dsh-spec-forge
需求锻造:需求澄清、提示词提炼与经验沉淀。把模糊的编程需求锻造成可执行规格,并在每次任务完成后沉淀为可自动复用的个人提示词模板库。
1383 results
需求锻造:需求澄清、提示词提炼与经验沉淀。把模糊的编程需求锻造成可执行规格,并在每次任务完成后沉淀为可自动复用的个人提示词模板库。
Drop a forked session's inherited pending prompts, so a fork child answers the prompt you send it instead of the source session's unclaimed queue.
DSH plugin (NInfer engine only): fixes compaction failure on local qwen3.8-27b gateways served by NInfer — xhigh thinking burns the entire output token budget, so thinking is off for compaction-only, with the model's non-thinking sampling parameters; the same idea applies to other launch methods
DSH rules plugin: activate rule prompts / markdown documents by glob-matching the files an agent reads or edits (Claude Code rules.md style).
Shut down Windows after DeepSeek Harness tasks complete — draggable button, auto-dodge, cancellable countdown. 任务完成后自动关机(按钮可拖动、自动避让,倒计时可取消)。
DSH skill_manage: agent-managed procedural memory. Create/patch/edit/disable/delete skills in ~/.dsh/skills (user scope) or <projectRoot>/.dsh/skills (project scope), with validation, delete guards (agent-created marker, pin, path confinement), disable/enable via disable-model-invocation, and an English trigger-discipline system prompt section. Built on top of skill-filesystem's hot-reload watcher.
DeepSeek Harness plugin: a General-settings selector that chooses which language the model reasons in, via a system-prompt section.
网页复刻:从参考图/URL 提取字体、颜色、动画、组件结构,生成还原度高的网页项目。受 xuanxuan-prompts(169★)启发。
构图法则
脑机接口术语
算法耗时对比
dsh-docker — typed, guarded container control for DSH: structured docker/compose tools, project-aware targeting, an approval gate for destructive ops, service-health context, and a replayable status-table renderer
DSH web UI-tweak plugin: show the provider display name next to the model name in the composer model seat, remove the chat column max-width, and more — every feature has its own switch on a dedicated Settings page. / DSH web 界面美化插件:在模型选择器显示厂商名、取消对话列最大宽度等,每个功能都在独立的「设置 → 聊天增强」页中开关。
Give text-only models eyes: an analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible vision endpoint. 给纯文本模型装上眼睛。
Universal local vision bridge tool for DSH: describe/answer questions about images via any OpenAI-compatible local inference framework (llama.cpp / Ollama / LM Studio / vLLM), vision models auto-detected
DeepSeek Harness health and safety diagnostics for effective tool surfaces, approvals, and AgentFuse composition
Markdown folder long-term memory for DeepSeek Harness: one file per fact, an index line per memory, mounted into every request as a system prompt section
DeepSeek Harness plugin: OpenCode Go plan usage readout docked under the composer, aligned with the input bar width
Harness-native J-Space cognition preset with cache-stable scoped prompt control.
Prompt Vault & Invoker for DeepSeek Harness — 管理、分类、快速调用提示词,支持侧边栏 GUI
按 Anima3 v3.0 模板把中文场景转为英文提示词:槽位顺序/互斥检查/自检/标签库(读取本地模板文件)
A configurable DeepSeek Harness host plugin that silently appends route-specific system-prompt guidance for GPT and DeepSeek steps.
Windows-first vision suite for DeepSeek Harness.
deepseek-eyes:给 DeepSeek Harness 的纯文本模型装上眼睛——把粘贴的图片经 OpenAI 兼容视觉 API 转成文字描述,再转发给真实的文本模型(Give text-only models in DeepSeek Harness eyes: describe pasted images via an OpenAI-compatible vision API, then forward to the real provider. Not affiliated with DeepSeek.)