Loading...
Loading...
Found 5,542 Skills
Process raw source documents into wiki pages. Use when the user adds files to raw/ and wants them ingested, says "process this source", "ingest this article", "I added something to raw/", or wants to incorporate new material into their wiki, second brain, or knowledge base.
Text analytics using LLM APIs — sentiment analysis, customer feedback classification, document entity extraction, multi-language support (English/Luganda/Swahili), feedback aggregation, and NLP feature implementation for PHP/Android/iOS. Sources...
Transform one piece of long-form content into 10 platform-ready assets using AI tools. Solves the content creation bottleneck for resource-constrained East African marketing teams. Invoke when a client needs more content output from their existing content investment.
Runs the Metabase semantic checker against a tree of Representation Format YAML files to verify that all references resolve — cross-entity references (collection_id, dashboard_id, parent_id, parameter source cards, snippet references, transform tags, etc.) and references to columns inside MBQL and native queries. Use when the user asks to "semantic check", "check references", "validate queries against the schema", or diagnose a broken reference. Requires database metadata on disk (by default `.metabase/metadata.json`).
Audit UI performance with Lighthouse and fix Core Web Vitals — LCP, CLS, INP. Fast UI is good UX. Use when optimising page load, fixing layout shift, reducing input delay, improving Lighthouse scores, or reviewing images, fonts, and render-blocking resources.
MUST be used when user asks to document TypeScript or Vue code — add TSDoc/JSDoc blocks, docblocks, или «задокументировать» functions, classes, methods, interfaces, type aliases, enums, generics, Vue composables, defineProps/defineEmits/defineModel. Enforces strict TSDoc spec (tsdoc.org) and writes all descriptions in Russian. Triggers on phrases like «добавь tsdoc», «задокументируй», «напиши док», «add tsdoc», «document this», «generate jsdoc».
Jiminny platform help — conversation intelligence, revenue intelligence, AI notetaker, sales coaching, and automatic CRM logging. Use when setting up Jiminny call recording or transcription, configuring Jiminny CRM sync to Salesforce or HubSpot, connecting Jiminny to a dialer like Aircall or Dialpad, troubleshooting calls not appearing in Jiminny or tagging delays, pulling activity data from the Jiminny API, comparing Jiminny vs Gong pricing or features, or evaluating Jiminny for pipeline visibility. Do NOT use for general coaching program design (use /sales-coaching) or comparing standalone AI note-takers (use /sales-note-taker).
Use when the user asks to "write a reconciler", "implement a reconciler", "add business logic", "handle resource changes", "process resource events", "implement the reconcile loop", "add async processing", "write a controller", "handle create/update/delete events", "use TypedReconciler", "use a Watcher", or asks how to respond to resource state changes in a grafana-app-sdk app. Provides guidance on implementing reconciler and watcher business logic for grafana-app-sdk apps.
Sprout Social platform help — Publishing, Smart Inbox, Analytics, Social Listening (add-on), Influencer Marketing, Employee Advocacy, AI Assist, API, Salesforce/HubSpot/Zendesk integrations. Use when Sprout Social posts aren't publishing on schedule, Smart Inbox is overwhelming and hard to triage, analytics reports don't show the metrics you need, social listening queries return too much noise, influencer campaigns in Sprout lack visibility, employee advocacy adoption is low, AI Assist suggestions feel off, CRM sync keeps disconnecting, or you're deciding between Sprout Social and Hootsuite/Buffer/Agorapulse. Do NOT use for social listening strategy across tools (use /sales-social-listening), influencer marketing strategy (use /sales-influencer-marketing), social media management strategy (use /sales-social-media-management), or employee advocacy strategy (use /sales-employee-advocacy).
Expert skill for using Future AGI — the open-source end-to-end platform for evaluating, observing, and improving LLM and AI agent applications with tracing, evals, simulations, datasets, gateway, and guardrails.
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
Implement end-to-end Medallion Architecture (Bronze/Silver/Gold) lakehouse patterns in Microsoft Fabric using PySpark, Delta Lake, and Fabric Pipelines. Use when the user wants to: (1) design a Bronze/Silver/Gold data lakehouse, (2) set up multi-layer workspace with lakehouses for each tier, (3) build ingestion-to-analytics pipelines with data quality enforcement, (4) optimize Spark configurations per medallion layer, (5) orchestrate Bronze-to-Silver-to-Gold flows via notebooks. Triggers: "medallion architecture", "bronze silver gold", "lakehouse layers", "e2e data pipeline", "end-to-end lakehouse", "data lakehouse pattern", "multi-layer lakehouse", "build medallion", "setup medallion".