debugging-workflows
This skill processes GitHub Actions logs to diagnose workflow failures and performance bottlenecks.
Install
mkdir -p .claude/skills/debugging-workflows && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/3224" && unzip -o skill.zip -d .claude/skills/debugging-workflows && rm skill.zipInstalls to .claude/skills/debugging-workflows
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Debug gh-aw workflows using run logs, audits, and failure triage.Key capabilities
- →Download workflow run logs and artifacts
- →Audit specific GitHub Actions workflow runs
- →Generate JSON summaries of workflow performance
- →Parse agent logs into Markdown reports
- →Visualize tool usage with Mermaid graphs
How it works
The skill interfaces with the GitHub CLI to fetch run artifacts and logs, then processes them to generate diagnostic reports and performance summaries.
Inputs & outputs
When to use debugging-workflows
- →Downloading logs for failed workflow runs
- →Auditing specific GitHub Actions executions
- →Identifying bottlenecks in agentic workflows
- →Troubleshooting workflow configuration issues
About this skill
Workflow Debugging Router
This skill remains available for existing invocations. Load and follow the evidence reference, where the instructions now live. It delegates setup to the bootstrap and execution policy to the shared strategy.
Use a matching local guidance checkout. For Contents API reads, use the guidance
owner/repository (owner=github, repo=gh-aw by default),
path=.github/aw/debug-workflow-evidence.md, retaining the ref of this skill.
The other API paths are .github/aw/debug-bootstrap.md and
.github/aw/debug-agentic-workflow.md. Normalize relative links against their
containing file before API reads; ../../aw/... is not an API path.
For default raw guidance, use https://raw.githubusercontent.com/github/gh-aw/<guidance-ref>/
plus the repository-root-relative path, including .github/. Preserve supplied
refs containing slashes and keep guidance identity separate from the target
workflow repository/ref. The bootstrap documents size-aware reads and public
raw fallback after API denial.
Read the canonical instructions before running commands. This compatibility router defines no separate setup, review, or live-execution procedure.
When not to use it
- →Debugging non-GitHub Actions workflows
- →Modifying workflow configuration files directly
Prerequisites
Limitations
- →Requires active GitHub Actions workflow runs
- →Limited to GitHub-hosted workflow logs
How it compares
Unlike manual log inspection, this skill automates the collection and parsing of agent-specific artifacts like safe_output.jsonl and tool usage metrics.
Compared to similar skills
debugging-workflows side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| debugging-workflows (this skill) | 1 | 6mo | Review | Intermediate |
| sentry-release-management | 1 | 4mo | Caution | Intermediate |
| analyzing-logs | 14 | 4mo | Review | Beginner |
| service-mesh-observability | 5 | 5mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by githubnext
View all by githubnext →You might also like
sentry-release-management
jeremylongshore
Manage Sentry releases and associate commits. Use when creating releases, tracking commits, or managing release artifacts. Trigger with phrases like "sentry release", "sentry commits", "manage sentry versions", "sentry release workflow".
analyzing-logs
jeremylongshore
Analyze application logs to detect performance issues, identify error patterns, and improve stability by extracting key insights.
service-mesh-observability
wshobson
Implement comprehensive observability for service meshes including distributed tracing, metrics, and visualization. Use when setting up mesh monitoring, debugging latency issues, or implementing SLOs for service communication.
sentry
openai
Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.
obsidian-incident-runbook
jeremylongshore
Troubleshoot Obsidian plugin failures with systematic incident response. Use when plugins crash, data is corrupted, or users report critical issues with your Obsidian plugin. Trigger with phrases like "obsidian crash", "obsidian plugin broken", "obsidian incident", "debug obsidian failure", "obsidian emergency".
gh-fix-ci
openai
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.