Loading...
Loading...
Found 43 Skills
Knowledge graph memory orchestration - entity extraction, query parsing, deduplication, and cross-reference boosting. Use when designing memory orchestration.
Multi-source search and deduplication layer with intent-aware scoring. Integrates Brave Search (web_search), Exa, Tavily, and Grok to provide high-coverage, high-quality results. Automatically classifies query intent and adjusts search strategy, scoring weights, and result synthesis accordingly. Activated for "deep search", "multi-source search", or when high-quality research is needed.
Expert B2B list building orchestrator for outbound sales campaigns. Use when the user asks about building lead lists, Sales Navigator search, boolean filters, ICP definition, ICP scoring, lead sources, data validation, email verification, list segmentation, Apollo prospecting, Clay Find People, list hygiene, deduplication, account qualification, ABM lists, or assembling prospect lists for cold outreach. Also triggers on "lead list", "list building", "Sales Navigator", "boolean search", "ICP", "ideal customer profile", "find leads", "prospect list", "lead source", "email verification", "data validation", "list hygiene", "Evaboot", "PhantomBuster", "export leads", "build a list", "find prospects", "deduplicate", "qualify accounts", "ABM". Do NOT use for enrichment workflows (use clay skill) or email writing (use cold-email skill).
Save structured content to Obsidian vault with standardized frontmatter, folder routing, deduplication, and wikilink generation. Persists res-deep research, res-price-compare reports, and generic content. Use when: saving to vault, persisting results, store in obsidian. Triggers: save to vault, vault save, persist this, save research, store in vault, update vault note.
DEFAULT search tool for ALL search/lookup needs. Multi-source search and deduplication layer with intent-aware scoring. Integrates Brave Search (web_search), Exa, Tavily, and Grok to provide high-coverage, high-quality results. Automatically classifies query intent and adjusts search strategy, scoring weights, and result synthesis. Use for ANY query that requires web search — factual lookups, research, news, comparisons, resource finding, "what is X", status checks, etc. Do NOT use raw web_search directly; always route through this skill.
This skill provides guidance for merging data from multiple heterogeneous sources (JSON, CSV, Parquet, XML, etc.) into a unified dataset. Use this skill when tasks involve combining records from different file formats, applying field mappings, resolving conflicts based on priority rules, or generating merged outputs with conflict reports. Applicable to ETL pipelines, data consolidation, and record deduplication scenarios.
Configure Prometheus Alertmanager with routing trees, receivers (Slack, PagerDuty, email), inhibition rules, silences, and notification templates for actionable incident alerting. Use when implementing proactive monitoring with automated incident detection, routing alerts to the appropriate team by severity, reducing alert fatigue through grouping and deduplication, integrating with on-call systems like PagerDuty, or migrating from legacy alerting to Prometheus-based alerting.
Set up @personize/signal — a smart notification engine that decides IF, WHAT, WHEN, and HOW to notify each person using Personize memory and governance. Guides you through connecting event sources, configuring delivery channels, setting up governance rules, and testing the decision engine. Use this skill whenever the user wants to build smart notifications, AI-powered alerts, notification fatigue prevention, daily/weekly digests, personalized messaging, or intelligent notification routing. Also trigger when they mention @personize/signal, notification scoring, quiet hours, deduplication, channel routing (email vs Slack vs in-app vs SMS), or want notifications that know when to stay silent.
Parse, analyze, and process SARIF (Static Analysis Results Interchange Format) files. Use when reading security scan results, aggregating findings from multiple tools, deduplicating alerts, extracting specific vulnerabilities, or integrating SARIF data into CI/CD pipelines.
Combines search results from multiple sources into coherent, deduplicated answers with source attribution. Handles confidence scoring based on freshness and authority, and summarizes large result sets effectively.
Track all identified/contacted people across strategies. CSV-backed contact database with dedup by LinkedIn URL or email. Prevents duplicate outreach when running strategies on a recurring cadence.
Run Codex, Claude Code, and Gemini CLI reviews against the current branch concurrently, deduplicate the findings, and report only the review comments that are still valid for the current codebase.