Loading...
Loading...
Found 1,237 Skills
Write, rewrite, or normalize structured `*.spec.md` specification files for agent-driven development. Use this whenever the user asks for a spec, requirements, acceptance criteria, implementation-ready documentation, feature definition before coding, or wants an existing idea/codebase turned into an actionable spec, even if they do not explicitly say "spec".
Package and build custom AI models with Cog for deployment on Replicate. Use when creating a cog.yaml or predict.py, defining model inputs and outputs, loading model weights at setup time, building Docker images for ML models, serving locally with cog serve or cog predict, or porting a HuggingFace, GitHub, or ComfyUI model to run on Replicate. Trigger on phrases like "build a model", "package a model", "create a Cog model", "wrap a model", "containerize an AI model", "predict.py", "cog.yaml", "BasePredictor", or "Cog container", and when referencing cog.run, github.com/replicate/cog, or github.com/replicate/cog-examples. Covers GPU and CUDA setup, pget for fast weight downloads, async predictors with continuous batching, streaming outputs, and cold-boot optimization for image, video, audio, and LLM models. For pushing built models to Replicate, see publish-models. For running existing models, see run-models.
OmniStudio FlexCard creation and validation with 130-point scoring. Use when building at-a-glance UI cards, configuring data source bindings to Integration Procedures, or reviewing existing FlexCard definitions for accessibility and performance. TRIGGER when: user creates FlexCards, configures data sources, designs card layouts, or asks about OmniUiCard metadata. DO NOT TRIGGER when: building OmniScripts (use building-omnistudio-omniscript), creating Integration Procedures (use building-omnistudio-integration-procedure), or analyzing dependencies (use analyzing-omnistudio-dependencies).
Generates structured test assertions and failure diagnostics for skill packages from a definition and task prompt. Triggers on: "verify this skill", "generate assertions", "surrogate verification", "diagnose skill failure". NOT for code review, use pr-review.
Gather concept definitions scattered across multiple modules into a single shared import module in template/. Removes the moved definitions from the original modules and adds the new import to their frontmatter. Use when concepts are duplicated or spread across modules and should be centralized.
Design and implement workflow automation with task routing approval chains and SLA monitoring for securities operations. Use when building a new operational workflow for account opening maintenance transfers or corporate actions, implementing task routing logic based on type priority or capacity, designing multi-level approval chains with dollar thresholds and delegation of authority, defining escalation rules for aging work items approaching SLA breach, selecting a workflow engine or BPM platform like Camunda Pega or ServiceNow, modeling an operational process as a state machine with defined transitions, adding audit trail and logging for SEC Rule 17a-3 or FINRA supervisory obligations, migrating from email-and-spreadsheet tracking to a structured workflow system, or measuring cycle time throughput queue depth and rework rate.
Design dashboards, write analytical SQL, define KPIs, and manage stakeholder analytics requirements. Cover chart selection, data storytelling, cohort/funnel analysis, metric definitions, and BI tool patterns (Tableau, Looker, Power BI). Triggers on "build dashboard", "design dashboard", "write analytical SQL", "cohort analysis", "funnel analysis", "define KPI", "define metric", "reporting requirements", "data storytelling", "stakeholder analytics", "retention analysis", or "BI report". For business model canvas, TAM/SAM/SOM, and competitor monetization research, use business-model-researcher—not bi-analyst. For building warehouse marts, dbt models, tests, and lineage—not dashboards—use analytics-data-engineer.
Use when the user asks to define a goal, create a Goal Contract, or clarify a concrete task's goal, scope, success criteria, evidence, or guardrails before planning or execution.
TanStack AI (alpha) provider-agnostic type-safe chat with streaming for OpenAI, Anthropic, Gemini, Ollama. Use for chat APIs, React/Solid frontends with useChat/ChatClient, isomorphic tools, tool approval flows, agent loops, multimodal inputs, or troubleshooting streaming and tool definitions.
Scaffolds a production-ready TypeScript CLI project with ESM, tsdown, vitest, oxlint, oxfmt, changesets, GitHub Actions, and an agent skill definition. Use when creating a new CLI tool, bootstrapping a TypeScript project, scaffolding a node CLI, starting a new npm package, or asking "scaffold a CLI project."
Author step content for Novu workflows defined in the Dashboard or generated/edited via the Novu MCP. Use when filling in step controls (subject, body, editorType, headers, body, conditions) for email, in-app, sms, push, chat, delay, digest, throttle, or HTTP Request steps.
Build code-first notification workflows with @novu/framework. Use when defining workflows in TypeScript (Zod / JSON Schema / Class Validator), composing channel steps (email, SMS, push, chat, in-app) with action steps (delay, digest, custom), exposing Step Controls for non-technical teammates, rendering React/Vue/Svelte Email templates, hosting the Bridge Endpoint inside Next.js, Express, NestJS, Remix, Nuxt, SvelteKit, H3, or AWS Lambda, syncing to Novu Cloud via CLI / GitHub Actions, securing production with HMAC, or implementing translations, hydration, multi-channel orchestration, and LLM-powered notification logic in code.