Loading...
Loading...
Found 1,737 Skills
Converts CSV/TSV inputs into Infrahub object YAML and loads them onto a fresh branch. Handles a single file, a folder of files, an explicit list of paths, and one-big-denormalized-sheet exports. TRIGGER when: importing CSV, loading CSV/TSV into Infrahub, ingesting spreadsheet data, converting CSV to Infrahub objects, splitting a denormalized CSV across multiple kinds, re-running an import after changing a column mapping, debugging why a row fails to convert or load. DO NOT TRIGGER when: running `infrahubctl load` against an LDJSON dump (different format and tool), designing or modifying schemas (this skill is read-only against the schema and fails closed on unmapped columns), exporting data from Infrahub (use `infrahubctl object get -o csv` for single-kind export), or ingesting JSON/XLSX (v1 is CSV+TSV only).
Operate Stability AI image generation, image-to-image, edit, control, background, and upscale APIs safely and reproducibly. Use when selecting or calling Stable Image Ultra, Core, Stable Diffusion 3.5, v2beta image edit/control services, or Stability open-weight image models; when debugging schemas, moderation, rate limits, cost, lifecycle, licenses, privacy, provenance, or migrations; and when planning production QA for Stability-generated images.
Systematic evidence-based debugging using runtime logs. Generates hypotheses, instruments code with NDJSON logs, guides reproduction, analyzes log evidence, and iterates until root cause is proven with cited log lines. Use when the user reports a bug, unexpected behavior, or asks to debug an issue.
Write and improve agent skills (SKILL.md files). Use when creating new skills, refactoring existing ones, debugging why an agent ignores instructions, or improving compliance. Covers prompt structure, TDD for skills, description optimization, and rationalization bulletproofing.
Python Playwright testing of local web apps. Use when verifying frontend functionality, debugging UI behavior, capturing browser screenshots, or viewing browser console logs.
Lakeflow Connect ingestion from SaaS apps (Salesforce, Workday, ServiceNow, HubSpot, SharePoint, Google Drive, OneDrive, Jira, ads, audit logs, 70+ more) and Kafka or RabbitMQ into Unity Catalog. Use when finding a connector, creating its connection and pipeline, scheduling or debugging it.
MLflow tracing and observability on Databricks. Use when getting started with MLflow, instrumenting GenAI apps and agents, retrieving and analyzing traces, debugging chat sessions, or querying aggregate trace metrics on supported OSS servers.
Terraform and OpenTofu infrastructure-as-code patterns for project layout, remote state, modules, variables, secrets, safe plan/apply workflows, and CI. Use when writing or reviewing .tf files, structuring modules or environments, configuring backends and state locking, or debugging plan drift, state, and provider errors.
Use when building or debugging UE5 gameplay: a character with double jump or dash, abilities with cooldowns, enemy AI that patrols, chases and attacks, a health bar or HUD; choosing Blueprint vs C++, GAS or not, StateTree vs Behavior Tree, EQS or Mass; setting up Enhanced Input, Common UI or UMG; replication, RepNotify, save games, World Partition state; "Blueprints are slow", Tick, casts and hard references; "ability won't activate", "enemy ignores the player"; or writing automated gameplay tests with injected input.
Use when calling the Spree 6 Admin API from the command line or driving it programmatically as an agent — exploring endpoints, reading or mutating store data, and especially DEBUGGING (inspecting an order/product/customer, checking why a request failed, reproducing a 403/422). The `spree api` command group in `@spree/cli` is a `gh api`-style generic HTTP client: `spree api get|post|patch|delete <path>` plus offline discovery (`spree api endpoints`, `spree api schema`). Common phrasings include "spree api", "spree CLI", "call the admin API from the terminal", "spree api get", "inspect this order", "why is this Spree request failing", "list admin endpoints", "spree auth". Also covers the project-side dev commands agents reach for while debugging (`spree shell`, `spree test`, `spree console`, `spree add`, `spree plugin new`). For SDK/TypeScript integration use spree-typescript-sdk; for raw API protocol details use spree-api-v3.
Subject-driven design and implementation of user-facing interfaces. Use when building, implementing, redesigning, reviewing, or refining pages, layouts, forms, navigation, dashboards, or reusable UI components in HTML, CSS, Vue, Nuxt, React, or other frontend frameworks, including implementation-framed changes to responsive design, styling, accessibility, visual hierarchy, interaction states, or user experience. Use alongside playwright-debug for browser verification (root-cause investigation of unexpected behavior is debugging).
The Aries Tools TypeScript toolchain (@ariestools/toolchain) behind XY, XYO, and XL1 repositories — the stable xy and experimental xyex CLIs, xy.config.ts, and the shared ESLint, TypeScript, and Vitest configs. Use when setting up a repo or choosing a project profile; running or debugging build, lint, test, or xy check; configuring package output; fixing deplint or publint findings; linting AGENTS.md and docs with xy agent; supporting product planning (papers, roadmap, PRDs) with xy repo init and xyex plan; managing skills; tracking work with xyex work; updating dependencies; auditing licenses or security; releasing packages; or interpreting xy command failures.