79 skills · sorted by relevance
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.
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.
Build AI data deduplication systems. TRIGGERS - Use when user needs help with ai-deduplication related tasks.
The English summary is being prepared. Showing the original description.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
The English summary is being prepared. Showing the original description.
Build AI data deduplication systems. TRIGGERS - Use when user needs help with ai-deduplication related tasks.
The English summary is being prepared. Showing the original description.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
The English summary is being prepared. Showing the original description.
Find prospects by role, industry, company size, and location, then add approved contacts to an Apollo sequence, a series of outreach emails. The workflow enriches details, creates contacts with deduplication, and reports enrollment results.
Convert Snowflake dbt SQL models to BigQuery through a bulk migration workflow. Preserve Jinja template logic while adapting configuration, explicit type conversions, JSON access, and deduplication patterns, with translated files saved in their directory structure.
Audit server-side advertising measurement by comparing browser and server events, checking duplicate handling, consent, and data quality. Reconcile platform diagnostics with source logs and business conversions, then return prioritized findings, owners, and verification steps.
Audit server-side paid-media measurement including server-side tag management, platform conversion APIs, event taxonomy, browser/server deduplication, consent, hashing, data quality, observability, and privacy. Use for server-side tracking, sGTM, server-side tagging, Meta CAPI, TikTok Events API, event_id, deduplication, pixel debugging, first-party measurement, or conversion data loss.
The English summary is being prepared. Showing the original description.
Deploy DefectDojo as a centralized vulnerability management dashboard with scanner integrations, deduplication, metrics tracking, and Jira ticketing workflows.
The English summary is being prepared. Showing the original description.
Create an Estuary derivation with custom SQLite state (internal tables) to make per-document decisions based on accumulated history — account balances, inventory levels, approval workflows, deduplication. Derivations add complexity and cost — confirm the user wants a derivation before reaching for this. Use when user says "stateful derivation", "derivation to track balance", "transformation to approve based on state", "derive an approval workflow", "deduplication derivation", or "build a stateful derivation".
The English summary is being prepared. Showing the original description.
Deploy DefectDojo as a centralized vulnerability management dashboard with scanner integrations, deduplication, metrics tracking, and Jira ticketing workflows.
The English summary is being prepared. Showing the original description.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
The English summary is being prepared. Showing the original description.
Deploy DefectDojo as a centralized vulnerability management dashboard with scanner integrations, deduplication, metrics tracking, and Jira ticketing workflows.
The English summary is being prepared. Showing the original description.
Design a shared notification workflow across GitHub, Linear, local hooks, desktop alerts, and existing communication tools. Classify urgency and ownership, merge duplicate events, and decide which updates need immediate attention, a digest, or a log entry.
Organize parallel code reviews across security, performance, architecture, testing, and accessibility. It helps assign review areas, merge duplicate findings, apply consistent severity ratings, and produce one report with locations, impacts, suggested fixes, and prioritized actions.
Build a central vulnerability dashboard with DefectDojo to combine scanner findings, remove duplicates, and track remediation. Includes Docker deployment, automated scan imports from CI/CD pipelines, Jira ticket integration, and API queries for reporting metrics.
Research prospective customers from public sources, add company and contact details, score their fit, and merge duplicate records. Organize the findings into prioritized lead lists with source information, using CSV, JSON, or Markdown tables.
Turn rough meeting notes, customer requests, and product ideas into structured backlog entries, a list of possible improvements. Capture who needs each idea and why, categorize it, and update matching entries with new evidence.
Process SARIF files, a standard format for static analysis results, to filter alerts, remove duplicates, combine findings from multiple tools, and produce reports. It also supports comparing runs and integrating result checks into CI/CD pipelines.
Add, extend, or review OpenAI Ads conversion tracking for purchases, signups, and other confirmed outcomes. The skill covers browser Pixel events, server-side Conversions API events, duplicate-event prevention, secret handling, and local verification with a setup report.
Paper Retrieval Agent - Multi-database paper fetching from Semantic Scholar, OpenAlex, arXiv Handles rate limiting, deduplication, and PDF URL extraction Use when: fetching papers, searching databases, paper retrieval Triggers: fetch papers, retrieve papers, database search, Semantic Scholar, OpenAlex, arXiv
The English summary is being prepared. Showing the original description.
Smart backward and forward citation following via Semantic Scholar, with relevance filtering and deduplication
The English summary is being prepared. Showing the original description.