dsh-purge
DeepSeek Harness 破甲:所有模型都可破甲,不同模型可换不同提示词;默认提示词面向国模「小码酱」。Jailbreak for every model. 求 Star ⭐
37 results
DeepSeek Harness 破甲:所有模型都可破甲,不同模型可换不同提示词;默认提示词面向国模「小码酱」。Jailbreak for every model. 求 Star ⭐
DSH 个人中心:设置 →「个人配置」分区(Token 用量统计 + 个性化自定义指令 + 外观/全局字号 + 成本估算 + 桌面宠物 + 会话状态概览)
Four-source migration wizard: copy Claude Code, Codex, OpenCode and Hermes sessions, memories, skills, instructions and slash commands into DeepSeek Harness as resumable sessions — copy-only, approval-gated, idempotent
DeepSeek Harness plugin bundle: optimize raw instructions into professional Role / Task / Context / Format prompts through the harness llm service
Edit ~/.dsh/AGENTS.md (global rules) from the web settings panel.
Inspect and manage the live instruction chain and project skills for the current dsh session, with in-place creation and editing — what you see is what the model gets
DSH web plugin: per-host personalization — global custom instructions, local long-term memory (collect / retain / integrate / manage), and reply tone presets.
Command history for the DeepSeek Harness web GUI composer: press Up/Down to cycle through your previously sent instructions, and reach the oldest draft again at the end of the history. 在 DSH Web 输入框中用上下方向键浏览此前发送的指令,回到历史末尾时恢复切换前的草稿。
DSH Web manager for global AGENTS.md with Markdown preview, reusable templates, version history, import rollback, and revision-conflict protection.
Clinical documentation toolkit for DeepSeek Harness: SBAR and I-PASS handovers, SOAP and APSO notes, admission H&P, discharge summaries with pending-results enforcement, patient-instruction readability scoring, HIPAA Safe Harbor de-identification, and cited FDA label/FAERS/recalls/Drugs@FDA, MedlinePlus, PubMed/PMC/Europe PMC, and ClinicalTrials.gov (search/details/eligibility/investigators/endpoints) lookups. Drafts only; not a medical device.
Semantic-Linter plugin and CLI for narrowing wide-boundary wording in LLM instruction files.
Inject a configurable dsh-ui status card instruction before every DSH agent reply
DSH conversation checkpoints: list every user instruction, jump/scroll to it, roll the visible conversation back to it (optionally with file snapshots), recall/edit sent instructions, show this round's file changes inline under the conversation, and a VS Code-like diff viewer (unified/side-by-side) with per-file undo.
Privacy-minimal provenance receipts for DeepSeek Harness workspace instructions
Claude Code-style `paths:` rule injection for DeepSeek Harness (DSH): inject rules from ~/.dsh/rules, <project>/.dsh/rules and <project>/.claude/rules into the model context.
Compare DeepSeek Harness, Codex, and Claude Code instruction surfaces for the same workspace.
DSH web plugin: a floating bubble at the top of the conversation showing the last user instruction that scrolled out of view.
My Habits for DeepSeek Harness: edit the user-global AGENTS.md from the Web settings — injected into every session by the built-in agent-instructions loader.
Edit DeepSeek Harness global AGENTS.md instructions and memory directly in Web settings.
AI turns repeated dev commands, prompts, and instructions into one-click DeepSeek Harness actions.
Stop runaway agent loops in DeepSeek Harness: denies repeated identical tool calls and enforces a per-agent call cap, outside the model where instructions cannot reach.
Personalization plugin for the DeepSeek Harness (dsh): teach your assistant who you are, who it is, and how it should behave. Adds a Personalization page to dsh settings (custom instructions, nicknames, persona) and injects the content into every agent turn's system prompt.
Sidebar skill hub for DeepSeek Harness Web GUI — shows the current/used skills of the active session and enables one or several skills at once by injecting their instructions into the conversation. 🌟 侧边栏技能中心:显示当前会话正在使用/已使用的技能,并可一次启用一个或数个技能(注入技能说明,整轮对话可用)。
统一管理 DSH 规则:编辑全局规则 ~/.dsh/AGENTS.md、编辑项目 AGENTS.md、LLM 自动拆分项目规则为分层 AGENTS.md + skills。合并自 dsh-global-rules 与 dsh-rule-splitter。