Install and operate a full GitHub issue-to-merge workflow for any repository using event-driven and cron missions. Handles issue planning, PR monitoring, CI fixing, staging review, and post-merge learning.
64
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./skills/github-workflow/SKILL.mdInstall and maintain a complete issue-to-merge workflow for any GitHub repository. Maps GitHub webhook events and cron schedules into automated missions for planning, implementation, review, CI fixing, staging validation, and post-merge learning.
projects/<owner>-<repo>/project.md or ask the user.event_emit.Read these from the project file in workspace, or collect from the user:
repository: owner/repo (required)maintainers: GitHub handles allowed to trigger implement/replan actionsstaging_branch: default staging (or null if no staging workflow)main_branch: default mainbatch_interval_hours: default 8Before installing missions, verify:
POST /webhook/tools/github.github_webhook_secret.event_emit tool for testing.workflow-routines.md.{{repository}}, {{maintainers}}, branch names)wf-issue-plan-nearai-ironclaw)mission_create with name, goal (the prompt), and cadence (cron expression or event:<pattern>)mission_list), update rather than duplicate.staging_branch is null, skip wf-staging-batch-review.projects/<owner>-<repo>/project.md.mission_list.Install these missions per repository:
wf-issue-plan-<slug>: on issue.opened or issue.reopened, generate implementation plan comment.wf-maintainer-gate-<slug>: on maintainer comments, decide update-plan vs start implementation.wf-pr-monitor-<slug>: on PR open/sync/review-comment/review, address feedback and refresh branch.wf-ci-fix-<slug>: on CI status/check failures, apply fixes and push updates.wf-staging-review-<slug>: every N hours, review ready PRs, merge into staging, run batch correctness analysis, fix findings, then merge staging to main.wf-learning-<slug>: on merged PRs, extract mistakes/lessons and write to shared memory.Use top-level filters for stability:
repository_name (e.g., owner/repo)sender_login, comment_authorissue_number, pr_numberci_status, ci_conclusionreview_state, pr_mergedAfter install, run:
event_emit with a synthetic issue.opened payload for the target repo.b60038b
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.