withPICA

View saved version →

---
name: catalog-audit
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.
triggers:
  - audit my catalog
  - how's my catalog doing
  - catalog health
  - what needs fixing
  - assess my catalog
audience: manager / label / artist
tools_required:
  - pica_dashboard_briefing
  - pica_works_inspect
  - pica_works_query
  - pica_catalog_stats
  - pica_find_duplicates
output: 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.
---

> **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.

_Copyright (c) 2025-2026 Withpica Ltd. All rights reserved._

# catalog-audit

Audit 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.

## Step 1 — Orient

Call `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.

## Step 2 — Pull the PICA Score

Call `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.

Do 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.

## Step 3 — Sample for quality

Call `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.

Common patterns to look for (publishing side — writer credits on works):
- Works with no credits at all
- Works where writer splits don't total 100%
- Works with no recordings
- Recordings with no ISRC
- People credited on works but missing IPI or ISNI

**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.

## Step 4 — Duplicate sweep

Call `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.

## Step 5 — Report

Produce three things, in this order:

1. **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.
2. **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").
3. **Score forecast.** "After those fixes, the score would likely rise from X to Y."

If urgent issues exist (e.g. missing ownership data on a work with active royalties, unverified works being licensed) flag them at the top.

## What not to do

- Don't run all sub-workflows at once. The audit is read-only — improvements are a separate user decision.
- Don't reco

Preview of the first 4,000 characters. Read full instructions →

View saved version →

---
name: first-session
description: When the user opens their workspace or asks "what should I do" — get them oriented in under a minute. Show who's acting on their behalf, surface what needs attention, and offer the single most worthwhile next move, routed to the right specialist skill. The user chooses where to start; this skill finds and offers, it doesn't do the work.
triggers:
  - what should I do
  - where do I start
  - morning
  - show me what's pending
  - open my workspace
  - i just connected
  - what's the state of things
audience: any agent connecting to PICA via MCP, especially on the first message of a session
tools_required:
  - pica_get_agent_activity
  - pica_dashboard_briefing
  - pica_dashboard_attention
  - pica_skill_list
  - pica_report_issue
  - pica_memory_list
  - pica_memory_save
  - pica_import_streaming_link
  - pica_import_youtube_link
output: Open by knowing (or learning, with at most one question) what the user is working toward; one line on who's acting for them; the few things most needing attention from the briefing; then one calibrated offer — the most worthwhile next move for THEIR goal and the specialist skill behind it — leaving the user to choose.
---

> **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.

_Copyright (c) 2025-2026 Withpica Ltd. All rights reserved._

# first-session

The user just arrived — "morning", "what should I do", "open my workspace", or a quiet first message that names no task. They don't yet know what's waiting for them. Get them oriented fast and hand them one clear next move.

This skill finds what matters and offers it. It does NOT do the work — no auditing credits, registering a work, or preparing for sync here. It surfaces the most worthwhile next move and names the specialist skill behind it; the user decides where to start. This is the map, not the journey.

Run it when the first message is an orientation phrase ("morning", "where do I start", "what should I do", "open my workspace") — not when the user names a single concrete action like "register work X" or "log yesterday's session". A task-specific prompt skips orientation; go straight to the work.

Where `set-up-workspace` helps a user configure a new account, `first-session` helps them re-enter an existing one and pick up where the catalog needs them.

If the user asks what PICA is, or what it's for, answer in one or two plain lines before anything else:

> _"pica helps you look after your songs, and everything that comes with them (who made them, the splits, the codes, the recordings, the agreements, the files), on your own terms. you hold the record and make the calls; pica remembers it all and shows you what's missing."_

Then make it concrete with one of THEIR songs by title if they have any. Every offer this skill makes gives the user more hold over a real song in one of four ways: **know** where it stands, **tidy** one gap themselves, **show** proof to someone, or **keep** it (it's theirs to export). Never answer with a feature list or a tool count.

Six quick beats, none of them a wall of text: know why they're here, who's acting for the user, the standing reporting-discipline note, load what needs attention, rank and offer the top move for THEIR goal, and a clean sweep at close-out.

## Phase 0 — Know why they're here

PICA's organizing question is: **who does this org want to be on the other side — what do they value?** That question is your internal lens. Never ask it out loud; people describe problems, not aspirations. You ask concrete things and infer.

First, read before asking: call `pica_memory_list` and look for the org-scoped key `org_intent`. Then branch:

- **The goal is on file** → open by con

Preview of the first 4,000 characters. Read full instructions →

View saved version →

---
name: register-my-works
description: Check registration status across collection societies (PRS, MCPS, PPL, MLC) and prepare works for registration. Identifies blockers, fills missing identifiers, and exports a registration bundle when works are ready.
triggers:
  - register my works
  - register my songs with my PRO
  - get this work to MLC
  - CWR export
  - registration bundle
  - am I ready to register
audience: songwriter / publisher / admin
tools_required:
  - pica_works_inspect
  - pica_resolve_work
  - pica_enrichment_proposals_list
  - pica_credits_update
  - pica_export_song_registration
output: Per-society registration coverage summary + the most common blocker and how to fix it + a list of works closest to being registration-ready, with offers to enrich missing ISWCs and export a registration bundle for ready works.
---

> **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.

_Copyright (c) 2025-2026 Withpica Ltd. All rights reserved._

# register-my-works

Help the user understand which of their works are registered with collection societies, which still need registration, and what's blocking the unregistered ones. Then offer to fix the blockers and export the works that are ready.

This is the highest-pain workflow in PICA. Most royalty loss happens because works aren't registered — or are registered with the wrong metadata. Be precise and offer concrete next actions.

## Pre-flight

Read these two resources before any writes:
- `pica://schemas/enrichment-resolve-required` — the canonical shape for `pica_resolve_work` calls (used to fill missing ISWCs from MLC)
- `pica://schemas/export-required` — the registration-bundle export shape used at the end of the flow

## Step 1 — Coverage check

Call `pica_works_query` to list works (default limit 50). Then call `pica_works_inspect` with `sections: ["registration"]` on each work, or use a representative sample if the catalog is large.

The `registration` section returns per-society status (PRS, MCPS, PPL, MLC). Three states are common:
- **fully registered** — every relevant society has the work
- **partially registered** — registered with some societies, missing from others
- **not registered** — no society has it

## Step 2 — Find the blockers

For unregistered or partially registered works, call `pica_works_inspect` with `sections: ["registration", "completeness"]` on a sample of 5-10 works. The completeness section names the blocker:

| Blocker | What it means | How to fix |
|---|---|---|
| Missing ISWC | Needed for PRS/MCPS | Call `pica_resolve_work` with `sources: ['mlc']` to look up the ISWC |
| Missing ISRC on recordings | Needed for PPL | Check recordings; if missing, the user may not have released yet or the DSP hasn't assigned one |
| Missing writer credits | Needed for all societies | Call `pica_credits_update` to add writers (treat `pica://schemas/work-credits-required` as the canonical shape — splits must total 100%) |
| Missing IPI on a credited writer | Needed for PRO registration | Call `pica_people_update` to add IPI; if unknown, `pica_resolve_person` may find it |

Treat `pica_resolve_*` calls as black boxes — they fan out over external sources and return proposals or matches. Do NOT speculate about how the source-weighting works.

## Step 3 — Enrichment proposals

If enrichment was triggered, call `pica_enrichment_proposals_list` to see what came back. Each proposal needs explicit user approval before applying. Do not auto-apply.

## Step 4 — Report

Produce:
- How many works are fully / partially / not registered, as numbers and percentages
- The most common blocker across unregistered works (one sentence)
- The 5 works closest to being registration-ready (fe

Preview of the first 4,000 characters. Read full instructions →