ClawHub

Deeplake

v1.0.1

SDK for ingesting data into Deeplake managed tables. Use when users want to store, ingest, or query data in Deeplake.

⭐ 0· 95·0 current·0 all-time
by@kaghni
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (Deeplake ingestion/query SDK) match the declared requirement (DEEPLAKE_API_KEY) and the SKILL.md content (examples for ingesting/querying, SDK usage). There are no unrelated credentials, binaries, or config paths requested.
ℹ
Instruction Scope
SKILL.md instructs the agent to install/use the Deeplake Python/Node SDK, read local dataset files (images, videos, CSVs, embeddings JSON), optionally call git-lfs to fetch large datasets, and call the Deeplake REST API endpoints. Reading local files and performing network fetches is expected for an ingestion SDK, but it means the agent will need filesystem and network access when used.
✓
Install Mechanism
This is instruction-only (no install spec). The skill tells users to run standard package installs (pip/npm) and system deps (ffmpeg, git lfs) as needed. No downloads from untrusted URLs or extraction of arbitrary archives are present in the skill metadata.
✓
Credentials
Only DEEPLAKE_API_KEY is declared as required/primary and is referenced throughout the docs as the API token. No other secrets or unrelated env vars are requested.
✓
Persistence & Privilege
always:false and normal model invocation. The skill does not request permanent presence or system-wide config changes. It does instruct operations that will read/write data via the Deeplake service and local files, which is within its scope.
Assessment
This skill appears coherent with its purpose. Before installing, understand that: (1) it needs your DEEPLAKE_API_KEY — grant only a token scoped appropriately; (2) using the skill will cause the agent to read local files (paths you supply) and may run package/system installs (pip/npm, ffmpeg, git-lfs) if you follow examples; (3) ingest workflows can pull large data (git-lfs) and generate thumbnails, so expect network and disk I/O; (4) the skill is instruction-only — it assumes the SDK/tools are installed in your environment; verify packages and token scope before use.

Like a lobster shell, security has layers — review code before you run it.

latestvk971n1hc71kns4j73nwy4qssth83hx2d

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

EnvDEEPLAKE_API_KEY
Primary envDEEPLAKE_API_KEY

Comments