.claude/skills/huawei-cloud-openviking-embedding-switchRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Switch OpenViking's embedding model to a local llama-server (or any OpenAI-compatible embedding endpoint) running inside a bwrap sandbox managed by job-env-manager. Handles the full lifecycle: detect current config, validate the target embedding endpoint, modify ov.conf, delete incompatible vectordb index when dimension changes, restart the openviking-server process in the sandbox, and verify the new collection dimension. Use this skill when the user wants to: (1) switch the OpenViking embedding model, (2) change…
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/huawei-cloud-openviking-embedding-switchRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/huawei-cloud-openviking-embedding-switchRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/huawei-cloud-openviking-embedding-switchRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @huaweicloudskill/huawei-cloud-openviking-embedding-switchclawhub inspect @huaweicloudskill/huawei-cloud-openviking-embedding-switch --version 1.0.1This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
exec (This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:e66e3e3492db9f9a21e8be85b5f06776fd3c54a6f6ea04229ada9f813d49e96edemo/example-input.jsonreferences/acceptance-criteria.mdreferences/config-reference.mdreferences/dataflow-diagram.mdreferences/guardrails.mdreferences/iam-policies.mdreferences/related-commands.mdreferences/troubleshooting.mdreferences/verification-method.mdscripts/switch-embedding-model.shskill-card.mdSKILL.md- Added support for switching the OpenViking embedding model to a local llama-server or any OpenAI-compatible embedding endpoint managed within a bwrap sandbox via job-env-manager. - Automatically detects current configuration, validates the target endpoint, modifies ov.conf, deletes incompatible vectordb index when dimension changes, and safely restarts openviking-server within the sandbox. - Verifies health, PID, and embedding dimension after the switch, with automatic rollback on failure. - No access to Huawei Cloud services required; operates entirely via local REST API to job-env-manager. - Includes robust validation, backup, error handling, and log checks to prevent common pitfalls and ensure seamless migration.