Verify citations and factual claims in long-form content. Checks URLs for accessibility and accuracy, validates quotes, analyzes source credibility, and distinguishes facts from opinions. Use when fact-checking article drafts, validating citations, or reviewing claims before publication.
Journalism source verification and fact-checking workflows. Use when verifying claims, checking source credibility, investigating social media accounts, reverse image searching, or building verification trails. Essential for reporters, fact-checkers, and researchers working with unverified information.
Analyze Twitter/X threads to extract insights from viral and educational content. Use when the user mentions Twitter, X, thread, tweets, viral thread, or provides a twitter.com or x.com URL.
Fetch and analyze Readwise reading activity for any date range. Use when user asks about articles saved, highlights created, or most-highlighted content for today, yesterday, last week, last month, or custom date ranges (e.g., "show my Readwise activity from Jan 1-7"). Requires READWISE_API_TOKEN env var. Connects to Readwise Highlights API (v2) and Reader API (v3).
Analyze Hacker News posts and discussions to extract insights from tech community discourse. Use when the user mentions Hacker News, HN, news.ycombinator, YC, or provides a HN URL.
TMDB (The Movie Database) API integration for React Native TV streaming apps. Use when users need help with movie/TV show data, poster images, search functionality, trending content, video trailers from TMDB, API authentication, rate limiting, or TypeScript types for TMDB responses.
Analyse rhétorique et épistémologique d'articles, discours et textes argumentatifs. Utiliser ce skill quand l'utilisateur demande d'analyser la qualité argumentative d'un texte, d'identifier des sophismes ou biais, d'évaluer la fiabilité des sources citées, de déconstruire la logique d'un raisonnement, ou de produire une réécriture critique structurée d'un document.
Advanced prior art search using the PatentsView API. Use this skill when users need to search for patents, perform prior art searches, analyze patent landscapes, or find patents by inventor, title, date range, or technical fields. Helps with patent research, freedom to operate analysis, and competitive intelligence.
Create bibliography citations from web page URLs with automatic Wayback Machine archival and metadata extraction. Use when the user asks to cite a website, create a citation for a URL, archive and cite a web page, or generate a bibliography entry from a web address.
Academic research synthesis, paper analysis, and comprehensive literature reviews across disciplines
Enhance author profiles by filling missing fields. Use when asked to "enhance author", "complete author profile", "find author info", or "update author details". Fills bio, avatar, website, and social links via parallel web research.
Signal detrending for baseline correction and trend removal
Meteorologist providing weather data via Open-Meteo API (FREE).
Ground station subproject context. Use when working in the ground_station package, telemetry reception, mission control interface, or real-time flight monitoring.
Width-based responsive image patterns for Astro. Local processing, AVIF/WebP/JPG, face-focus, OG generation. Includes Picture and FixedImage components.
Progress reporting for universe selection phases. Trigger when: (1) selection appears to stall/hang, (2) no output after data fetching, (3) need visibility into hard filter or scoring phases.
KINTSUGI deconvolution: True lightsheet PSF calculation to fix horizontal banding artifacts. Trigger: deconvolution artifacts, horizontal banding, PSF issues, fcyl, slitwidth, lightsheet, LsDeconv.
SNAKE vs RASTER tile acquisition patterns for image stitching in KINTSUGI
KINTSUGI deconvolution: Output scaling must preserve original intensity relationships for quantitative analysis. Trigger: deconvolution saturates at 65535, channel intensity ratios inverted, hist_clip scaling issues.
Parallel processing for universe selection with 3-4x speedup. Trigger when: (1) selection takes too long, (2) 'No data returned' warnings for cached symbols, (3) need to process 100+ candidates.
