Skip to main content
AI/MLjmagly

media-curator-quickref

AUTO-INVOKE when user mentions media curation, discography, archive, music collection, source acquisition, metadata tagging, Plex, Jellyfin, MPD. Media-curator framework quick reference — discovery phrases for discography analysis, source discovery, acquisition, quality filtering, metadata, archive integrity.

Stars
141
Source
jmagly/aiwg
Updated
2026-05-31
Slug
jmagly--aiwg--media-curator-quickref
View on GitHubRaw SKILL.md

// install — copy + paste into any project

mkdir -p .claude/skills && curl -fsSL https://raw.githubusercontent.com/jmagly/aiwg/HEAD/agentic/code/frameworks/media-curator/skills/media-curator-quickref/SKILL.md -o .claude/skills/media-curator-quickref.md

Drops the SKILL.md into .claude/skills/media-curator-quickref.md. Works with Claude Code, Cursor, and any agent that loads SKILL.md files from .claude/skills/.

Media Curator Framework — Quick Reference

This is your always-loaded directory for the AIWG media-curator framework. It does not list every skill. Instead, it teaches the framework's mental model and gives you curated search phrases that map to aiwg discover lookups.

Canonical access pattern: discover → show

When you find a candidate via aiwg discover, fetch its body with aiwg show <type> <name>. Never use find, ls, Glob, or direct Read on <provider>/skills/ paths — those reflect the kernel-pivot deploy state, not the full surface.

aiwg discover "<phrase>"             # find — returns ranked candidates
aiwg show skill <name>               # fetch — streams the SKILL.md body

If your platform's Skill tool errors on a non-kernel skill (expected — most aren't kernel), the fallback is aiwg show, never filesystem browsing. Last-resort if aiwg itself is broken: read directly from $AIWG_ROOT/agentic/code/... (the canonical corpus, always present).

How to use this quickref

  1. Identify the capability domain the user's need belongs to
  2. Pick a curated phrase from that domain (or paraphrase the user's words)
  3. Run aiwg discover "<phrase>" and surface the top match (or top-3) to the user

Do not enumerate skills from memory. Discovery is the lookup surface.

What this framework is for

End-to-end media archive management: discover sources across YouTube/Internet Archive/Bandcamp, acquire with yt-dlp-based patterns, score quality, embed cover art, apply consistent metadata, generate gap notes for missing content, verify integrity with SHA-256, and export to platform-specific formats (Plex, Jellyfin, MPD, mobile, archival).

Capability domains

Domain Covers
Catalog planning Artist discography analysis, canonical catalog structure
Discovery & acquisition Find sources, download with quality scoring, yt-dlp / Internet Archive patterns
Metadata & assembly Tag files, embed cover art, assemble compilations
Completeness & gaps Audit collection completeness, document missing content
Integrity & export SHA-256 verification, platform-specific export bundles
Provenance Track derivation chains for media files

Curated discovery phrases

Catalog planning

aiwg discover "analyze artist discography"     # → analyze-artist

Discovery & acquisition

aiwg discover "find media sources"             # → find-sources
aiwg discover "acquire media"                  # → acquire
aiwg discover "youtube acquisition"            # → youtube-acquisition (pattern reference)
aiwg discover "archive acquisition"            # → archive-acquisition (pattern reference)
aiwg discover "audio extraction"               # → audio-extraction (pattern reference)
aiwg discover "quality filter media"           # → quality-filtering

Metadata & assembly

aiwg discover "tag media collection"           # → tag-collection
aiwg discover "metadata tagging"               # → metadata-tagging (pattern reference)
aiwg discover "cover art embedding"            # → cover-art-embedding (pattern reference)
aiwg discover "assemble compilation"           # → assemble

Completeness & gaps

aiwg discover "check collection completeness"  # → check-completeness
aiwg discover "gap documentation"              # → gap-documentation

Integrity & export

aiwg discover "verify archive integrity"       # → verify-archive (score 0.73)
aiwg discover "integrity verification"         # → integrity-verification
aiwg discover "export media collection"        # → export (score 1.00)

Orchestration & provenance

aiwg discover "curate"                         # → curate (end-to-end orchestrator)
aiwg discover "provenance tracking"            # → provenance-tracking

Workflow shape

analyze-artist (catalog plan)  →
  find-sources (discovery)  →
    quality-filtering (accept/reject)  →
      acquire (download)  →
        tag-collection (metadata)  →
          verify-archive (integrity)  →
            export (target platform)

gap-documentation and check-completeness run cross-cutting at any stage.

Artifact directory layout

.aiwg/media/
├── catalogs/         # Per-artist canonical discographies
├── sources/          # Discovery output (ranked candidates)
├── acquisitions/     # Acquired files + checksums
├── gaps/             # GAP-NOTE markers for missing content
├── exports/          # Platform-specific export bundles
└── verify/           # Integrity reports

When the curated phrases don't fit

aiwg discover "<your need, paraphrased>" --limit 5

Anti-pattern: don't enumerate

If a user asks "what media skills are available?", do not list from this skill. Run:

aiwg discover --type skill --limit 20 "<their interest area>"