Loading...
Loading...
Found 298 Skills
Automatic CSV Data Analysis and Insight Generation Tool
Automatically fetch YouTube video transcripts, generate structured summaries, and send full transcripts to messaging platforms. Detects YouTube URLs and provides metadata, key insights, and downloadable transcripts.
Paste in a DM or email thread where partnership terms were discussed and receive a clean bulleted summary of all agreed terms formatted to send back to the creator for confirmation. This skill should be used when summarizing a creator conversation into agreed terms, extracting deal points from a DM thread, turning an email negotiation into a confirmation message, documenting what was agreed with an influencer, cleaning up a messy negotiation thread into clear terms, converting informal creator discussions into a written agreement summary, pulling terms from a back-and-forth DM exchange, creating a confirmation recap from a creator call or chat, formalizing a verbal deal with a creator, or drafting a terms confirmation message to send after a negotiation. For writing the initial outreach messages, see creator-outreach-sequence-generator. For negotiation strategy and counter-offer language, see creator-negotiation-assistant.
Extract BUAA classroom replay artifacts from `livingroom` or `coursedetail` URLs by reusing a local Chromium login session. Use when Codex needs replay metadata, course-transcript files, optional PPT auxiliary artifacts, replay-ready lesson lists, or a standalone semantic rebuild packet / final lesson note.
Analyzes CSV files, generates summary stats, and plots quick visualizations using Python and pandas.
Format a final summary message for Linear. Your output is automatically streamed to the Linear agent session — just format it well, do not post it yourself.
Create sophisticated, Apple-inspired web interfaces with refined aesthetics and corporate elegance. Emphasizes generous whitespace, ultra-precise typography, asymmetric layouts, and purposeful interactions. Combines minimalist design philosophy with premium brand execution. Use when building premium landing pages, marketing sections, product showcases, or corporate interfaces that demand visual sophistication beyond standard business UI.
Build and run evaluators for AI/LLM applications using Phoenix.
Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, review experiments, and inspect datasets. Use when debugging AI/LLM applications, analyzing trace data, working with Phoenix observability, or investigating LLM performance issues.
Video understanding for any model — native passthrough for small files, frame extraction + audio transcription fallback for large files. Use when the user asks to analyze, describe, or understand a video file (e.g. "what's in this video", "summarize this clip", "transcribe this recording").
Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.