dsh-xray
X-ray for your DeepSeek Harness — diagnostics for what's actually loaded, why, and what it costs: per-plugin context-tax attribution, per-request token ledger, skill catalog pricing, dependency cascades.
99 results
X-ray for your DeepSeek Harness — diagnostics for what's actually loaded, why, and what it costs: per-plugin context-tax attribution, per-request token ledger, skill catalog pricing, dependency cascades.
Content-aware tool output compression for DeepSeek Harness.
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。
Cut MCP context and API cost in DeepSeek Harness with two model-facing tools, lazy discovery, and exact-schema calls
Evidence-backed working memory for DeepSeek Harness: a cited ledger of what already worked in this workspace, built from the session log you already have
AI提示词优化器:诊断Prompt问题并输出结构化、高质量的优化版本
DeepSeek Harness 插件:Matt Pocock 工程技能包——grilling、spec/ticket 流程、TDD、code review、domain modeling 等工程技能(移植自 mattpocock/skills)
DSH (DeepSeek Harness) scaffold plugin & preset: strict 5-phase init runbook, engineering standards, and six runnable starter templates (node-ts / react-vite / python / go / spring-boot / monorepo). 项目初始化脚手架预设:严格流程 + 工程规范 + 六套模板。
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。
上下文工程:按层级(规则文件→规格→源码→错误输出→对话历史)主动策划 agent 看到的信息,提升输出质量。受 addyosmani/agent-skills(88k★ MIT)启发。
Engineering-discipline skill pack for DeepSeek Harness — code review, simplification, plan-then-execute, test-first, and conflict resolution, delivered as a bundled skill provider plugin.
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。
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
SSH-friendly interactive terminal TUI plugin for DeepSeek Harness
A DSH (DeepSeek Harness) bundle plugin that rewrites the ask_user_question tool description at prompt-assembly time with a fixed narrative-voice rule (default: the answerer narrates), toggled live via the /voice command.
Task boundaries for DeepSeek Harness Web: use Focus for execution scope and Persistent Anchors for explicit constraints without rewriting prompts.
Out-of-tree DeepSeek Harness bundle: an executable implementation of the Harness Engineering Methodology (HARNESS-METHODOLOGY-SPEC v1.0) — agent-discipline prompt section + artifact scaffolding tool + compliance audit tool.
开源的 Prompt 构建与增强工具包:方法工坊(Studio)+ 对话快捷增强器(QuickEnhancer)。内置 22 个 Markdown 思考方法(含技术开发/数据分析等场景卡 + frontmatter + prompt 正文),可作为 npm 库嵌入,也可直接安装为 DSH 浏览器插件。
A conservative intent compiler for Vibe Coders in DeepSeek Harness: clarify messy drafts without inventing details, then fill the result back into the composer.
NovelAI Diffusion V4.5 Full image generation for DeepSeek Harness: text-to-image, Danbooru tag lookup, and image-to-prompt reverse engineering.
An approval-gated OME engineering delivery agent preset for DeepSeek Harness
DSH 上下文管理插件:任务边界、项目帧、自动判别与上下文优化(开发中,R2 判别域 P8–P14b1 已施工)
CodeBuddy (copilot.tencent.com) provider bundle for DeepSeek Harness (dsh): 18 models (DeepSeek, GLM, Kimi, MiniMax, Hunyuan, auto) with adjustable reasoning efforts, CodeBuddy web search / web fetch backends for the stock dsh tools, and a settings card in the Web UI.
Tiered micro-clear layer for DeepSeek Harness compaction: clears whitelisted re-runnable tool results to placeholders before the official summarization tier, freeing context with no model call.