chunk — Codex skill: what it does, how to install
Connects AI workflows to CircleCI Chunk via web UI or chunk-cli to troubleshoot failing builds and configure tasks.
npx skills add openai/plugins --skill chunk -a codexWhat chunk does
This skill guides developers through CircleCI Chunk setup using either the web application or the chunk-cli terminal tool. The UI path assists with organization setup, model provider connections, and environment files. The CLI path targets terminal actions like init, validate, build-prompt, auth, sandbox, and task.
Every run begins by confirming project context, branch details, GitHub App integrations, and API key setups. Execution outputs always list what succeeded, what is still blocked, and the next safe command.
Because sandbox capabilities remain in private preview, access gates must be cleared before requesting those tasks.
What it helps with
- Diagnose and fix broken CI/CD pipeline builds
- Set up chunk-cli commands and authentication
- Configure model providers and project environments in CircleCI
- Generate build prompts and context for pipeline tasks
Example prompts for the agent
- Help me configure CircleCI Chunk for this repository using chunk-cli
- Inspect the failed build in CircleCI and recommend a fix
- Run chunk-cli validate on our current project setup
How to install chunk
1Skills CLI (Vercel)
npx skills add openai/plugins --skill chunk -a codex2Manually: put the files in place
.agents/skills/chunk/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add openai/plugins --skill chunk -a claude-code2Manually: put the files in place
~/.claude/skills/chunk/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/chunk/
Manually: put the files in place
.cursor/skills/chunk/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install openai/plugins chunk2Manually: put the files in place
.github/skills/chunk/SKILL.mdPlatform CLI
gemini skills install https://github.com/openai/plugins --path plugins/circleci/skills/chunkManually: put the files in place
.devin/skills/chunk/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: Codex skills: how to install, where they live, how to call them
Questions about chunk
How do I install chunk in Codex?
Run npx skills add openai/plugins --skill chunk -a codex. The skill file is placed at .agents/skills/chunk/SKILL.md.
What does the chunk skill do?
It determines the right route between CircleCI web tools and the chunk-cli utility, executing builds and troubleshooting pipeline issues.
What prerequisites does Chunk need?
You need an active GitHub integration, model provider keys or CircleCI-managed access, and local environment tokens for CLI commands.
Source text
SKILL.md · MIT
--- name: chunk description: Use CircleCI Chunk for AI-assisted CI/CD work through either the Chunk web UI or the chunk-cli. Trigger this skill when users ask to set up Chunk, troubleshoot or fix failing builds with Chunk, configure Chunk environments, schedule/proactively run Chunk tasks, or use chunk-cli commands such as init, validate, build-prompt, auth, sandbox, task, and skill install. --- # Chunk ## Overview Use this skill to choose the best Chunk workflow (UI or CLI), then execute it with clear prechecks and safe defaults. Keep responses action-oriented and grounded in verified commands and setup requirements. ## Workflow 1. Classify the request path. - Use UI path for org setup, model-provider onboarding, fix buttons, or environment selection in the CircleCI app. - Use CLI path for terminal-based project setup, validation hooks, prompt/context generation, sandbox operations, or scripted task execution. - Use mixed path when users want UI setup plus CLI execution in the same flow. 2. Gather minimum context. - Confirm repository/project, branch, and whether GitHub integration is in place. - Confirm whether the user is using CircleCI-managed model provider or bring-your-own keys. - For CLI operations, confirm local OS compatibility and required tokens/auth. 3. Execute using the matching reference. - For UI/setup flows, load [chunk-ui.md](references/chunk-ui.md). - For CLI flows, load [chunk-cli.md](references/chunk-cli.md). 4. Close with verification. - State what was configured or run, what remains blocked, and the next safest command or UI action. ## Guardrails - Treat Chunk features as beta unless the user confirms otherwise. - Never expose or log secret values (API keys, tokens, bearer credentials). - Do not invent `chunk` subcommands or flags; stick to documented command families. - If sandbox features are requested, call out private preview status and any access gate. - If a task depends on org-level prerequisites (GitHub App install, org toggles, contexts), verify those first. ## Reference Map - [chunk-ui.md](references/chunk-ui.md): CircleCI app setup, provider onboarding, fix buttons, environment file/setup, and operational troubleshooting. - [chunk-cli.md](references/chunk-cli.md): Installation, command map, quick-start flows, auth/env variables, and platform constraints. ## Output Contract Provide: 1. Path chosen (UI, CLI, or mixed) and why. 2. Steps executed with exact command/UI actions. 3. Required prerequisites not yet met. 4. Concrete next action to finish the user’s goal.
© CircleCI · MIT · openai/plugins
