How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

recoup-research-playlist-targets - Skill

Name: recoup-research-playlist-targets
Author: recoupable

Imported from recoupable/skills (skills/recoup-research-playlist-targets/SKILL.md). Install upstream with npx skills add recoupable/skills --skill recoup-research-playlist-targets. Copyright stays with the author.

Recoup Research — Playlist Targets

Catalog-wide playlist strategy from research data (not one audio file).

export RECOUP_API="https://api.recoupable.dev/api"   # auth header: x-api-key: $RECOUP_API_KEY

Procedure

/playlists?artist={ARTIST}&status=current for placements; status=past for re-pitch opportunities.
/similar → /playlists on each peer → playlists hosting 2+ peers you're NOT on are the warmest targets (the gap analysis).
/track/playlists?id={track_id}&editorial=true ($0.05 = 50,000 micro-dollar credits) for per-track editorial coverage.
/metrics (playlists_editorial_current) to judge editorial vs algorithmic balance.

Answer: target playlists (ranked, warmest first), placement gaps, editorial vs algorithmic, and which catalog tracks to push. Full chains in references/workflows.md (Playlist Pitching Intelligence, Catalog Optimization).

Guardrails

No invented placements. followers_total is a formatted string ("34.3M") — parse it if sorting numerically.
Credits: on insufficient credit or entitlement, preserve the task and explain the unavailable feature. Do not surface billing/checkout links, initiate purchases, rely on automatic credit purchases or retry silently.

References

references/workflows.md — playlist pitching + catalog optimization chains.

Install recoup-research-playlist-targets and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "recoupable-skills-recoup-research-playlist-targets", "kind": "skill", "name": "recoup-research-playlist-targets", "description": "Find which playlists an artist or whole catalog should target and where the placement gaps are — catalog-wide playlist strategy from research data. Use for \"which playlists should we target\", \"placement gaps\", \"editorial vs algorithmic\", or \"which catalog tracks to push\". This is desk strategy from data; to pitch ONE song from its audio use recoup-song-placement-pitch.", "publisher": "recoupable", "version": "1.0.0", "capabilities": { "domains": [ "coding", "finance" ], "tags": [ "skill-md", "skills-sh" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Find which playlists an artist or whole catalog should target and where the placement gaps are — catalog-wide playlist strategy from research data. Use for \"which playlists should we target\", \"placement gaps\", \"editorial vs algorithmic\", or \"which catalog tracks to push\". This is desk strategy from data; to pitch ONE song from its audio use recoup-song-placement-pitch." ], "primary": false, "metadata": { "source": { "provider": "skills.sh", "repository": "https://github.com/recoupable/skills", "path": "skills/recoup-research-playlist-targets/SKILL.md", "ref": "HEAD", "url": "https://github.com/recoupable/skills/blob/HEAD/skills/recoup-research-playlist-targets/SKILL.md", "key": "recoupable/skills/skills/recoup-research-playlist-targets/SKILL.md" } }, "instructions": "# Recoup Research — Playlist Targets\n\nCatalog-wide playlist strategy from research data (not one audio file).\n\n```bash\nexport RECOUP_API=\"https://api.recoupable.dev/api\" # auth header: x-api-key: $RECOUP_API_KEY\n```\n\n## Procedure\n\n- `/playlists?artist={ARTIST}&status=current` for placements; `status=past` for\n re-pitch opportunities.\n- `/similar` → `/playlists` on each peer → playlists hosting 2+ peers you're NOT on\n are the warmest targets (the gap analysis).\n- `/track/playlists?id={track_id}&editorial=true` ($0.05 = 50,000 micro-dollar credits) for per-track\n editorial coverage.\n- `/met", "cost": { "context_tokens": 338 } }

recoup-research-playlist-targets

About

Recoup Research — Playlist Targets

Procedure

Guardrails

References

Install recoup-research-playlist-targets and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Use it

Manifest

Reviews