con un clic
process-issues
// Process open Linear issues — pick up, fix, and ship one PR per issue. Use when the user asks to process issues, work on Linear issues, tackle the backlog, or fix open issues.
// Process open Linear issues — pick up, fix, and ship one PR per issue. Use when the user asks to process issues, work on Linear issues, tackle the backlog, or fix open issues.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Goal-oriented repository maintenance and release-readiness work. Use when the user asks for maintenance, release prep, repo health review, dependency refreshes, spec/docs alignment, test gap review, technical debt analysis, or general cleanup without prescribing an exact sequence.
Run manual UI test cases using agent-browser against a running stack. Use when the user asks to run UI tests, test the UI, run manual tests, or verify UI behavior.
Goal-oriented workflow for landing a requested change safely. Use when the user asks to ship, fix and ship, take a change through validation, or drive PR/CI/merge to completion.
Take UI screenshots using agent-browser. Use this skill to capture visual state of UI components for code review, visual regression testing, or documentation.
Reference for working with the Everruns(Dev) managed harnesses platform (https://dev.everruns.com) - core concepts, UI links, entity naming, and API workflows for agents, harnesses, capabilities, sessions, models, and apps.
| name | process-issues |
| description | Process open Linear issues — pick up, fix, and ship one PR per issue. Use when the user asks to process issues, work on Linear issues, tackle the backlog, or fix open issues. |
| metadata | {"internal":true} |
| user-invocable | true |
Goal: resolve open Linear issues from the OSS project by shipping one merged PR per issue, with full /ship quality.
This skill is outcome-oriented. Do not blindly walk a fixed checklist. Start from the issue backlog, pick the highest-value work, and drive each issue to a merged PR.
See specs/issue-tracking.md for project scope and prerequisites.
Use this skill when the user asks to:
$ARGUMENTS — Optional: specific issue IDs, priority filter, or project override (defaults to OSS project)One PR per issue, always.
{issue-id}-{short-description} from origin/main (lowercase kebab-case).Each PR ships via the /ship skill.
/ship using the Skill tool — never duplicate its logic (validation, PR creation, CI checks, merge)./ship owns the full shipping lifecycle: diff review, simplification, security review, artifact sync, evidence gathering, PR creation, CI wait, and squash merge./ship required outcomes: goal met, validation matches risk, artifacts updated, CI green, PR merged safely.Issues are fully resolved or explicitly skipped.
/ship, issue marked Done in Linear with a comment linking the merged PR.Ownership is checked before pickup.
updatedAt, recent comments, and linked PRs to detect active ownership.updatedAt is older than 1 day, raise it to the human user as a stale-ownership conflict. Do not auto-take over, auto-reassign, or silently reset the issue.Sequential merging prevents conflicts.
/ship merges each PR, rebase remaining open PRs onto updated main before shipping the next.Cargo.toml workspace deps, the second merge can create duplicate key errors — rebase catches this.A summary report is delivered.
Verify environment before starting:
doppler run -- env | rg 'LINEAR_API_KEY|GITHUB_TOKEN'
doppler run -- bash -lc 'GH_TOKEN="$GITHUB_TOKEN" gh auth status'
Linear MCP server must be configured in .mcp.json.
$ARGUMENTS filters if provided)updatedAt, recent comments, and linked PRsFor each issue, process up to 5 concurrently using subagents:
git fetch origin main && git checkout -b {issue-id}-{short-description} origin/mainfix(core): resolve X — Fixes EVE-123)/ship skill — invoke /ship using the Skill tool to handle validation, PR creation, CI, and merge. Do NOT duplicate /ship logic (validation, PR creation, merge sequencing) inline — always delegate.
/ship owns: diff review, simplification, security review, artifact sync, evidence gathering, PR creation, CI wait, and merge/ship completes merge: mark issue Done in Linear, add comment with merged PR linkWhen multiple issues produce PRs, merge sequentially (not in parallel):
/ship merge the first PR (CI must be green)main, push, then invoke /ship for that PRSkip an issue if:
Leave a Linear comment explaining the skip only when the current run actively investigated the issue and the skip is due to a blocker, missing clarification, or missing access. Do not leave an automated Linear comment for ownership-only skips: if the issue is already In Progress and stale, raise it to the human user for a takeover decision instead.
/ship via the Skill tool for validation, PR, CI, and merge. Never inline /ship logic or skip shipping steps