dsh-skill-search: Zero-Preloading DeepSeek Harness Skill Search Plugin
dsh-skill-search is a plugin for DeepSeek Harness (DSH), designed to address the high context costs caused by preloading all skill metadata during startup as the skill library expands. The plugin adopts a "zero preloading, on-demand search" strategy, avoiding the injection of skill names and descriptions at startup to reduce fixed overhead. When required by the model, it uses the `skill_search` tool to search for SKILL.md files on the disk using keywords. The matching scope covers directory names, Frontmatter information, and the beginning of the body text. Upon a match, it reads the full corresponding file and executes it, ensuring context costs depend only on the actual matched content. The plugin features pure read-only operation, zero runtime dependencies, and no HTTP routing, automatically falling back to Node traversal if `rg` is unavailable. Users can specify...
Read Moredsh-find-skill: Integrating skills search, installation, and lifecycle for DSH
`dsh-find-skill` is an MIT-licensed plugin for DeepSeek Harness (DSH) (v0.2.1) designed to bridge the `vercel-labs/skills` ecosystem, providing LLM-driven skill search, installation, and lifecycle management. The plugin supports three scopes: temporary, project, and global. Temporary skills are visible only within the current session and are automatically cleaned up upon session destruction; project or global skills are persisted to the hosted root directory. Core features include `skill_find` (searching based on the `skills.sh` API), `skill_install` (isolated installation via CLI), and `skill_remove`, along with a `/skill` subcommand for manual maintenance. Configuration options include the search base URL, default scope, and Provider ranking.
Read More