working with MuseScore or sheet music files (.mscz, .mxl, .musicxml), or when the user asks to transpose, export, or extract parts from a score" — this directly addresses the missing 'when' that caps completeness at 3.

Include natural trigger terms and synonyms currently missing: "sheet music", "MuseScore", ".mscz", and "MusicXML" — users needing this skill would commonly say these.

Mention the score-analysis capabilities (media probe/stats/diff) to close the coverage gap in the action list.

DimensionReasoningScore

Specificity

Lists several concrete actions — "transpose, export PDF/audio/MIDI, extract parts, manage instruments" — which matches anchor 4. Not 5 because capabilities present in the body (score analysis via media probe/stats/diff, MusicXML export) are omitted, leaving minor gaps in coverage.

4 / 5

Completeness

The "what" is clearly stated (transpose, export, extract parts, manage instruments), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because the "when" is entirely absent rather than merely implicit-but-present.

3 / 5

Trigger Term Quality

Good natural keywords — "music notation", "transpose", "extract parts" — but misses common variations users would say such as "sheet music", "MuseScore", and file extensions like ".mscz". Anchor 4 ("good keyword coverage; a few natural terms missing") is the best fit; not 5 since extensions and synonyms are absent.

4 / 5

Distinctiveness Conflict Risk

"CLI for music notation" carves out a clear niche with notation-specific triggers (transpose, parts, instruments), so it is mostly distinct. Not 5 because generic audio/MIDI export terms could overlap with a general audio-conversion skill — minor overlap risk consistent with anchor 4.

4 / 5

Total

15

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

HKUDS/CLI-Anything

Path

musescore/agent-harness/cli_anything/musescore/skills/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.