179 skills · sorted by relevance
Research recent X posts by narrowing dates, trusted accounts, and keywords. Compare posts with web search results, link to the original posts, and distinguish reported reactions from claims that lack independent confirmation.
Plan subtitles as layers over a video, deciding which spoken phrases to omit, show normally, or emphasize behind the subject. The guidance preserves full-frame composition and limits large embedded words to occasional key moments.
Prepare experiments for Ginkgo Cloud Lab by choosing a protocol, organizing required inputs, checking configured pricing, and navigating browser ordering. Covers protein expression, RNA synthesis, stability assays, and setup of measurement methods.
Bring together public reviews, complaints, and customer activity to identify recurring issues and customers who may leave. Produce evidence-backed themes, review reply drafts in the owner's voice, and personalized messages to win back inactive customers.
Analyze competitors using deal outcomes, customer quotes, and public developments. Prepare tactics for a specific deal, battlecards—sales reference sheets for each competitor—and weekly updates that distinguish evidence from interpretation.
Turn interviews, surveys, usability notes, and customer feedback into shared themes, user groups, and prioritized recommendations. Findings include supporting quotes and participant counts, helping teams connect research evidence to concrete product improvements.
Turn exported AI chats and agent session logs into dated, searchable pages in gbrain. Check for missing conversations, extract facts, and trace when a topic first appeared or how an idea developed, with quotes and dated references.
Turn meeting transcripts into structured GBrain pages with decisions, assigned tasks, and verified quotes. Resolve speakers using evidence, split recordings containing separate meetings, and update related people and companies with links and dated meeting context.
Connect Gmail, Calendar, and Contacts to track people awaiting replies and promises still outstanding. Get a prioritized digest with supporting quotes, email links, deadlines when available, and background context to help prepare a response.
Checks factual claims in articles and reports against current sources or independently queried original data. Applies corrections, assigns one of six confidence levels to each claim, and produces a sourced report with an overall pass or fail assessment.
Check YAML frontmatter, the metadata at the top of knowledge pages, for formatting and identity errors. Explain why gbrain holds files during sync, preview proposed changes, and repair supported problems after approval.
Find YouTube videos, retrieve caption transcripts, browse channels, and list playlist contents through TranscriptAPI. Use the results to summarize videos, extract quotes, check new uploads, or build a searchable collection of transcript documents.
Analyze meeting transcripts to understand speaking share, verbal habits, listening, and facilitation. Receive feedback grounded in specific quotes, practical suggestions for future meetings, and comparisons across periods when enough meeting data is available.
Turn interviews, surveys, usability notes, and customer feedback into shared themes, user groups, and prioritized recommendations. Findings include supporting quotes and participant counts, helping teams connect research evidence to concrete product improvements.
Turn supplied text or data into an X-style post card for video overlays or image sharing. Create a single HTML file with profile details, engagement counts, and light or dark styling in landscape or square formats.
Analyze individual stocks using current quotes and historical price data. Calculate trend and momentum measures, identify price gaps and potential support or resistance levels, and produce a three-day outlook with trading scenarios and risk notes.
Work around file-writing errors caused by quotes, backticks, or JavaScript template literals using a temporary Python script. The workflow includes reading back each saved file to check its contents and removing the helper script afterward.
Work around file-writing failures involving quotes, backticks, or template literals by using a Python helper script. Then run TypeScript directly through Node.js and filter diagnostic output to focus on errors reported in newly written files.
Build serverless endpoints that relay external API requests for a dashboard while keeping API keys on the server. Includes Vercel examples for input checks, caching, cross-origin access, and consistent JSON responses.
Build dashboard panels in vanilla TypeScript with resizing, saved layout state, loading indicators, and retry controls. Examples also show how to wrap existing data-fetching functions with caching and temporary request pauses after repeated failures.
Build dashboard panels in vanilla TypeScript with shared loading and error displays, saved panel state, and request handling. Examples show retries with increasing delays and CircuitBreaker integration to pause repeated failures and reuse cached results.
Run multiline Python code by saving it to a script file before executing it through the shell. The workflow covers working directories, timeouts, error checks, and optional cleanup to make execution easier to debug.
Analyze public reviews, app stores, and forums to identify unmet customer needs, competitor weaknesses, and reasons for switching products. Receive short customer quotes with source links, recurring themes, and hypotheses to validate in interviews.
Build a company research brief from public sources, covering executive statements, product strategy, organizational practices, and transformation initiatives. Use dated sources to prepare for interviews, understand competitors, assess potential partners, or explore market entry.