dsh-skill-studio

Skill studio for DeepSeek Harness with self-improving pipeline: per-turn worth judgement, auto-accept into the skill library, semantic merging with category tags + model verdict + tombstone guard, and model calls routed through DSH (no stored API key). 适合需要构建、沉淀和自动优化Agent技能库的用户。

パッケージ

dsh-skill-studio

互換性

未検証

Harness ピア範囲

^0.1.0-rc.6 || ^0.1.1-rc.1 || ^0.1.2-alpha.1 || ^0.1.5-rc.1 || ^0.2.0-rc.2

Cordis ピア範囲

^4.0.1

バージョン

0.4.0

ライセンス

MIT

最終更新

2026/10/24

同名パッケージの別リポジトリ

zhengjy01/dsh-skill-studio

Configuration

Config file: ~/.dsh/dsh-skill-studio/extractor.json (mode 0600).

{
  "enabled": true,
  "autoPerTurn": true,
  "intervalMinutes": 60,
  "windowDays": 7,
  "maxCandidatesPerRun": 3,
  "autoAccept": true,
  "mergeThreshold": 0.2,
  "skillLanguage": "auto",
  "agentSkillDir": "C:\\Users\\\\.agents\\skills",
  "provider": "",
  "model": ""
}

Key	Purpose
`autoPerTurn`	Run the YES/NO judgement at the end of every turn
`intervalMinutes`	Fallback sweep interval; `0` disables it and relies on per-turn only
`autoAccept`	Write straight into the library instead of the review queue
`mergeThreshold`	Local similarity pre-filter (the merge decision itself is the model's)
`skillLanguage`	`auto` / `zh` / `en`; code, commands, and paths are never translated
`provider` / `model`	Empty = follow the session; or pick one in the panel

The legacy llmBaseUrl / llmApiKey / llmModel fields still work as an HTTP fallback for hosts without ctx.llm. Leave them empty in normal use.

dsh-skill-studio

同名パッケージの別リポジトリ

インストール

ドキュメント

Configuration