sonos

Sonos control: search, queue, playlists, rooms/groups, volume, YouTube.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/sonos/SKILL.md

Quality

Content

78%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 lean, well-organized body with a clear workflow and an explicit verify step, but the actual execution guidance is deliberately generic — no Sonos commands or examples are ever shown, so actionability stalls at the incomplete-guidance level. This is the one dimension separating the content from top marks.

Suggestions

Include at least one concrete example of the local Sonos tooling being invoked (e.g., the actual CLI command or API call the repo uses to play a track or set volume), so step 4 "Execute the requested playback action" has executable substance.

Add an error-recovery branch after the verification step (e.g., "If the state didn't change, re-check the room/group target and retry once") to turn verification into a true feedback loop and lift workflow clarity to 5.

Name the specific repo discovery targets more concretely than "package scripts or CLI help" — e.g., which package manager scripts or which CLI entry point to check.

Dimension	Reasoning	Score
Conciseness	Sections like "Prefer existing local Sonos tooling in the current repo before inventing shell/API calls" and "Do not change speaker groups, queues, or playback unless the user asks for it" are lean imperatives with zero padding and no explanation of concepts Claude already knows — every token earns its place.	5 / 5
Actionability	Some concrete guidance exists ("rg --files", "Dry-read current state", the discover/identify/execute/verify workflow), but the core step "Execute the requested playback action" and the rule to "Prefer existing local Sonos tooling" never name an actual command, CLI, or example — key execution details are missing, matching the incomplete-guidance anchor rather than the executable anchor 4.	3 / 5
Workflow Clarity	The numbered workflow (discover commands → identify target → dry-read state → execute → "Verify by reading current state again") is a clear sequence with an explicit verification checkpoint, but there is no error-recovery feedback loop for when verification shows the action failed, fitting anchor 4 rather than 5.	4 / 5
Progressive Disclosure	The body is under 50 lines, needs no external references, and is cleanly organized into Rules, Workflow, Common Tasks, and YouTube Notes sections — per the rubric's simple-skill guidance this earns a 5 on well-organized sections alone.	5 / 5
	Total	17 / 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.

A concise, distinct description with good natural keyword coverage, but it lacks the explicit 'Use when...' trigger guidance the rubric expects, capping completeness at 3. Adding a trigger clause and a few playback verbs would round out coverage.

Suggestions

Append a trigger clause such as "Use when the user asks to play, control, or group music on Sonos speakers" to answer 'when' explicitly and lift completeness above 3.

Add natural playback terms users actually say — "play music", "pause", "skip", "speakers" — to broaden trigger coverage beyond the current topic nouns.

Rephrase capability areas as concrete actions (e.g., "plays music and playlists, manages queues, groups rooms, sets volume") to push specificity from 4 toward 5.

Dimension	Reasoning	Score
Specificity	Phrases like "search, queue, playlists, rooms/groups, volume, YouTube" list several concrete capability areas, matching the anchor listing several specific actions with minor gaps; it falls short of 5 because playback verbs (pause, skip, seek, mute) are absent and items are topics rather than explicit actions.	4 / 5
Completeness	The description clearly answers 'what' ("Sonos control: search, queue, playlists, rooms/groups, volume, YouTube") but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3; it is above 2 because the 'what' is concrete, not vague.	3 / 5
Trigger Term Quality	"Sonos", "queue", "playlists", "volume", "YouTube" are natural terms a user would say, giving good keyword coverage, but common variations like "play music", "speakers", "pause", and "skip" are missing, so it sits between anchors 3 and 5 rather than at comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	"Sonos control" carves out a clear hardware niche with minimal conflict risk, but the bare keyword "YouTube" creates minor overlap with generic YouTube/music playback skills, fitting anchor 4 rather than the fully distinct anchor 5.	4 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: steipete/agent-scripts
Path: skills/sonos/SKILL.md
Commit: 3f8c6a3

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.