Qmd

Local hybrid search for markdown notes and docs. Use when searching notes, finding related content, or retrieving documents from indexed collections.

This skill appears coherent and implements a local markdown search: it will read and index whatever files you point it at (so avoid indexing secrets), and it may download and store local model files (GGUF) to ~/.cache/qmd/models/ and load them into memory for semantic search which can be slow and resource-heavy. Installing qmd as suggested (bun install -g from GitHub) will execute third-party code — review the upstream repository before installing. If you plan to automate indexing (cron or agent scheduler), restrict the collection paths and run with a user account with limited privileges. If you have sensitive notes, either exclude those paths or run qmd in a sandboxed environment. Overall the skill is internally consistent with its stated purpose, but verify the upstream qmd project and its model-download/network behavior before installing.

Type: OpenClaw Skill Name: qmd-skill-4 Version: 0.1.0 The skill instructs the agent to install the `qmd` tool globally from an external GitHub repository (`https://github.com/tobi/qmd`) via `bun install -g` in `SKILL.md`. While this action is necessary for the skill's stated purpose, it introduces a supply chain vulnerability, as the integrity of the external repository is not guaranteed and could be compromised to deliver malicious payloads. The skill also involves extensive local file system interaction and shell command execution, which are powerful capabilities that, while plausible for a local search tool, could be misused if the agent were prompted to do so.