269 skills · sorted by relevance
Find, inspect, summarize, and update documents, spreadsheets, and presentations across Google Drive, Docs, Sheets, and Slides. Consolidate plans and trackers, clean shared files, and identify duplicates or outdated materials within a connected workflow.
Manage GitHub repository operations with the gh command-line tool. Classify issues, check pull request readiness, investigate failed automated checks, prepare releases and changelogs, and review dependency or exposed-secret security alerts.
Monitor prices and availability for specific products, flights, hotels, or listings. Compare totals including required fees against chosen conditions, account for variants and refund terms, and send alerts while suppressing duplicates.
Turn meeting notes or transcripts into sourced decisions and action items with owners and deadlines. Check existing tasks for duplicates, then draft minutes, tickets, and follow-up messages while keeping missing details and unresolved conflicts visible.
Read email linked to assigned Paperclip tasks, send new messages or replies through an assigned AgentMail inbox, and check delivery outcomes. Follow task permissions and preserve retry identifiers to avoid duplicate sends.
Select random winners from lists, CSV files, Excel, or Google Sheets. Choose multiple winners without duplicates, exclude previous winners, apply entry-based weighting, and record the selection method and timestamp for review.
Plan and coordinate Strix security assessments across source code, running applications, APIs, and continuous integration pipelines. Combine findings into one prioritized remediation plan based on demonstrated impact, removing duplicates and documenting gaps in test coverage.
Update existing ChatGPT Pages or a Space using new meetings and source material. The skill reconciles plans, tasks, and reference information, combines duplicates, preserves human edits and dated records, and reports changes and coverage gaps.
Maintain a private task list with deadlines, next steps, waiting parties, and blockers. Update progress and dependencies, merge duplicate items, and archive closed tasks so ongoing commitments stay clear and easy to follow.
Search multiple job portals for new roles matching a candidate’s profile, remove previously seen or applied listings, and present a table ordered by fit with deadlines, requirements, and LinkedIn search links for potential contacts.
Create integration tests for syncable metadata entities in Twenty itself. Cover invalid inputs, validation errors, and successful data operations, using reusable GraphQL request helpers, error snapshots, and cleanup routines to organize the test suite.
Plan and audit HypoGeniC workflows that use language models to propose patterns from labeled text. Check configurations, dataset splits, cost limits, and saved predictions while keeping candidate hypotheses separate from scientific confirmation.
Find academic papers, verify authors and publication details, and create BibTeX entries, a structured format for references. Use it to organize bibliographies, remove duplicates, and check missing fields or mismatches with a manuscript.
Screen study titles, abstracts, and full texts against confirmed eligibility rules. Two AI reviewers assess records separately, with a third resolving conflicts, while outputs document exclusion reasons, selection counts, and the methods used.
Prepare and submit bug reports or feature requests to GitHub, checking for duplicates and following issue templates. Reports are previewed for approval before submission, or saved locally when GitHub authentication is unavailable.
Collects resolved questions and practical solutions in a project FAQ, checking for duplicates before adding or updating entries. It also searches saved keywords when new questions arrive, so relevant answers can be reused.
Capture unexpected behavior and workarounds encountered while using Prisma 8, Prisma Compute, or Prisma Postgres. Record symptoms, causes, versions, and reproduction steps in a local log linked to a Linear ticket, checking for duplicates first.
Turn Codewhale bugs and feature ideas into GitHub issues. Gather reproduction details, check for duplicates, and present the exact draft for approval before submitting it and returning the issue link.
Compare specification requirements with the codebase and create GitHub issues for unmet requirements. Check existing issues for duplicates, then include requirement IDs, implementation guidance, context, and acceptance criteria in each new issue.
Build automated pipelines that collect threat indicators, such as malicious IP addresses and file hashes, from multiple feeds. Standardize formats, remove duplicates, assess confidence, and distribute indicators to security monitoring systems for matching and alerts.
Set up a local web search server using Bright Data SERP API and unfancy-search. Retrieve results from multiple engines, optionally expand queries with AI, and receive combined rankings with duplicates removed and results grouped by domain.
Prepare training datasets for large language models with GPU-assisted cleaning. Covers duplicate removal, quality filtering, and personal information redaction, with workflows for text, images, video, and audio using NeMo Curator.
Organize scattered concept notes into a map of recurring ideas. Merge duplicates, rank concepts into four tiers, trace how stronger ideas developed across sources, and assess which notes to keep, rewrite, merge, or remove.
Extract figures and fields from emails, websites, and APIs into source-linked tracking tables. Configurable recipes guide collection, preserve original material, and check duplicates for records such as investor updates, expenses, and company metrics.