Agent skills for DeepSeek Harness

Build production-ready LLM applications, advanced RAG systems, and intelligent agents.

Equips AI coding agents with 23 specialized engineering roles, domain-specific guidance, and production-ready technical scripts.

6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent…

Design a Funhouse Mirror activity where students use their own domain expertise to detect AI distortions, omissions, and overconfidence.

Design AI-supported collaborative tasks that structure group interaction and address participation problems.

Design and implement an AI feature integration — model selection, architecture pattern, system prompt, data flow, error handling, cost…

Audit and redesign AI-generated feedback for pedagogical quality, timing, and learning impact.

Optimizes project structures and documentation to maximize AI collaboration efficiency and reduce token consumption.

This skill is part of a three-layer AI collaboration system: This skill helps design project architecture that maximizes AI collaboration…

Design a fact-checking protocol for AI-generated text, extending SIFT with AI-specific adaptations for hallucination detection.

Build a step-by-step path from a plain repository to a full agent-driven engineering workflow.

Analyzes multi-dimensional health data to identify patterns, predict medical risks, and generate personalized wellness recommendations.

Evaluates AI-generated images and text-to-image models across standard benchmarks, alignment metrics, and visual quality scores.

Guides users through an interactive, zero-code wizard to create custom batch image generation skills for any scenario.

Create an AI clone video (talking head) from a single reference photo, a text script, and a cloned voice.

Create AI influencer or branded character personas.

Standardizes the creation and maintenance of AI instruction files like CLAUDE.md and AGENTS.md to ensure consistent AI behavior across all…

Standardizes the creation and maintenance of AI instruction files like CLAUDE.md to optimize AI assistant behavior and development…

Run a private, evidence-based job-search system in Codex.

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous…

Generates and edits AI images and videos using structured prompt recipes, quality assurance checks, and standardized preview-ready…