dsh-requirements-alignment
Runtime requirement drift guard for DeepSeek Harness — keeps long-running agents aligned with user intent while they work.
20 results
Runtime requirement drift guard for DeepSeek Harness — keeps long-running agents aligned with user intent while they work.
dsh-qa QA Workbench: a local software testing workbench plugin for DeepSeek Harness. Project/iteration dual-mode, full-flow requirements / test cases / defects / milestones / reports, native QA preset, themes, kanban and calendar.
Delivery quality gate for DeepSeek Harness: grill the requirements, test the implementation, prove the delivery, and gate the handoff with a deliverable/rework decision.
Workflow skill pack for DeepSeek Harness: requirement grilling, specs, implementation, delivery review, repair planning, bug diagnosis, and source-backed research.
Engineering workflow layer for DeepSeek Harness (dsh): a disciplined-engineer agent preset with five gated phases — requirements clarification, plan approval, TDD implementation, parallel subagent execution, and verified finishing. Skills adapted from the obra/superpowers workflow methodology.
A green interrupt button beside the DeepSeek Harness send box: silently stops a running agent, which then summarizes its progress and asks for your new requirements; the interrupt prompt is customizable.
AI-assisted requirement clarification and Git-backed Spec co-creation for DeepSeek Harness, ending at a human-confirmed Ready Spec.
Native DeepSeek conversation capture, requirement analysis, and DSH Desktop handoff.
Plugin insight center — one answer to '哪些值得装': requirement matching (plugin_guide), environment recipes (recipe), health scoring (plugin_rank), static security scanning (plugin_audit), and a single install verdict (plugin_verdict)
DSH 插件:春笋(ChunSun)驱动的 AI 原生项目交付 —— 需求/Run/Step/场景/用例/工作记忆 + 验收闭环(pm = project management)
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。
Pure-incremental directive-driven compaction for DeepSeek Harness: /compact-directive <requirement> summarizes the session middle per your requirement, /trim-directive <requirement> trims the whole conversation per your requirement
DSH web plugin: a task kanban that refines requirements into phased plans, auto-executes them in git worktrees (one session per phase), and auto-merges into the main branch on completion.
Requirement-driven dsh plugin discovery and environment recipes ('点菜, not 逛超市' / 插件界的 dotfiles): plugin_guide matches natural-language needs to a curated directory; recipe installs whole environments from bundled community bundles with ordered plans
Local project, requirement-group, and conversation workbench for DeepSeek Harness Web and Desktop
Spec-Driven Development 三件套技能(Spec New / Spec Implement / Spec Validate)DSH 组合包:把模糊 Idea 收敛成 specs/ 三件套,按规格有序实现,并对照验收标准验收。
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。
Visual web settings panel for the official @tencent-connect/dsh-qqbot plugin: manage the QQ Bot AppID/AppSecret, c2c & group access modes/allowlists, cwd and requireMention directly in the DSH web settings page (reads/writes the qqbot profile's cordis.patch.yml).
RPA-style scheduled web automation for DeepSeek Harness: record browser operations, turn them into a requirements doc, let the LLM generate Python + Playwright code, then schedule execution with run records and email notifications.
User-set session/global must-do and must-not requirements injected at conversation start (Baize).