AGENT SKILL

GitHub CI Fix Debugging

Debug and fix failing GitHub PR checks by inspecting GitHub Actions logs, summarizing failure context, drafting fix plans, and implementing fixes after approval.

License 许可
MIT
最近更新
2026-11-04
Stars
★ 0
Forks
0

01 前言 Front Matter

name
GitHub CI Fix Debugging
tags
[ "github-actions", "ci", "debugging", "pr-checks", "fix" ]
agents
[ "claude-code", "cursor", "github-copilot", "windsurf", "codex", "aider", "continue", "cline", "zed", "bolt" ]
author
openai
domains
[ "devops" ]
license
MIT
version
1.0.0
languages
[ "yaml", "typescript", "javascript", "python" ]
frameworks
[ "github-actions" ]
description
Debug and fix failing GitHub PR checks by inspecting GitHub Actions logs, summarizing failure context, drafting fix plans, and implementing fixes after approval.
testingTypes
[ "integration" ]

03 SKILL.md 正文

GitHub CI Fix Debugging

Use gh CLI to locate failing PR checks, fetch GitHub Actions logs for actionable failures, summarize the failure, propose a fix plan, and implement after explicit approval.

Prerequisites

Authenticate with the GitHub CLI:

gh auth login  # Ensure repo + workflow scopes
gh auth status  # Verify authentication

Workflow

1. Verify Authentication

gh auth status

If unauthenticated, ask the user to run gh auth login with repo + workflow scopes.

2. Resolve the PR

# Current branch PR
gh pr view --json number,url

# Or use a specific PR number
gh pr checks <pr-number>

3. Inspect Failing Checks

# List all PR checks with status
gh pr checks <pr> --json name,state,bucket,link,startedAt,completedAt,workflow

# For each failing check, get the run details
gh run view <run_id> --json name,workflowName,conclusion,status,url

# Fetch the logs
gh run view <run_id> --log

4. Scope Non-GitHub Actions Checks

  • If detailsUrl is not a GitHub Actions run, label it as external
  • Only report the URL for external providers (Buildkite, etc.)

5. Summarize Failures

For each failing check, provide:

  • The failing check name
  • The run URL
  • A concise log snippet showing the actual failure
  • Root cause analysis

6. Create a Fix Plan

Draft a concise plan including:

  • What failed and why
  • Proposed fix with specific file changes
  • Impact assessment
  • Request explicit approval before implementing

7. Implement After Approval

  • Apply the approved plan
  • Summarize diffs and changes made
  • Run relevant tests locally if possible

8. Recheck Status

# After fixes, verify checks pass
gh pr checks <pr>

Common CI Failure Patterns

Test Failures

  • Check test output for assertion errors
  • Look for environment-specific issues
  • Verify test data and fixtures

Build Failures

  • Check dependency versions and lockfiles
  • Verify TypeScript/compilation errors
  • Check for missing environment variables

Lint/Format Failures

  • Run linter locally to reproduce
  • Apply auto-fix where possible
  • Check for new rule violations

Timeout Issues

  • Identify slow tests or builds
  • Check for infinite loops or deadlocks
  • Consider increasing timeout or optimizing

04 同仓库更多 Skills

GrupoANDevelopment-m
GrupoANDevelopment-m/alberto-ai

nemoclaw-user-reference

Describes the NemoClaw integration layer and blueprint architecture and how they orchestrate compatible agent sandboxes. Use when looking up architecture, agent integration, plugin structure, or blueprint design. Trigger keywords - nemoclaw architecture, nemoclaw agent architecture, nemoclaw plugin blueprint structure, nemoclaw vs openshell, which cli, nemoclaw cli, openshell cli, sandbox commands, nemoclaw cli commands, nemoclaw command reference, nemoclaw network policy, sandbox egress control operator approval, nemoclaw troubleshooting, nemoclaw debug sandbox issues.

★ 0
GrupoANDevelopment-m
GrupoANDevelopment-m/alberto-ai

nemoclaw-user-overview

Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when to prefer NemoClaw versus integrating OpenShell and OpenClaw directly. Use when users ask about the relationship between OpenClaw, OpenShell, and NemoClaw, or when to use NemoClaw versus OpenShell. Trigger keywords - nemoclaw ecosystem, openclaw openshell, nemoclaw vs openshell, sandboxed openclaw, how nemoclaw works, nemoclaw sandbox lifecycle blueprint, nemoclaw overview, openclaw always-on assistants, nvidia openshell, nvidia nemotron, nemoclaw release notes, nemoclaw changelog.

★ 0
GrupoANDevelopment-m
GrupoANDevelopment-m/alberto-ai

nemoclaw-user-monitor-sandbox

Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox logs. Trigger keywords - monitor nemoclaw sandbox, debug nemoclaw agent issues.

★ 0
GrupoANDevelopment-m
GrupoANDevelopment-m/alberto-ai

nemoclaw-user-manage-sandboxes

Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential reset, rebuilds, network presets, upgrades, and uninstall. Trigger keywords - manage nemoclaw sandboxes, nemoclaw status, nemoclaw list, nemoclaw dashboard port, nemoclaw rebuild, nemoclaw upgrade sandboxes, nemoclaw uninstall, sandbox mutability, sandbox runtime configuration, sandbox rebuild, nemoclaw backup, nemoclaw restore, workspace backup, openshell sandbox download upload, nemoclaw messaging channels, nemoclaw telegram, nemoclaw discord, nemoclaw slack, nemoclaw wechat, nemoclaw whatsapp, openshell channel messaging, nemoclaw workspace files, soul.md, user.md, identity.md, agents.md, sandbox persistence.

★ 0
GrupoANDevelopment-m
GrupoANDevelopment-m/alberto-ai

nemoclaw-user-manage-policy

Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint access. Trigger keywords - customize nemoclaw network policy, sandbox egress policy configuration, nemoclaw integration policy examples, post-install policy setup, openshell approval workflow, policy preset, nemoclaw approve network requests, sandbox egress approval tui.

★ 0
GrupoANDevelopment-m
GrupoANDevelopment-m/alberto-ai

nemoclaw-user-get-started

Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time. Trigger keywords - nemoclaw quickstart, install nemoclaw openclaw sandbox, nemohermes quickstart, hermes agent nemoclaw, run hermes openshell sandbox, nemoclaw prerequisites, nemoclaw supported platforms, nemoclaw hardware software, nemoclaw windows wsl2 setup, nemoclaw install windows docker desktop.

★ 0