{"id":41796,"plugin_id":"plugin_asdk_app_69e8b6ea372c8191b97e6821a75f4bc3","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-10-24T13:01:28.254Z","digest":"2ad22815ae98488091fdb62088f5b5a0d8582a99817e014b58276213b0d0af8b","against":null,"payload":{"description":"Audit a music catalog for completeness, quality, and registration readiness using PICA's MCP tools. Produces a structured report with statistics, gap analysis, and prioritised improvement actions.","included_files":[],"name":"catalog-audit","skill_md_contents":"---\nname: catalog-audit\ndescription: Audit a music catalog for completeness, quality, and registration readiness using PICA's MCP tools. Produces a structured report with statistics, gap analysis, and prioritised improvement actions.\ntriggers:\n  - audit my catalog\n  - how's my catalog doing\n  - catalog health\n  - what needs fixing\n  - assess my catalog\naudience: manager / label / artist\ntools_required:\n  - pica_dashboard_briefing\n  - pica_works_inspect\n  - pica_works_query\n  - pica_catalog_stats\n  - pica_find_duplicates\noutput: Plain-language health summary (suitable for a non-technical stakeholder) + top 3 highest-impact improvements with specific steps + post-fix score estimate + any urgent issues.\n---\n\n> **Using this in ChatGPT:** PICA's tools are reached through the withPICA app's three tools. Find a tool with `pica_discover`, read its arguments with `pica_tool_details`, and run it with `pica_execute {tool: \"<name>\", args: {...}}`. Where this skill says `pica_skill_list`, check which withPICA skills are installed alongside this one instead.\n\n_Copyright (c) 2025-2026 Withpica Ltd. All rights reserved._\n\n# catalog-audit\n\nAudit a music catalog for completeness, quality, and registration readiness. Use this when a user asks \"how's my catalog doing,\" \"what needs fixing,\" or wants a health check before a release / sync push / sale.\n\n## Step 1 — Orient\n\nCall `pica_dashboard_briefing` first. The briefing returns a single compressed snapshot of catalog state (counts, recent activity, upcoming deadlines, top priorities). This is the cheapest first call and sets the routing decision for everything that follows.\n\n## Step 2 — Pull the PICA Score\n\nCall `pica_works_inspect` with `sections: [\"score\"]` on a representative work, or read the `catalog://health` resource. The score is a 0-100 composite across four pillars (income, ownership, asset, verification). The pillar with the lowest score is the audit's primary subject.\n\nDo NOT speculate about how the score is calculated beyond what the tool returns. Treat it as a black box that reports a number and pillar breakdown.\n\n## Step 3 — Sample for quality\n\nCall `pica_works_query` with `health_filter: \"low_completeness\"` and pull up to 20 works. For a sample of those, call `pica_works_inspect` with `sections: [\"completeness\"]` to see per-work gaps.\n\nCommon patterns to look for (publishing side — writer credits on works):\n- Works with no credits at all\n- Works where writer splits don't total 100%\n- Works with no recordings\n- Recordings with no ISRC\n- People credited on works but missing IPI or ISNI\n\n**Recording-side / master-ownership health** (artist / producer / label splits) is a separate domain handled per-recording by `set-recording-splits` — not surfaced by the score pillars at present. If the user mentions producer points, label splits, or master royalties, flag that this audit doesn't cover them and point to `set-recording-splits` per-recording.\n\n## Step 4 — Duplicate sweep\n\nCall `pica_find_duplicates`. A clean catalog has zero or near-zero duplicate signals. High duplicate counts indicate an import that needs reconciliation before further work.\n\n## Step 5 — Report\n\nProduce three things, in this order:\n\n1. **One-paragraph plain-language summary.** Suitable for a non-technical stakeholder. Lead with \"your catalog has X works and is healthy / has gaps / needs attention\" — not raw numbers.\n2. **Top 3 improvements, prioritised by effort vs impact.** Each with the specific tool call that would address it (e.g. \"add IPI numbers to 12 writers — call `pica_people_query` filtered by `has_ipi: false`, then `pica_people_update` for each\").\n3. **Score forecast.** \"After those fixes, the score would likely rise from X to Y.\"\n\nIf urgent issues exist (e.g. missing ownership data on a work with active royalties, unverified works being licensed) flag them at the top.\n\n## What not to do\n\n- Don't run all sub-workflows at once. The audit is read-only — improvements are a separate user decision.\n- Don't recommend `pica_works_delete` or any destructive operation. The audit's job is to describe, not to mutate.\n- Don't quote raw `pica_works_query` results back at the user verbatim. Summarise.\n\n## Follow-on skills\n\nAfter the audit, the natural next skills are:\n- `catalog-modelling` if the audit surfaces duplicate-title works or blank-ISWC variants that should be recordings under one work\n- `register-my-works` if registration coverage is low\n- `prepare-for-sync` if sync-readiness is the user's goal\n- `close-the-loop` (prompt) if the user wants to fix specific works one at a time\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}