AI Agent Skills

ONLY use when user explicitly says 'deep research', 'exhaustive', 'comprehensive report', or 'thorough investigation'. Slower and more expensive than parallel-web-search…

Use when a task involves continuing a project, restoring project context, maintaining file-based project memory, updating current-state summaries, or recording meaningfu…

DyNote: systematically and efficiently extract raw Douyin/DY video data and analyze videos, comments, accounts, hashtags, and short-video scenes into evidence-graded lea…

Translate text content between languages with high quality and natural phrasing. Covers document translation, content localization, and multi-language research support f…

Parse and extract structured content from PDFs, Word documents, and other file formats. Converts documents into clean, machine-readable text for analysis, summarization,…

compilable markdown for linear algebra

Pre-implementation planning — interview to clarify scope, then compile into a PRD. Triggers "help me figure out", "vague scope", "define requirements" (discovery phase);…

Merge implemented spec deltas into the permanent specs library and archive the plan. Use when implementation is verified — after /speq-implement produces verification-re…

Deep-research methodology with a ROLE-BASED team of parallel sub-agents. One `delegate_task` batch dispatches 2–3 researchers (each on a distinct sub-question), 1 critic…

Use to import, prepare, read, or synthesize a complete supported book in verified source order. Skip ordinary document lookup.

THE reference manager with features including PDF reading/annotating, Markdown/Excalidraw note-taking, project/note linking, and more...

A bidirectional LSTM with attention for multiclass/multilabel text classification.

Weekly clinical-trial status diff — the 11-category change report over the stored weekly snapshots (spec 055 FR-B03). Surfaces exactly what changed on the trial registry…

Use when the user wants to deeply learn a new topic from scratch. Runs a pre-interview (current knowledge, end-goal proficiency, depth, practice load, background, scope)…

Run browser-grounded, read-only social research through Jev Social when a user wants posts, profiles, comments, video evidence, or a source-linked report from Instagram,…

Vector search demo with the arXiv paper dataset, RedisVL, HuggingFace, OpenAI, Cohere, FastAPI, React, and Redis.