Use when installing, configuring, operating, or developing the local Career Agent Workbench application, including its public CLI, Flask tracker, FastMCP server, external private workspace, and offline validation surfaces.
Extract timestamped transcripts and top-liked public comments from YouTube URLs, then turn them into grounded summaries, key ideas, highlights, chapter timelines, comment excerpts, or notes. Use when a user pastes a YouTube, youtu.be, Shorts, embed, or live URL and asks what the video says, requests highlights or…
Write code in this user's personal style, using their codeprint profile (style rules + prior-code exemplars from the codeprint MCP server). Invoke with /codeprint-style when the user asks for code written the way they write it.
Compone música real con el servidor MCP sinfo — sinfonías, canciones, corales, beats — planeando la forma, escribiendo las voces, verificando armonía y conducción de voces, y exportando a MIDI, MusicXML, partitura SVG y audio WAV. Úsala SIEMPRE que aparezcan las herramientas scorecreate, partwrite, melodygenerate…
Drive the Tidy backup & sync tool from the terminal. Use whenever the user asks to back up, sync, schedule, push, pull, or manage their git-backed folders/repos (e.g. an Obsidian vault). Tidy is a git-based backup tool — each repo folder has one or more daily backup times, and every other goal is mapped to a tidy CLI…
Use RoASr from Hermes — audit Meta (Facebook/Instagram), Google Ads and Yandex Direct ad accounts for wasted budget, list AI audit findings ranked by money at stake, read Direct search queries and ad moderation status, spy on competitor ads from the Meta Ad Library, and get Vision analysis of ad creatives (hooks…
Audit an AI agent deployment against the CUSTODY containment framework and LASM threat model. Checks identity, input handling, supervision, traceability, operational controls, dependency management, and yield/teardown. Maps findings to NIST AI RMF, OWASP, CUSTODY pillars, and LASM layers.
Guide an incremental, evidence-aware discussion that turns an AI, product, model-strategy, competition, or implementation topic into durable personal cognition. Use when the user wants to discuss, learn, explore, compare, challenge, or deeply understand such a topic, including a recommended daily topic. Ask one…
Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; webfetch fails; the site has anti-bot protections; write Python code to…
Operate, administer, diagnose, or explain the local Linux Computer workspace and its MCP tools. Use for GUI/application automation, screenshots, pointer or keyboard actions, internal dwm tags and layouts, starting/stopping/showing/hiding the viewer, ownership takeover/release, moving live X11 windows into or out of…
Compare live grocery prices across Indian quick-commerce platforms (Blinkit, Zepto, BigBasket, Amazon Now) to find which is cheapest for a whole basket. Use when the user gives a shopping list, asks "where should I buy these", "which app is cheaper", "how much is X", "compare prices for my groceries", mentions…
Index and semantically search private local text, source code, documentation, and logs with the intel-npu-tools MCP server. Use when an agent needs meaning-based retrieval from a local project or document directory, needs to refresh an existing NPU index, or needs source-backed local context without uploading files.
Answer a question about a Minneapolis-St. Paul property or market from joined public records — what it sold for, who owns it, what shares its lot line, whether it carries a contamination file. Use when the subject is inside the seven-county metro and the answer should come from an administrative record rather than…
Combine the community-contributed Unofficial UWM Mortgage Reader's live read-only mortgage data with ChatGPT's built-in Finance integration. Use for mortgage reviews, cash-versus-principal decisions, payoff projections, or liquidity analysis that needs both sources.
A code-review workflow written in Chinese that checks software changes for correctness, security, performance, and maintainability. It also defines a report format for critical issues and suggestions.
Use when analyzing, auditing, reviewing or diagnosing a sales call transcript — find where the deal was lost, closer mistakes, objections missed, and a recovery line. Returns an evidence-backed QC 4.1 Light report with exact quotes, breakpoint minute, corrections, and a speakable recovery script. Works for high-ticket…
Use this skill when the user runs open source DataHub (self-hosted, not Acryl Cloud) and wants to write quality signals, not just read them: raise or resolve incidents on a dataset, or register external assertions with pass/fail results so they appear in the Validations tab. Triggers on: "raise incident on OSS"…
Read the screen and drive the desktop: accessibility tree, window targeting, screenshots, clicking, and typing. Use when a task needs a graphical application that has no command-line equivalent, or when the user asks to click, type into, or read something on screen.
A skill for researching short videos on Douyin and TikTok, including speech-to-text transcription and analysis of viral opening hooks. It ranks content by saves compared with likes, where saves indicate that viewers want to return to it.
★not rated 0 1mo agoA56 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: