dsh-cursor-settings
DSH web plugin: Cursor-like Settings pages (AGENTS.md Rules, Skills, MCP servers, import) plus a pinned 'latest input' chat bar with a backward walk
569 results
DSH web plugin: Cursor-like Settings pages (AGENTS.md Rules, Skills, MCP servers, import) plus a pinned 'latest input' chat bar with a backward walk
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)
DeepSeek Harness plugin: Lord/Serf agent protocol 0.5 skills (file-based multi-agent orchestration with bounded execution and schema-validated submissions)
User-approved Goal, Milestone, and Turn checkpoints for solo long-running DeepSeek Harness projects.
Plug-in vision for text-only LLMs — a DeepSeek Harness (dsh) fork of ModLens adding multi-engine support (Gemini, Volcengine Ark/Doubao, Claude) and per-call engine selection
让 DeepSeek Harness 打开工作区时自动载入 Claude Code 配置:Skills/Rules/Hooks/Agents 四样资产,固定双位置(工作区自身 .claude + ~/.claude)运行时直读、零写入。Claude Code 兼容层。
Plugin tools provider for DeepSeek Harness: install plugin/skill development tools (expert2skill, skill-compliance, dependency-scan) via ctx.skills from a line catalog.
DSH bundle: manage user-level skills from Settings — list all skills with enable/disable switches (disabled skills are excluded from model catalogs)
HarmonyOS NEXT / ArkTS development skills for DeepSeek Harness — ArkTS/ArkUI coding knowledge and ArkTS code review.
DeepSeek Harness Doctor: read-only DSH runtime capability diagnostics for tools, models, skills, workspaces, sessions, plugins, and MCP troubleshooting
LVGL 8.4 knowledge skill pack for DeepSeek Harness (dsh): registers an offline LVGL 8.4 skill library on ctx.skills so the agent writes correct v8 API code and avoids v9 confusion.
基于抖音官方资料的 DeepSeek Harness 自媒体创作与运营插件
DSH arch-doc skill plugin: analyze a codebase and generate architecture documentation (module responsibilities, dependencies, entry points and run methods).
浏览器测试与 UI 验证:用真实浏览器验证 DOM/控制台/网络/性能,替代猜测。受 addyosmani/agent-skills(88k★ MIT)启发。
CI/CD 自动化:质量门禁、shift-left、构建部署管线、发布策略。受 addyosmani/agent-skills(88k★ MIT)启发。
云 Well-Architected 六支柱评审框架:可靠性(用户经验目标/SLO/冗余/水平扩展/可观测性/优雅降级/恢复测试/无指责复盘)、成本优化、运维卓越、性能优化、安全、可持续性——设计原则+建议驱动架构评估与改进。受 google/skills(18.5k★ Apache-2.0)启发。
AI coding delivery trust layer for governance-aware coding agents — zcode plugin packaging. The plugin surface lives in skills/ and commands/; this file only provides the npm package identity expected by the zcode plugin host.
Claude Code compatibility layer for DeepSeek Harness: load .claude skills/commands/agents and install plugins from Claude Code marketplaces as native dsh skills.
Vision-first MCP for text-only Agents, using Agnes AI for image understanding with experimental generation and editing.
pushplus 消息推送:通过 pushplus API 向微信发送通知。当用户要求推送消息、发送通知、任务完成后汇报结果时,自动使用此 skill 调用 scripts/pushplus.py 推送消息到用户微信。
文档预编译成可执行技能:把官方文档(API 模式/配置流程/最佳实践/约束/故障排查决策树/安全合规)预编译为结构化可执行技能,而非每次 RAG 检索——提取→分类→按用户意图按需揭示。受 MicrosoftDocs/Agent-Skills(Azure Agent Skills)启发。
June dual-persona agents (June-M / June-S) for DeepSeek Harness: a dsh bundle that installs the june-m and june-s agent presets plus the git-backup and june-style skills.
Skill bundles for DeepSeek Harness: a bundle box holds a root skill and sub-skills, loaded by metadata (loadSubskills) or by model decision from body text.
Deep Design — design mode for DeepSeek Harness: the design-loop agent preset plus design-principles and design-qa skill packs