Coding-agent skills for pull-request work and orchestration: an adversarial multi-pass PR reviewer, PR description and title writing, answering review comments, CI failure triage and PR nursing, a DAG orchestrator that delegates to cheaper subagents, and file-channel coordination between agents. Supports GitHub and GitLab.
95%
Does it follow best practices?
Impact
98%
1.88xAverage score across 10 eval scenarios
Low
Low-risk findings worth noting
Platform-specific commands for investigating CI failures on GitHub Actions.
The repository uses GitHub Actions if .github/workflows/ exists.
gh pr view --json number,title,headRefName,statusCheckRollupgh run view <run-id> --json jobs --jq '.jobs[] | select(.conclusion == "failure") | {name, conclusion}'gh run view <run-id> --log-failedUse the run count N from the skill (default: 10) as the --limit value, filtering to completed runs on other branches:
gh run list --repo <org>/<repo> --limit <N> \
--json databaseId,conclusion,workflowName,headBranch \
--jq '[.[] | select(.workflowName == "<workflow>" and .conclusion != "" and .headBranch != "<current-branch>")] | .[0:5]'gh run view <id> --json jobs --jq '.jobs[] | select(.name | test("<failing-job-pattern>")) | {name, conclusion}'gh pr diff