wellorbetter
User100% AI-native product delivery workflow plugin for DeepSeek Harness: full product-to-release pipeline (research → PRD → OpenSpec → parallel multi-agent → review loops → tests → release audit) with loop closure. 产品交付工作流插件:从产品到发布全流程,自带闭环,100% AI 原生,睡前启动醒来收货。
Categories
Indexed Skills (10)
product-delivery-workflow
Full product-to-release workflow for client applications. Use when the user asks for product research, competitor analysis, PRD, OpenSpec architecture, multi-agent implementation, swarm or parallel tasks, review loops, persistent learning, testing, or pre-GitHub privacy and release auditing.
agent-team
Multi-agent team and swarm workflow for DeepSeek Harness using bounded subagents, parallel workflows, disjoint ownership, and independent review.
architect-agent
Senior software architect that decomposes PRDs into components, boundaries, interfaces, data flow, contracts, and dependency-ordered implementation tasks without writing production code.
perf-reviewer-agent
Read-only performance reviewer for CPU, memory, latency, I/O, allocation, contention, binary size, and platform resource use against PRD budgets.
product-agent
Senior product manager that makes evidence-backed product decisions, writes PRDs with acceptance criteria and metrics, and validates delivery against the PRD.
release-audit-agent
Read-only pre-commit and pre-GitHub release audit for secrets, privacy leaks, unrelated changes, generated artifacts, dependencies, licenses, and release hygiene.
senior-dev-agent
Senior Rust developer that implements bounded tasks from architecture contracts, writes tests, handles errors explicitly, and preserves agreed interfaces.
test-agent
Focused automated testing and manual platform/device verification against architecture contracts and PRD acceptance criteria.
evolution-agent
Analyze completed workflows and propose measurable improvements to prompts, skills, task decomposition, retrieval, review gates, and token usage.
memory-curator
Curate safe cross-session project memory candidates from approved workflow evidence without storing secrets, transcripts, source dumps, or private data.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.