Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    GitHub Actions Fetcher

    2

    Fetch recent CI/CD workflow runs, statuses, and logs links for any GitHub repository directly from your AI agent.

    Free

    Security scanned
    GitHub Actions Fetcher

    GitHub Actions Fetcher

    Example session with this skill installed

    Get the last 3 workflow runs for jusspound-netizen/context-bridge.

    • Read your context and instructions
    • Compiled the github actions fetcher

    I have fetched the 3 most recent workflow runs for the repository. All recent CI processes have completed.

    GitHub Actions Status: jusspound-netizen/context-bridge

    NameBranchStatusConclusionWorkflow URL
    CImaincompletedsuccessView Run
    LintingmaincompletedsuccessView Run
    DeploymaincompletedfailureView Run

    Next steps

    • Review the logs for the failed Deploy run using the provided URL.
    • Re-run the fetcher in 5 minutes if you trigger a new build.
    • Verify the GITHUB_PERSONAL_ACCESS_TOKEN has permission to view private logs if the link is inaccessible.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Your CI just went red. You open GitHub, click Actions, find the failed run, scroll to the failed step, read the log, copy the error, paste it back into your agent.

    This skill skips all of that.

    Ask your agent "what failed on the last CI run for owner/repo?" and it fetches the run, status, and the failing step's log link directly into the conversation. No tab-switching, no copy-paste, no context loss.

    What you get

    • SKILL.md — the skill definition your agent reads
    • scripts/run.py — the fetcher itself, stdlib-only, no pip install
    • reference/setup.md — how to create a GitHub token and point the skill at it

    Example

    You: "Why did CI fail on jusspound-netizen/context-bridge?"

    Agent: calls the skill, returns

    Run #42 — failure — failed step: "pytest tests/" Log: https://github.com/.../runs/42#step:3:12 Conclusion: 3 tests failed in test_parser.py

    Requires

    • A GitHub Personal Access Token with actions:read scope
    • Set as GITHUB_PERSONAL_ACCESS_TOKEN environment variable

    (The setup guide walks you through creating it in 2 minutes.)

    What it does not do

    • No network calls beyond the GitHub API you already trust
    • No dependencies — runs on a clean Python 3.9+ install
    • No data stored, no logs uploaded anywhere

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for DevOps & Cloud.

    Requires GITHUB_PERSONAL_ACCESS_TOKEN environment variable. Limited to repository-level workflow runs.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 2 days ago

    • Free with an Agensi account

    Accounts
    GitHub

    Needs a GitHub Personal Access Token (actions:read scope) set as GITHUB_PERSONAL_ACCESS_TOKEN. The 2-minute setup guide is in reference/setup.md.

    Permissions

    Terminal / Shell
    Network Access
    Environment Variables

    Allowed Hosts

    api.github.com
    Listed2 days ago
    Updatedtoday

    What's inside

    Frequently Asked Questions

    This skill eliminates the need to switch to a web browser to check CI/CD status, allowing you or your AI agent to monitor build health and identify failure points directly within your development environment.

    You will need a GitHub Personal Access Token (PAT) with 'repo' scope permissions configured as an environment variable to allow the skill to securely access your workflow data.

    Yes, provided your environment variable has the necessary permissions, the skill can retrieve and analyze workflow runs for both your private repositories and public ones.

    The skill returns a structured JSON list containing the run status, conclusion (success/failure), timestamp, and a direct URL to the full logs for deep-dive debugging.

    The skill is designed to be framework-agnostic and works with any AI agent or terminal environment that supports Python-based tool execution and environment variable management.

    New in DevOps & Cloud

    Free