request-frame-preview
Preview and download the exact request frame (system prompt + tools + wire messages) that DeepSeek Harness sends to the model.
365 results
Preview and download the exact request frame (system prompt + tools + wire messages) that DeepSeek Harness sends to the model.
Single-select answer modes for DeepSeek Harness.
Glob-activated rule prompts for DeepSeek Harness (DSH): when the agent reads or edits a matching file, the rule activates and is injected into the conversation (Claude Code rules.md / # Path: style).
Per-workspace custom system prompts for DeepSeek Harness (DSH): set one active prompt per workspace, captured into a session at creation time, editable from a session-header dialog. 给 DeepSeek Harness 的「工作区自定义提示词」插件:每个工作区一条生效提示词,新建会话时固化注入,会话头部弹窗增删改查。
DSH compatibility guard: repairs compaction limits, fail-safe sandbox escalation, and missing tool descriptions for third-party models; capability lookups are cached and the deprecated prompt-injection path is off by default.
DSH 提示词锻炉:零配置流式优化(复用会话模型)+ 轻量词库(JSON 文件)+ 一键存技能。Prompt Forge: zero-config streaming optimization + file-based prompt library + one-click skills.
MxPage for DeepSeek Harness: ecommerce product-image workbench (analyze → plan → Visual Prompt Agent → generate) on top of an extracted, host-agnostic core of ziguishian/MxPage.
DeepSeek Harness 插件:把一段自定义 Markdown 提示词注入每次模型请求(独立上下文注入行),可在设置页编辑,并支持从 Claude Code / Codex 一键导入规则。
SQL 优化模式:EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents(38k★ MIT)启发。
提示词工程模式:结构化推理(CoT/ToT)、few-shot、模板变量、生产级提示词优化。受 wshobson/agents(38k★ MIT)启发。
DSH 提示词优化插件:在发送前拦截用户提示词,结合上下文给出 3 条改进建议
Persistent cross-session memory plugin for DeepSeek Harness: workspace-scoped durable facts with model-facing memory_write/list/search/forget tools and bounded prompt injection
dsh 提示词优化助手:发送前调用专门的提示词工程 agent 润色/补全/扩写命令,支持重写、多轮改写与撤回(host + client 双半插件,dsh plugin add 一键安装,随 harness 启动自动加载)。
DSH plugin that injects a system-prompt rule block for assisting with DeepSeek Harness plugin development: what you CAN / SHOULD / MUST NOT / SHOULD NOT do.
Cache-aware API token usage bar for the DeepSeek Harness Web UI
Global and workspace rules for DeepSeek Harness agents: configurable storage paths, system-prompt injection and a rules_read model tool.
DSH 插件:提示词工具,规范模型的思维链与回答内容,提供 Web UI 编辑 preset.md 与 AGENTS.md,并按 skills 目录注册可开关技能。
Todo-backed turn-stop gate and prompt plugin for DeepSeek Harness: blocks stop on unfinished work and prompts on no-todo or stale-todo streaks, configurable in the settings page.
Queue Consolidation for DeepSeek Harness: when the agent is busy and you queue several follow-up messages, the next turn runs with ONE consolidated formal prompt — the model rewrites the batch into a single prompt and executes once, instead of piecemeal one-message-per-turn rework.
Cron schedules for dsh-TUI: /cron saves 5-field cron entries that fire a prompt into the live conversation as a follow-up user message.
obra/superpowers skills provider plus system-prompt bootstrap for DeepSeek Harness
DeepSeek Harness plugin: cron-driven scheduled items. Each item carries a title, a prompt, and a croner expression; executions spawn a fresh agent session in a bound workspace (or the default cwd) and run on schedule or on demand. Includes a full-page management UI.
dshX live model working-status line (fork of dsh-working-activity): standard enterprise copy, running tool, turn elapsed — for the dshX TUI prompt.
DSH plugin: compress verbose voice-dictation text into token-efficient prompts, fully local.