First-pass support for recurring accounting and finance-operations work — month-end close checklists and tie-outs, AP/AR reconciliation, invoice validation (3-way match, duplicate and math checks), and financial-model review. Use this skill whenever the user uploads or pastes ledgers, trial balances, AP/AR aging, vendor statements, bank statements, invoices, POs, or a financial model (Excel/CSV/Google Sheets export) and asks to close the books, reconcile, tie out, match, validate invoices, find discrepancies or duplicates, review a model, or "check the numbers" — even if they don't use the exact accounting term. Also use for questions like "does this reconcile?", "is this invoice ok to pay?", or "review this model for errors.
Turn raw notes, ticket/task data, metrics, and standup updates into polished, consistent status reports and executive summaries in a reusable house format. Use this skill whenever the user wants to write, draft, generate, or clean up a weekly status report, team/project update, exec or leadership summary, stakeholder update, or "what I did this week / where things stand" report — or asks to define a house format for reports, make last week's format consistent, or summarize progress for leadership. Trigger even when the user just pastes messy notes, a task export, or last week's report and says "turn this into an update," and even if they don't use the exact word "status report.
First-pass support for core insurance operations — claims intake / FNOL triage, underwriting submission checklists and risk screening, and side-by-side policy comparison. Use this skill whenever the user uploads or pastes a first notice of loss, claim file, loss run, underwriting submission/application, quote, or one or more policies/dec pages and asks to triage a claim, screen or check an underwriting submission, assess a risk, compare policies or quotes, find coverage gaps, or spot red flags — even if they don't use the exact insurance term. Also use for questions like "is this claim ready to assign?", "does this submission fit our appetite?", or "which of these quotes has better coverage?
Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, streaming responses, background research tasks, function calling, structured output, or migrating from the old generateContent API. This skill covers the Interactions API, the recommended way to use Gemini models and agents in Python and TypeScript.
Integrate Firecrawl `/search` into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should search the web and optionally hydrate result content.
Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.
Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.
Datadog docs lookup using docs.datadoghq.com/llms.txt and linked Markdown pages.
Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.
Diagnoses and fixes slow Qdrant indexing and data ingestion. Use when someone reports 'uploads are slow', 'indexing takes forever', 'optimizer is stuck', 'HNSW build time too long', or 'data uploaded but search is bad'. Also use when optimizer status shows errors, segments won't merge, or indexing threshold questions arise.