dev-start
Quick start for new Capsem developers. Use for "how do I get started" or "first time setup"; for environment troubleshooting use dev-setup instead.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-02 00:09
Deployment & operations
12,936 results
vertex-tuning
Vertex AI Model Tuning. Use when you need to fine-tune models using Vertex AI's infrastructure.
sagemaker-endpoint-deployer
Sagemaker Endpoint Deployer - Auto-activating skill for ML Deployment. Triggers on: sagemaker endpoint deployer, sagemaker endpoint deployer Part of the ML…
tensorflow-model-deployment
Deploy and serve TensorFlow models
aio11y
Use when the user wants to list or search AI Observability conversations, inspect generations, manage evaluators (create, test, delete), set up evaluation…
supabase-cli
Use the Supabase CLI to manage databases, run migrations, manage auth, storage, edge functions, and local development. Use this instead of the Supabase MCP…
terraform-cli
Use Terraform CLI to define, plan, and provision infrastructure as code across any cloud provider. Use this instead of the Terraform MCP server.
demo-scaffolding
Create production-ready demo platforms for Assistant Skills plugins. Use when you want to "create a demo", "scaffold demo infrastructure", "set up demo for…
setup-wizard
This skill should be used when the user asks to "set up Assistant Skills", "configure venv", "install dependencies", "run assistant-skills-setup", or needs…
release
Internal maintainer skill for cutting graphistry-skills releases (changelog bump, PR merge, semver tag, and GitHub release publish).
ship
Use when the user asks to deploy the current project with Ship, usually as "$ship 현재 프로젝트 demo로 배포 해줘" or "$ship deploy this Dockerfile project as <service>".…
github-agentic-workflows
GitHub Agentic Workflows (gh-aw) — markdown-defined AI automation with Copilot/Claude/Codex, safe outputs, 5-layer security, and Continuous AI patterns
jarvis-doctor
Health check for a Jarvis that's already built: is it running, reachable, inside its spend cap, up to date above the security floor, and still locked to its…
jarvis-refresh
Maintainer command: re-verify every pinned version, price, model ID and policy in knowledge/ against live sources, and report what moved. Use before a release…
matriz-doctor
Diagnóstico de Matriz Viralidad: revisa Node, ffmpeg, yt-dlp, la skill watch, tus llaves (sin mostrarlas), las carpetas, el perfil y cuánto llevas gastado en…
building-inferencesh-apps
Build and deploy applications on inference.sh. Use when getting started, understanding the platform, creating apps, configuring resources, or needing an…
god-ship
Release gate and shipping checklist. Requires fresh checks, a passing review and security record, and no open critical risk, then covers deploy, rollback,…
god-status
Show Godpowers project state, evidence freshness, and open risks without changing anything. Use for /god-status, "where are we", or "is this verified".
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production",…
portability
Forge kernel data portability — getting issue data in and out of the local kernel. `forge export [--dir] [--dry-run]` writes the kernel backlog to…
setup
Forge install & setup lifecycle. `forge setup` interactively configures Forge for your coding agents; `forge init [--profile minimal|standard|full]` writes the…
ship-and-watch
Use after pushing a Forge branch, opening a PR, or when asked "is the PR ready / what's the status / are checks green" — reads shepherd verdicts instead of…
setup-superconductor-project
Configures a repository for super.engineering with repo-owned worktree setup and development-server scripts. Use when asked to "make this project…
containerize
Containerise the current project - Dockerfile, .dockerignore and compose.yaml with current Docker practice.