music-search

Search cloud drives for downloadable music resources (songs, albums, lossless audio). Use this skill when the user wants to download a specific song or album. Do NOT use for general music information, lyrics, or recommendations.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./SKILLs/music-search/SKILL.md

Quality

Content

76%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 highly actionable with copy-paste commands, parameter tables, examples, and a JSON output schema, and it is reasonably concise and well-structured with real bundle files. Its main gap is the absence of validation/error-recovery feedback loops in the agent workflow.

Suggestions

Add an explicit validation/error-handling step to the agent workflow (e.g., check `success` in the JSON, retry with `--engine web` or different keywords on empty results) to support a feedback loop.

Move the full env/config block and the JSON output schema into a short reference file linked from SKILL.md to tighten progressive disclosure.

Trim the explanatory asides under 热门推荐 and 引擎说明 since the examples already convey the behavior.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with command tables, short option explanations, and minimal padding, though a few explanatory asides (e.g., '本质上是以推荐类关键词调用搜索', engine blurbs) could be trimmed; not a 5 because a couple of tokens restate what examples already show.	4 / 5
Actionability	Every command is given as copy-paste-ready bash/powershell with concrete arguments, a parameter table with defaults, five worked examples, a sample JSON output schema, and field definitions; matches 'fully executable; copy-paste ready; specific examples cover the common cases'.	5 / 5
Workflow Clarity	The 'Agent 使用流程' lists a clear 5-step sequence, but it is a read-only search/resolve operation with no validation checkpoints and no error-recovery loop; per the rubric's batch/feedback-loop notes a skill lacking validation feedback loops caps here, so not a 4.	3 / 5
Progressive Disclosure	Structure is well-organized with clear section headers and real bundle files (music-search.sh/.ps1/.js, shared/deep-extract.js) referenced by path; the JS implementation lives in separate scripts rather than inlined, which is good. Not a 5 because SKILL.md still inlines the full config/env and output schema inline and references are by path string rather than clickable one-level links.	4 / 5
	Total	16 / 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 clearly defines a niche (downloading music from cloud drives) with explicit use/don't-use trigger guidance, making it highly distinct. It is held back by limited concrete action verbs and only moderate natural-term coverage.

Suggestions

Replace the single verb 'Search' with several concrete actions (e.g., 'search, filter by drive and audio format, and resolve share links') to lift specificity.

Add common user synonyms such as 'track', 'single', 'lossless/.flac', and 'hi-res' to broaden trigger-term coverage.

Expand the 'Use when...' clause to enumerate more concrete trigger phrases (e.g., 'when the user wants a FLAC/Hi-Res download or a share link for a song/album').

Dimension	Reasoning	Score
Specificity	Names the domain (cloud drives, downloadable music, songs/albums/lossless audio) but lists no concrete actions beyond 'search'; closest to the 'names domain and 1-2 concrete actions but not comprehensive' anchor, not a 4 which requires several specific actions.	3 / 5
Completeness	Clearly states what it does (search cloud drives for downloadable music) and gives explicit 'Use this skill when...' guidance plus a 'Do NOT use for...' exclusion; 'when' is explicit and concrete but slightly narrow, so just below the 5 anchor that demands comprehensive concrete trigger phrases.	4 / 5
Trigger Term Quality	Includes natural terms like 'download a specific song or album' but lacks synonyms/variations (track, single, .flac, hi-res) users might say; sits at 'some relevant keywords but missing common variations' rather than the fuller coverage of a 4.	3 / 5
Distinctiveness Conflict Risk	The exclusion clause ('Do NOT use for general music information, lyrics, or recommendations') carves a clear niche distinct from general music skills, minimizing conflict risk; matches the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: netease-youdao/LobsterAI
Path: SKILLs/music-search/SKILL.md
Commit: 100d3f7

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.