Agent skills for DeepSeek Harness

Academic literature orientation skill that searches papers via free keyless APIs (PubMed E-utilities + OpenAlex) by default — with the…

Reorganize the user's X and LinkedIn network with review-first pruning, add/follow recommendations, and channel-specific warm outreach…

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns.

X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics.

Create refreshable, auditable OpenDesign artifacts backed by connector or local data.

Methodology for evaluating the live product via a real browser (Playwright MCP) when planning work or evaluating a PRD.

Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract…

Build a real-time support chat system with a floating widget for users and an admin dashboard for support staff.

Report the embedded release marker when testing public Skill installation or marketplace updates.

Inspect LiveView socket assigns for memory bloat — missing temporary_assigns, unused assigns, unbounded lists needing streams, memory…

Use for Livewire performance work. Covers what one Livewire request actually costs, the snapshot that travels both ways on every request…

Maintains an implementation-agnostic, behavior-first functional blueprint to guide AI-driven refactoring and long-term project evolution.

Develop and contribute to the PinchTab project.

Deconstructs academic papers into simplified summaries and visualizes cognitive insights using ASCII art and personal knowledge baselines.

Converts structured outlines into high-impact, slogan-style HTML presentations with ultra-bold typography and minimalist aesthetics.

Transforms complex articles, papers, and books into sharp, logical Q&A chains that reveal an author's core argument skeleton.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons…

Use when ANY runtime debugging is needed — setting breakpoints, inspecting variables, evaluating expressions, analyzing threads, or…

LLM-based text classification: codebook, validation, agreement statistics.

LLM-based zero-shot and few-shot classification for flexible intent detection