From memv-skills
This skill should be used when the user asks to 'upload a PDF to memv', 'ingest a document', 'add an image to memv', 'process audio with memv', or when calling client.upload.batch.create. Covers multimodal-first ingestion and when to use upload.batch.create vs memories.add. For video specifically, use memv-video-ingest instead.
How this skill is triggered — by the user, by Claude, or both
Slash command
/memv-skills:memv-filesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
1. `docs/memv/sdk/files.md` — upload API (`client.upload.batch.create`).
docs/memv/sdk/files.md — upload API (client.upload.batch.create).docs/memv/sdk/error-handling.md — upload-failure modes.docs/memv/sdk/videos.md — video → use that skill instead (same upload.batch.create path, video skill has format guidance).docs/memv/sdk/files.md)client.upload.batch.create(space_id, files=[...], ...) — upload PDF / doc / image / audioclient.upload.batch.get_status(batch_id) — poll for processing done (sync wrapper) / TS: getStatusclient.files.list(space_id) — enumerate files in spacespace_id mandatory.upload.batch.create async. Returns batch_id. Poll get_status(batch_id) until done before assuming memories searchable.asyncio.gather with backoff per sdk/error-handling.md.with open(file_path, "rb") as f:
response = client.upload.batch.create(
space_id=space_id,
files=[f],
metadata={"source": "user_upload", "filename": file_path.name},
)
batch_id = response.batch_id
# poll until processing completes
while True:
status = client.upload.batch.get_status(batch_id=batch_id)
if status.state in ("completed", "failed"):
break
client.upload.batch.create (skill memv-video-ingest for format guidance)client.upload.batch.create (this skill)client.memories.add(content=...) (skill memv-add-memory)client.memories.add(content=open(pdf).read()) — stuffs raw bytes as text. Use upload.batch.create.create() returns. Poll get_status first.npx claudepluginhub drpod/memv-skills --plugin memv-skillsProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.