LabscoConnect MCP ↗
openai logo✓ Official★ 4,000

circleci-cli

Runs and troubleshoots CircleCI from its command-line tool: checking pipeline, workflow and job status, finding the first failing step, validating your config file locally, and rerunning or triggering pipelines. It reads before it changes anything, and confirms the organisation and project before any rerun or trigger.

by openaipart of openai/plugins
🔥🔥🔥 ✓ VerifiedFreeQuick setup#automation#git

This skill ships inside the OpenAI-Curated Plugins plugin — install the plugin and you also get 40 slash commands, 3 agents, hooks and an MCP server.

WHEN YOUR AGENT SHOULD USE IT

A QUICK BOUNDARY

USE FOR

  • Find which job and step broke a failing pipeline.
  • Validate a CircleCI config file before committing it.
  • Rerun only the failed workflow or job.
  • Trigger a pipeline on a branch with set parameters.

DO NOT USE FOR

  • Reading cloud job logs when the CLI has no logs command: use the CircleCI web app or CircleCI's MCP tools for those.

Documents

This is the playbook your agent receives when the skill activates — you don't need to read it to use the skill, but it's here to audit before installing.

CircleCI CLI

Overview

Use this skill when the fastest path is CircleCI CLI-driven operations rather than editing config first. Prioritize safe, read-first diagnostics, then run targeted mutating commands only after confirming scope.

Inputs To Gather
  • Repository path and target branch
  • CircleCI project slug (if needed)
  • Whether objective is inspect, rerun, trigger, or validate
  • Required token/auth state and org permissions
Workflow
  1. Verify CLI and auth state.
    • Confirm circleci is installed and version is available.
    • Confirm token/auth before issuing remote CircleCI commands.
  2. Run read-only diagnostics first.
    • Inspect available pipeline/project/trigger state and capture concrete identifiers.
    • Extract first failing scope and step details from supported command output before rerun/trigger actions.
  3. Validate config locally when relevant.
    • Run config validation/processing commands before committing risky edits.
  4. Run targeted mutation commands.
    • Rerun only required workflow/job scope.
    • Trigger pipelines with explicit parameters and branch context.
  5. Report results and next action.
    • Provide exact command results, remaining blockers, and safest follow-up.
Guardrails
  • Prefer read-only commands before rerun/trigger/cancel operations.
  • Confirm organization/project scope before mutating pipeline state.
  • Never print raw secret values from environment variables or tokens.
  • If permissions fail, report exact auth/scope gap and safest remediation.
  • Respect installed CLI capabilities and avoid inventing commands.
  • Do not use circleci api, circleci workflow, or other unavailable legacy commands unless circleci help confirms they exist.
Installed CLI Compatibility

For newer circleci builds that expose domain subcommands (for example pipeline, project, trigger) but not api:

  • Verify available commands first with circleci help.
  • Use only discovered subcommands from help output.
  • Prefer circleci pipeline list|create|run and circleci trigger ... for pipeline operations.
  • For cloud job logs, use supported platform tools (CircleCI app/UI or connected CircleCI MCP tooling) if the CLI does not expose a logs command.
Output Contract

Provide:

  1. Commands run and purpose.
  2. Key outputs (pipeline/workflow/job ids, status, failing step).
  3. Actions taken (rerun/trigger/validate) and why.
  4. Remaining blockers and next recommended CLI command.

Installation

Copy & paste — that's it
npx skills add openai/plugins --skill "circleci-cli" --full-depth

Run this in your project — your agent picks the skill up automatically.

BEFORE IT WILL WORK

1 FOR YOU
  1. 01
    The CircleCI command-line tool, signed in

    The CircleCI command-line tool installed and signed in with a token that can reach your organisation and project.