Agent skills for DeepSeek Harness

Audits DDD aggregate design rules. Checks single transaction boundary, identity by root, invariant enforcement, small aggregates, and…

Orchestrates a rigorous three-round debate between three AI personas to reach a reasoned consensus on complex topics.

Agile product ownership toolkit for Senior Product Owner including INVEST-compliant user story generation, sprint planning, backlog…

Analyzes sprint retrospective data to identify recurring themes, sentiment trends, and track action item effectiveness.

Master Agile SDLC orchestration engine for autonomous software engineering.

Automate Agiled tasks via Rube MCP (Composio).

Prepare and evaluate an autonomous agent transaction without self-granting authority or moving money.

Content quality and E-E-A-T analysis with AI citation readiness assessment, plus last-mile draft cleanup (AI-typical phrasing and…

Streamlines the manuscript preparation and submission process for the Journal of Agrotechnical Economics (《农业技术经济》).

Verifies academic bibliography metadata field-by-field against authoritative databases to eliminate citation hallucinations.

Create, update, inspect, or repair Data Analytics semantic layers.

Narrow conversion skill. Invoke only when the user explicitly asks to convert an existing local or blob-hosted HTML analytics report into…

Use when doing ANY task involving Supabase.

Core Data for iOS persistence. Data models, fetch requests, background contexts, and SwiftData migration.

防止 AI 幻覺，確保分析程式碼或提出建議時給出以證據為基礎的回應。 Use when: 分析程式碼、提出建議、提供選項，或使用者詢問把握度／確定性時。 Not for: 撰寫 AI 指令檔本身——請用 /ai-instruction-standards；審查具體的…

Synchronizes educational curriculum and lesson materials safely from upstream repositories to keep learning content up to date.

Automates the delegation of code reviews to specialized AI sub-agents to identify bugs and architectural flaws before merging.

Prevent AI hallucination and ensure evidence-based responses when analyzing code or making suggestions.

Explain an AI or LLM concept at the depth the person actually needs — working definition, the mechanism, where it breaks, and the decision…

Checks whether AI crawlers and answer-time fetchers can actually retrieve the site: robots.txt directives per named agent, CDN, WAF and…

Synchronizes project configuration files across Agents.md, claude.md, and gemini.md to ensure consistent AI behavior and instructions.