agentleFS
WhispersOfJWhispersOfJ/arrfleet-toolkit/skills/trash-guides-applier/SKILL.md

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

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
  1. Very specific:

    Treat these as starting-point examples, not gospel — edit them to match the user's own quality-tier preferences before applying, and always …

    line 30
  2. Very specific:

    Always run diff before apply when the profile JSON files have been hand-edited, to catch typos before they hit a live Radarr/Sonarr …

    line 56

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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 now

Auth via the same RADARR_URL/RADARR_API_KEY (and Sonarr equivalent) environment variables as arr-config-sync — no separate credential config.

Safety rules

  • apply is additive/updating only by matching custom-format and quality-profile name: 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. apply creates 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 diff before apply when the profile JSON files have been hand-edited, to catch typos before they hit a live Radarr/Sonarr instance.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.