recoup-content-pack
Batch-generate a whole pack of content for one song — 15–30 assets as a "clip family" for a release push. Use when the user says "content pack", "batch of clips", "a week of content", "30 posts for the launch", "clip family", "fill my content calendar for [song]", or "lots of content for [release]". Fans out across formats (multiple short-video looks, quote cards, a carousel, a Canvas) and, with audience data, themes them to where the song's fans actually are. Estimates cost and confirms before spending.
What this skill does
# Content Pack
Modern release pushes need **volume** — the consensus is 15–30 assets per song, posted as
a cohesive "clip family." This skill orchestrates the other content skills to produce that
batch in one run, and (the moat) uses audience data to theme the pack toward where the
song's listeners actually are.
Read `references/content-api.md` (endpoints, async, `estimate`),
`references/account-resolver.md` (auth + IDs), `references/workspace-context.md`
(context + write-back), and `references/analyze-gate.md` (verify each asset). All ship
alongside this skill.
## This skill spends real credits — gate it
A 30-asset fan-out costs meaningfully more than one clip. **Always estimate and confirm
before generating:**
```bash
curl -sS -X POST "$BASE/content/estimate" "${AUTH[@]}" -H "Content-Type: application/json" \
-d "$(jq -n --arg a "$ARTIST_ACCOUNT_ID" --argjson n "$ASSET_COUNT" '{artist_account_id:$a, count:$n}')"
```
Show the estimate and the planned asset list; only fan out after the user approves. On
`insufficient_credits`, surface the `checkoutUrl`.
## Steps
1. **Resolve artist + context** (`references/account-resolver.md`,
`references/workspace-context.md`).
2. **Plan the pack.** A balanced default for one song (~20 assets):
- 6–10 **short-video** clips across looks (bedroom / stage / outside / album-record-store)
and hooks — lead each with a `recoup-song-hook` moment (from `recoup-song-analysis`).
- 4–6 **quote cards** from the strongest lines.
- 1 **carousel** (photo dump / lyric breakdown).
- 1 **Canvas/visualizer** loop.
- captions per asset in the artist's voice (`recoup-brand-voice-caption`).
3. **Theme to the audience (the moat).** With audience demographics / top cities (the
`recoup-research` skills), bias looks and copy toward where the fans are — e.g. an R&B
ballad → intimate/aesthetic edits, not high-energy meme cuts. State the targeting
rationale in the manifest.
4. **Estimate + confirm** (above).
5. **Generate** by delegating to the per-format skills; **analyze-gate every asset**
(`references/analyze-gate.md`) and drop/regenerate failures.
6. **Assemble a manifest** — list each asset, its format, hook/line, target platform, and
suggested caption.
## Persist
Workspace → `artists/{slug}/releases/{release-slug}/content-pack/` with the assets +
`pack-manifest.md`, commit `{what}: {why}` (`references/workspace-context.md`). Otherwise
return the asset list + manifest.
## The boundary (read this)
This skill makes **legitimate creative volume + audience targeting** to power the real
pages an artist or marketer runs. It does **not** create or operate networks of fake/burner
accounts, proxy/anti-detect ban-evasion, or automated mass-posting. We supply the content
and the targeting, not an account farm. If the user asks for the farm, decline that part
and deliver the creative pack.
## Guardrails
- **Estimate + confirm before spending.** No silent 30-asset fan-outs.
- **Cohesion** — the pack is a clip *family*, consistent look + voice, not 20 unrelated files.
- **Never cross-post identical files** — see `recoup-content-reformat` for per-platform cuts.
Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.