arr-media-stack
Radarr, Sonarr, Prowlarr, Bazarr, and qBittorrent APIs for automated media management — search, add, monitor, and troubleshoot downloads
82
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./arr-media-stack/SKILL.mdQuality
Discovery
67%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 specific tools and concrete actions, making it highly distinctive in its niche. However, it lacks an explicit 'Use when...' clause and could benefit from additional natural language trigger terms that users might say when needing help with media automation (e.g., 'download movies', 'TV shows', 'torrents').
Suggestions
Add a 'Use when...' clause such as 'Use when managing media downloads, configuring *arr stack, or troubleshooting torrent automation'
Include natural user phrases like 'download movies', 'TV shows', 'torrents', 'media library', or 'Plex/Jellyfin setup' to capture more trigger scenarios
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'search, add, monitor, and troubleshoot downloads' along with naming the specific tools (Radarr, Sonarr, Prowlarr, Bazarr, qBittorrent) and domain (automated media management). | 3 / 3 |
Completeness | Clearly answers 'what' (API interactions for media management with specific actions), but lacks an explicit 'Use when...' clause or trigger guidance. The 'when' is only implied through the tool names. | 2 / 3 |
Trigger Term Quality | Includes good tool-specific keywords (Radarr, Sonarr, Prowlarr, Bazarr, qBittorrent) that users would naturally mention, but missing common user phrases like 'download movies', 'TV shows', 'torrents', 'media server', or 'Plex/Jellyfin' that often accompany these tools. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific tool names (Radarr, Sonarr, etc.) that create a clear niche. Unlikely to conflict with other skills as these are specialized media automation tools with unique names. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality API reference skill that excels at conciseness and actionability. Every command is executable with proper authentication patterns shown. The main weakness is the lack of explicit validation steps for destructive operations (deletes, bulk searches) and no feedback loops for error recovery in multi-step workflows.
Suggestions
Add a verification step before destructive operations like delete commands (e.g., 'First confirm the movie exists and check its ID: curl ... | jq', then proceed with delete)
Include a brief validation workflow for the qBittorrent VPN setup showing how to verify traffic is actually routing through VPN before proceeding
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. No unnecessary explanations of what Radarr/Sonarr are or how APIs work. Every section jumps straight to executable commands with minimal prose. | 3 / 3 |
Actionability | Fully executable curl commands throughout with proper headers, JSON payloads, and jq filters. Copy-paste ready examples for every operation including auth, CRUD operations, and troubleshooting. | 3 / 3 |
Workflow Clarity | Commands are well-organized by service and function, but lacks explicit validation checkpoints. For destructive operations like delete with files, there's no verification step or confirmation workflow. The qBittorrent auth flow is sequential but other multi-step processes lack feedback loops. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections per service, a troubleshooting table for quick reference, and appropriate inline content. For a reference-style skill of this scope, the single-file organization with clear headers is appropriate and navigable. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%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
87d2278
- 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.