elviskahoro

Scan design/ for backlog/todo artifacts, check if work has been merged into the codebase, and auto-rename completed ones to done-. Use for periodic hygiene, after merging branches, or to audit design artifact status.

Use when writing Dagger pipelines in Python, building containerized CI/CD with the Dagger Python SDK, creating Dagger modules/functions/objects, integrating services (PostgreSQL, Redis) in Dagger, using Dagger LLM/agent features, or running Dagger in GitHub Actions.

Use when creating specifications, implementation plans, or tools for a feature - enforces consistent naming across related artifacts

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use this skill when the user wants to run hotdata CLI commands, query the Hotdata API, list workspaces, list connections, create connections, list tables, manage datasets, execute SQL queries, inspect query run history, search tables, manage indexes, manage sandboxes, manage workspace context and the data model via the context API (`hotdata context`), or interact with the hotdata service. Activate when the user says "run hotdata", "query hotdata", "list workspaces", "list connections", "create a connection", "list tables", "list datasets", "create a dataset", "upload a dataset", "execute a query", "search a table", "list indexes", "create an index", "list query runs", "list past queries", "query history", "list sandboxes", "create a sandbox", "run a sandbox", "workspace context", "pull context", "push context", "data model", or asks you to use the hotdata CLI.

Use when building, deploying, or debugging applications on Modal (modal.com) — serverless cloud compute for Python. Covers container images, GPU functions, web endpoints, volumes, secrets, scheduling, distributed training, calling deployed functions, and scaling patterns.

Use when calling deployed Modal functions from a CLI or external service without needing the Modal app running locally

Use when you have a spec or requirements for a multi-step task, before touching code

Redeploy the Beacon telemetry launch agents (sidecar collector + traces bridge) with fresh Infisical credentials from dotfiles/beacon.env, TCC-safely.

[Warp terminal app ONLY] Add MCP servers to Warp's MCP config files (~/.warp/.mcp.json or {repo}/.warp/.mcp.json). Trigger ONLY when the user is configuring MCP for the Warp terminal app specifically. Do NOT trigger for Claude Code, Cursor, Zed, Continue, Cline, or any other tool's MCP configuration — those have different config paths and formats. If the user just says 'add an MCP server' without naming Warp, ask which tool before invoking this skill.

[Bundled with the Warp terminal app] Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER ONLY when: code imports `anthropic`/`@anthropic-ai/sdk`; the user explicitly asks for the Claude API, Anthropic SDK, or Anthropic Managed Agents; user adds/modifies/tunes a Claude-specific feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in an Anthropic SDK file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP for: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML, or any task that does not specifically involve Anthropic's API.

[Bundled with the Warp terminal app] Create or modify agent skill packages (SKILL.md files with frontmatter, plus their scripts/references). Trigger ONLY when the user explicitly wants to author, edit, evaluate, or benchmark an agent skill — meaning a skill in the SKILL.md / agent-skill format used by Warp, Claude Code, or Anthropic agents. Do NOT trigger for general code authoring, writing utility functions, refactoring, creating CLI tools, or any task that the user has not specifically framed as 'building/editing a skill'.

[Warp terminal app ONLY] Create new Warp tab config TOML files (Warp's terminal-tab layout files in ~/.warp/tab_configs/). Trigger ONLY when the user is creating a layout for the Warp terminal app specifically. Do NOT trigger for tmux configs, iTerm/Terminal.app profiles, VS Code/JetBrains workspace layouts, browser tabs, or any non-Warp 'tab' or 'layout' concept. If the user just says 'tab config' or 'tab layout' without naming Warp, ask which tool before invoking.

[Warp terminal app ONLY] Turn rough feedback about the Warp terminal app into a filed GitHub issue (or duplicate-issue response) on the `warpdotdev/warp` repo. Trigger ONLY when the user is reporting a bug, regression, UX issue, or feature gap specifically about the Warp terminal app and wants it filed against warpdotdev/warp. Do NOT trigger for: feedback about other apps/tools, generic 'I have feedback' messages, complaints about Claude/this assistant, requests to file issues against other repos, or general bug reporting workflows. If the target app/repo is unclear, ask before invoking.

[Warp terminal app ONLY] View or modify Warp terminal application settings using Warp's bundled JSON schema. Trigger ONLY when the user is changing settings of the Warp terminal app specifically. Do NOT trigger for: Claude Code settings.json, shell rc files (.zshrc/.bashrc), git config, IDE/editor settings, OS preferences, or any other application's configuration. If the user just says 'change a setting' without naming Warp, ask which app before invoking.

[Warp terminal app ONLY — Warp's Oz cloud agent platform] Use Warp's Oz REST API and CLI to spawn, schedule, configure, and inspect Warp cloud agents and their environments/secrets. Trigger ONLY when the user is working with Warp's Oz cloud agent platform specifically. Do NOT trigger for: Claude Code agents, Anthropic Managed Agents, GitHub Actions, generic 'cloud agents', other agent platforms, or any non-Warp scheduling/automation. If 'cloud agent' is mentioned without naming Warp/Oz, ask before invoking.

Reference for deploying, configuring, and troubleshooting applications on Railway (railway.com). Covers config-as-code (`railway.json` / `railway.toml` schema), services, environments (persistent + PR), variables + reference variables, cron jobs, Functions, builds (Dockerfile + Railpack), deployments (healthchecks, restart policy, pre-deploy, regions, scaling), and a Reflex-on-Railway troubleshooting guide including an Alpine Dockerfile pattern that survives free-tier memory limits. Invoke explicitly (e.g. via `/railway`) when working on Railway config — the skill does not auto-trigger on incidental Railway mentions.

Use when deploying a Reflex app to Reflex Cloud using `reflex deploy`, configuring cloud.yml for regions, VM types, scaling, environment variables, custom domains, or deployment strategies. Also use when managing multi-environment deployments (dev/staging/prod) on Reflex Cloud.

Use when self-hosting a Reflex app with Docker and Docker Compose, creating Dockerfiles for Reflex backend/frontend, configuring nginx as a reverse proxy, deploying to EC2 or any VPS, or pushing Reflex Docker images to a container registry (ECR, Docker Hub).

Use when deploying a Reflex app to Google Cloud Platform, setting up Cloud Run for the backend, Firebase Hosting for the frontend, configuring VPC networking with Redis, or creating Cloud Build CI/CD triggers for a Reflex project.

Use when building web apps with Reflex (reflex.dev), creating frontend UIs in pure Python, managing reactive state, defining pages and routing, integrating databases, or deploying Reflex applications. Default to Buridan UI component library for pre-built, customizable components.

Update the Attio Python SDK by fetching the latest OpenAPI spec from https://api.attio.com/openapi/api, verifying overlays, and regenerating with Speakeasy

Reference guide for creating and modifying OpenAPI Overlays used to customize the Attio API spec before SDK generation with Speakeasy