arr-media-stack

Radarr, Sonarr, Prowlarr, Bazarr, and qBittorrent APIs for automated media management — search, add, monitor, and troubleshoot downloads

Quality

68%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./arr-media-stack/SKILL.md

Quality

Discovery

72%

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 effectively identifies a clear niche with specific tool names that serve as strong trigger terms, making it highly distinctive. However, it lacks an explicit 'Use when...' clause and could benefit from more detailed enumeration of specific capabilities beyond the high-level verbs provided.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about managing movies, TV shows, subtitles, indexers, or torrent downloads through Radarr, Sonarr, Prowlarr, Bazarr, or qBittorrent.'

Expand the action list with more specific capabilities like 'configure quality profiles, manage indexers, handle subtitle downloads, check queue status, resolve failed imports' to improve specificity.

Dimension	Reasoning	Score
Specificity	Names the specific tools (Radarr, Sonarr, Prowlarr, Bazarr, qBittorrent) and some actions (search, add, monitor, troubleshoot downloads), but doesn't list comprehensive concrete actions like configuring indexers, managing quality profiles, or handling subtitle downloads.	2 / 3
Completeness	The 'what' is reasonably covered (API interactions for media management tools), but there is no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	Includes strong natural keywords users would say: Radarr, Sonarr, Prowlarr, Bazarr, qBittorrent, downloads, media management, search, add, monitor. These are the exact terms users in the *arr ecosystem would use.	3 / 3
Distinctiveness Conflict Risk	The specific tool names (Radarr, Sonarr, Prowlarr, Bazarr, qBittorrent) create a very clear niche that is unlikely to conflict with other skills. These are highly distinctive trigger terms.	3 / 3
	Total	10 / 12 Passed

Implementation

64%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a strong reference skill with excellent actionability — every service section provides executable, copy-paste-ready curl commands with useful jq filters. The main weaknesses are the monolithic structure (covering 7 services in one file without progressive disclosure) and the lack of explicit validation steps in multi-step or destructive workflows. The troubleshooting table is a valuable addition.

Suggestions

Add explicit validation checkpoints to multi-step workflows, e.g., after movie lookup verify the result before adding, and after delete operations confirm the resource is removed.

Consider splitting per-service API details into separate referenced files (e.g., RADARR.md, SONARR.md) and keeping SKILL.md as a concise overview with quick-start examples and cross-references.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient with executable examples and minimal prose, but it's quite long (~200+ lines) covering 7 services. Some sections could be tightened — e.g., the common storage layout and VPN docker-compose are nice-to-have but add bulk. However, it avoids explaining what these tools are or how APIs work in general, which is good.	2 / 3
Actionability	Every section provides fully executable curl commands with proper headers, endpoints, and jq filters. The examples are copy-paste ready with clear placeholders (YOUR_RADARR_KEY, TORRENT_HASH). The troubleshooting table maps specific problems to specific fixes.	3 / 3
Workflow Clarity	The skill presents individual API calls clearly but lacks explicit multi-step workflows with validation checkpoints. For example, the 'search and add a movie' flow doesn't explicitly say 'verify the lookup result before using tmdbId in the add call.' The delete operations (movie with files, torrent with files) are destructive but have no confirmation/validation steps. The health check script at the end is a good validation tool but isn't integrated into workflows.	2 / 3
Progressive Disclosure	The content is well-organized with clear section headers per service, but it's a monolithic file with no references to external files for deeper content. Given the breadth (7 services), splitting detailed API references per service into separate files would improve navigation. However, the flat structure with clear headings is functional.	2 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ddnetters/homelab-agent-skills
Commit: 808c382

Reviewed: 27 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.