trash-guides-applier
Skill1 starsChanged 4 months agoMITView on GitHub
Apply TRaSH-Guides-style quality profiles and custom formats to Radarr and Sonarr via their REST APIs, using the JSON profile definitions in profiles/. Use when the user asks to set up or refresh quality profiles following TRaSH-Guides, or add a custom format (e.g. HDR10+, remux-tier scoring). Trigger phrases: "apply trash guides profiles", "set up quality profiles", "add this custom format", "refresh radarr/sonarr profiles".
- Reads credentials
In this repository7 other files it gives its agents.
- arr-config-syncSkill
- docker-compose-managerSkill
- download-client-orchestratorSkill
- health-monitorSkill
- media-path-validatorSkill
- request-manager-integratorSkill
- secret-injectorSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 30
Treat these as starting-point examples, not gospel — edit them to match the user's own quality-tier preferences before applying, and always …
- Very specific: line 56
Always run diff before apply when the profile JSON files have been hand-edited, to catch typos before they hit a live Radarr/Sonarr …
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
TRaSH-Guides Applier
Applies TRaSH-Guides-recommended quality profiles and custom formats to Radarr/Sonarr directly via their REST APIs — a lighter-weight alternative to running a full Recyclarr scheduled sync when the user just wants to apply or refresh profiles on demand.
Profile files
profiles/radarr-profiles.json— quality profiles + custom formats for Radarr, following TRaSH-Guides' movie recommendations (WEB-DL/Remux tiering, HDR bonus scoring).profiles/sonarr-profiles.json— same shape for Sonarr (episode quality tiering).
Each file has the shape:
{
"quality_profiles": [
{"name": "HD Bluray + WEB", "upgrade_allowed": true, "cutoff": "WEB 1080p", "items": [...]}
],
"custom_formats": [
{"name": "HDR10+", "score": 30, "specifications": [...]}
]
}Treat these as starting-point examples, not gospel — edit them to match the user's own
quality-tier preferences before applying, and always diff after a hand-edit to catch typos.
Usage
python3 applier.py apply radarr --profiles profiles/radarr-profiles.json
python3 applier.py apply sonarr --profiles profiles/sonarr-profiles.json
python3 applier.py diff radarr --profiles profiles/radarr-profiles.json # what would change
python3 applier.py list-current radarr # what's live right nowAuth via the same RADARR_URL/RADARR_API_KEY (and Sonarr equivalent) environment
variables as arr-config-sync — no separate credential config.
Safety rules
applyis additive/updating only by matching custom-format and quality-profilename: it creates missing ones and updates changed custom-format scores, but never deletes a profile/format that exists live but isn't in the local JSON — a user may have a profile that's intentionally not TRaSH-standard.- Quality-profile item ordering (the actual quality tier ladder) isn't blind-overwritten on
an existing profile — Radarr/Sonarr assign real quality-item IDs server-side, and item
ordering isn't safely derivable from this JSON alone.
applycreates a skeleton for a brand-new profile and tells the user to finish item ordering in the Arr UI; it never touches an existing profile's item list. - Always run
diffbeforeapplywhen the profile JSON files have been hand-edited, to catch typos before they hit a live Radarr/Sonarr instance.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

