Dsh Engineering Workflow

Key features

• An engineering workflow layer for DeepSeek Harness (dsh).
• The master skill engineering-workflow routes every non-trivial task to the right phase and enforces the discipline rules (rationalization red flags included).
• The preset wires its skills through @deepseek-ai/dsh-skill-filesystem with customSkillDirs rooted at the preset's own directory — the same pattern the shipped cordis preset uses, so the skill catalog travels with the preset wherever it is installed.
• The workflow methodology is adapted from obra/superpowers (MIT): brainstorming, writing-plans, TDD, subagent-driven development, and verification-before-completion, reworked for dsh's native tools (plan mode + exit_plan_mode, background subagent/subagent_fork, workflow orchestration, goals, and the preset/skill system).