DSHПЛАГИНЫ
⚡
ПЛАГИН DEEPSEEK HARNESS

dsh-skill-intelligence

Автор: @PolinniZhong ↗

Плагин «dsh-skill-intelligence» для DeepSeek Harness: Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page that keeps its declaration apart from its run: the body split into structure, declared workflow and progressive disclosure, the run logic read from local receipts, and the per-step evidence behind each claim. Evidence is never promoted into a conclusion — a step with no observed evidence is reported as such, not as executed or not executed — and the run's instruction hash is shown beside the current definition as match, mismatch or unavailable. It also reads the body, offers a Chinese reading version, and can clone a Skill into a local copy. It never writes back to the source Skill and never runs its scripts.

★ 0 звёзд GitHub15 октября 2026 г. добавлен
БЫСТРАЯ УСТАНОВКА

Команды для терминала DSH

dsh plugin --profile web add github:PolinniZhong/dsh-skill-intelligence

Запустите команду в терминале, где работает DeepSeek Harness. Перезапуск применит плагин автоматически.

ОПИСАНИЕ И ВОЗМОЖНОСТИ

Что делает dsh-skill-intelligence

Плагин «dsh-skill-intelligence» для DeepSeek Harness: Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page that keeps its declaration apart from its run: the body split into structure, declared workflow and progressive disclosure, the run logic read from local receipts, and the per-step evidence behind each claim. Evidence is never promoted into a conclusion — a step with no observed evidence is reported as such, not as executed or not executed — and the run's instruction hash is shown beside the current definition as match, mismatch or unavailable. It also reads the body, offers a Chinese reading version, and can clone a Skill into a local copy. It never writes back to the source Skill and never runs its scripts.

Показать оригинальное описание (EN/ZH)

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page that keeps its declaration apart from its run: the body split into structure, declared workflow and progressive disclosure, the run logic read from local receipts, and the per-step evidence behind each claim. Evidence is never promoted into a conclusion — a step with no observed evidence is reported as such, not as executed or not executed — and the run's instruction hash is shown beside the current definition as match, mismatch or unavailable. It also reads the body, offers a Chinese reading version, and can clone a Skill into a local copy. It never writes back to the source Skill and never runs its scripts.

УДАЛЕНИЕ ПЛАГИНА

Как удалить при необходимости

dsh plugin --profile web remove dsh-skill-intelligence
🛡️

Безопасность и аудит

Плагины выполняются в окружении пользователя DSH. Рекомендуется проверять исходный код, зависимости и запрашиваемые разрешения в репозитории автора перед установкой.