Loading...
Loading...
Found 42 Skills
Analyze lakehouse data interactively using Fabric Livy sessions and PySpark/Spark SQL for advanced analytics, DataFrames, cross-lakehouse joins, Delta time-travel, and unstructured/JSON data. Use when the user explicitly asks for PySpark, Spark DataFrames, Livy sessions, or Python-based analysis — NOT for simple SQL queries. Triggers: "PySpark", "Spark SQL", "analyze with PySpark", "Spark DataFrame", "Livy session", "lakehouse with Python", "PySpark analysis", "PySpark data quality", "Delta time-travel with Spark".
Generate structured narrative text visualizations from data using T8 Syntax. Use when users want to create data interpretation reports, summaries, or structured articles with semantic entity annotations. T8 is designed for unstructured data visualization where T stands for Text and 8 represents a byte of 8 bits, symbolizing deep insights beneath the text.
Pull structured data from messy text using AI. Use when parsing invoices, extracting fields from emails, scraping entities from articles, converting unstructured text to JSON, extracting contact info, parsing resumes, reading forms, or any task where messy text goes in and clean structured data comes out. Powered by DSPy extraction.
Plan and evaluate mesh generation for numerical simulations — estimate grid resolution from physics scales (interface width, boundary layers, wavelengths), check aspect ratios and skewness against quality thresholds, choose between structured, unstructured, and adaptive mesh refinement strategies, and compute grid sizing for 1D/2D/3D domains. Use when setting up a new mesh, diagnosing poor solver convergence caused by mesh quality, deciding how many points to place across a phase-field interface or boundary layer, or preparing a mesh convergence study, even if the user only asks "what resolution do I need" or "why is my solver failing."
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
Converts unstructured field notes, text messages, voice-to-text transcripts, or informal subcontractor updates into a properly formatted Solar EPC construction daily report. Use this skill whenever a user provides raw field notes, a dump of information from a site superintendent, a forwarded text thread, or any informal description of a day's construction activity and needs it turned into a structured daily log. Trigger for phrases like "format this into a daily report", "turn this into a daily log", "my super sent me this", "here's what happened on site today", "write up today's progress", or when a user pastes a block of unstructured text that describes construction activity. Also trigger when a user asks how to document a weather delay, crew idle time, or a site condition that affected production. Every unrecorded day of construction is an unprotected schedule claim.
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is accessed through federation mechanisms such as Apache Iceberg, other "zero-copy ETL" methods, or remote query push-down. Use this skill when designing an architecture for efficient analytics across large volumes of structured and unstructured data that's located in multiple systems and environments, including other cloud providers and on-premises.
This skill should be used when the user wants a "blob store" or "object storage", names "S3" or an S3-compatible store, needs to "store images / video / files", asks about "multipart upload" or "resumable upload", "signed / presigned URLs", "media storage", "unstructured data at scale", object "versioning", storage "tiering" (hot/cold/archive), or "erasure coding" vs replication for durability. Use it whenever a design must hold large unstructured objects (photos, video, backups, logs, ML datasets) and serve them cheaply and durably, even if the user just says "where do we put the files".
Captures and organizes chaotic brain dumps into a structured, actionable system with zero information loss. Use this skill whenever the user says 'capture this', 'brain dump', 'let me dump some ideas', 'I've got a bunch of thoughts', 'here's everything on my mind', 'idea dump', 'let me get this out of my head', 'I need to organize my thoughts', 'here's what I'm thinking', or any variation where someone is unloading a messy stream of ideas, tasks, thoughts, and plans wanting them turned into something coherent. Also trigger when the user pastes or dictates a long, unstructured block of mixed ideas — even without the exact phrase — the intent is the same. Fast-to-action by design: no upfront intake. Output is four sections (Projects/Ideas, Tasks, Connections, How I Can Help) ending with a directive question. Asks at most one mid-organization clarifying question when a single item is genuinely ambiguous between task and project.
When the user wants to build or improve a sales bot's ability to pull key data points (budget, timeline, company size, location, requirements) from unstructured prospect responses. Also use when the user mentions "extracting data," "parsing responses," "pulling out details," "structured data from conversations," or "NER for sales."
Blueprint client, patient, or project intake forms with clear section flow, calibrated field density, and trustworthy fillable layout intent—not an unstructured questionnaire dump or generic web-form paste. Use when the user asks for an intake form, onboarding questionnaire, registration packet, new-client paperwork, or new-patient form. Create intake forms with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets them focus on semantic content and design intent while automatically handling layout, typography, and formatting complexity.
Use when setting up a new repository, when AI agents lack project context, or when codebase guidelines are scattered and unstructured.