skill CX Codex

deploy-chalk-function — Claude Code skill: deploy Python

Q: How do I install deploy-chalk-function in Claude Code?

Run `npx skills add chalk-ai/chalk-ai-plugins --skill deploy-chalk-function -a claude-code`. The skill will be available at `~/.claude/skills/deploy-chalk-function/SKILL.md`.

Q: What does deploy-chalk-function do?

It explains how to deploy a standalone Python function with `chalkcompute`. Importing the decorated function starts image creation, upload, and registration, while calling it sends the work to Chalk remotely.

Q: Which environment variables does chalkcompute require?

Set `CHALK_API_SERVER`, `CHALK_CLIENT_ID`, `CHALK_CLIENT_SECRET`, and `CHALK_ENVIRONMENT_ID`. The SDK reads these values from the environment, and omitting `CHALK_ENVIRONMENT_ID` causes a `permission_denied` result during image handling.

This skill walks through deploying a standalone Python function to Chalk’s container infrastructure and calling it remotely with chalkcompute.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓

npx skills add chalk-ai/chalk-ai-plugins --skill deploy-chalk-function -a claude-code

Open on GitHub

What deploy-chalk-function does

The skill outlines a Python file that imports chalkcompute, marks a function with @chalkcompute.function(), and calls it from the script. Importing the decorated function triggers image building, upload, and registration. A later call runs remotely and returns the result.

The example uses a uv script header with an inline dependency declaration. Python must stay within >=3.12,<3.14 because the transitive Rust package chalk-remote-call-python currently builds only through Python 3.13. The decorator requires parentheses; leaving them out raises TypeError.

Credentials come from CHALK_API_SERVER, CHALK_CLIENT_ID, CHALK_CLIENT_SECRET, and CHALK_ENVIRONMENT_ID, rather than the chalk CLI configuration. Without CHALK_ENVIRONMENT_ID, the image operation fails with permission_denied. If the configured index cannot resolve chalkcompute, the skill shows how to point uv to a local chalk-sandbox-sdk checkout.

What it helps with

deploy a standalone Python function to Chalk
run a decorated function remotely
declare chalkcompute as a uv dependency
provide Chalk credentials through environment variables
trace a permission_denied image-build failure

Example prompts for the agent

Create a uv Python script that uses @chalkcompute.function() and deploys the function to Chalk.
List the environment variables required by chalkcompute and explain the permission_denied error.
Show how to invoke the decorated function from the same script with uv.

How to install deploy-chalk-function

1Skills CLI (Vercel)

npx skills add chalk-ai/chalk-ai-plugins --skill deploy-chalk-function -a claude-code

2Manually: put the files in place

~/.claude/skills/deploy-chalk-function/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/deploy-chalk-function/

1Skills CLI (Vercel)

npx skills add chalk-ai/chalk-ai-plugins --skill deploy-chalk-function -a codex

2Manually: put the files in place

.agents/skills/deploy-chalk-function/SKILL.md

For all projects use ~/.agents/skills/

1Skills CLI (Vercel)

npx skills add chalk-ai/chalk-ai-plugins --skill deploy-chalk-function -a cursor

2Manually: put the files in place

.cursor/skills/deploy-chalk-function/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install chalk-ai/chalk-ai-plugins deploy-chalk-function

2Manually: put the files in place

.github/skills/deploy-chalk-function/SKILL.md

1Skills CLI (Vercel)

npx skills add chalk-ai/chalk-ai-plugins --skill deploy-chalk-function -a gemini-cli

2Platform CLI

gemini skills install https://github.com/chalk-ai/chalk-ai-plugins --path plugins/chalk-deploy-function/skills/deploy-chalk-function

Manually: put the files in place

.devin/skills/deploy-chalk-function/SKILL.md

The legacy .windsurf/skills/ path still works

Skills CLI (Vercel)

npx skills add chalk-ai/chalk-ai-plugins --skill deploy-chalk-function -a opencode

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about deploy-chalk-function

How do I install deploy-chalk-function in Claude Code?

Run npx skills add chalk-ai/chalk-ai-plugins --skill deploy-chalk-function -a claude-code. The skill will be available at ~/.claude/skills/deploy-chalk-function/SKILL.md.

What does deploy-chalk-function do?

It explains how to deploy a standalone Python function with chalkcompute. Importing the decorated function starts image creation, upload, and registration, while calling it sends the work to Chalk remotely.

Which environment variables does chalkcompute require?

Set CHALK_API_SERVER, CHALK_CLIENT_ID, CHALK_CLIENT_SECRET, and CHALK_ENVIRONMENT_ID. The SDK reads these values from the environment, and omitting CHALK_ENVIRONMENT_ID causes a permission_denied result during image handling.

setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. 1,052,851installs ask-matt Matt Pocock Routes you to the right Matt Pocock skill or flow for the task at hand. Use it when you need a starting point for a feature, prototype, incoming issue, or hard bug. 766,587installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. 711,230installs writing-plans Jesse Vincent This skill turns requirements for a multi-step task into an implementation plan before code changes begin. It helps when another engineer needs exact files, interfaces, and checks. CX Codex 282,859installs caveman-review JuliusBrussee Turns code review comments into one line per finding: location, problem, fix. Useful when a diff or PR needs a fast pass without the filler. CX Codex +1 411,800installs caveman-compress JuliusBrussee Compresses CLAUDE.md, todo lists, and other prose files into a shorter format while retaining a readable backup. CX Codex +1 411,500installs

From the same set4

accelerate-python-resolvers Converts Python feature resolvers in Chalk codebases into native columnar expressions. It runs diagnostics and rewires unsupported operations to satisfy the static accelerator. CX Codex +1 838installs benchmark-vllm-model Works out what a self-hosted model costs per token and per request: brings it up on a GPU, loads it to saturation, then divides the hourly price by measured throughput. CX Codex +1 837installs debug-plan-cache-misses Finds Chalk plan cache misses by analyzing engine logs and diffing query payloads. Useful when repeated plan generation increases response latency. CX Codex +1 836installs