// Use when given a GitHub issue number and base branch to implement end-to-end
Use when creating new agents, editing existing agents, or defining specialized subagent roles for the Task tool
Trigger the issue triage workflow for a specific issue. Usage: /triage {issue_number}
Use after resolving a bug, failed task, or unexpected agent behavior to improve the pipeline skills, agents, hooks, or scripts that contributed to the problem. Also proactively suggest improvements when recurring patterns or inefficiencies are observed.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Install build and extraction tools needed for building Claude Desktop Debian packages
Run shellcheck and actionlint on shell scripts and GitHub Actions workflows. Use before pushing or when fixing lint issues.
| name | implement-issue |
| description | Use when given a GitHub issue number and base branch to implement end-to-end |
| argument-hint | [issue-number] [base-branch] |
End-to-end issue implementation via orchestrator script.
Announce at start: "Using implement-issue to run orchestrator for #$ISSUE against $BRANCH"
Arguments:
$1 — GitHub issue number (required)$2 — Base branch name (required)Immediately launch the orchestrator:
.claude/scripts/implement-issue-orchestrator.sh \
--issue $ISSUE_NUMBER \
--branch $BASE_BRANCH
Or with explicit agent override:
.claude/scripts/implement-issue-orchestrator.sh \
--issue $ISSUE_NUMBER \
--branch $BASE_BRANCH \
--agent patch-engineer
Check progress via status.json:
jq . status.json
Watch live:
watch -n 5 'jq -c "{state,stage:.current_stage,task:.current_task,quality:.quality_iterations}" status.json'
| Stage | Agent | Description |
|---|---|---|
| setup | default | fetch, worktree, research, evaluate, plan |
| implement | per-task | execute each task from plan |
| task-review | spec-reviewer | verify task achieved goal |
| fix | per-task | address review findings |
| simplify | cdd-code-simplifier | clean up code |
| test | bats-test-validator | run test suite (shellcheck + BATS) |
| lint | default | run shellcheck and actionlint |
| review | code-reviewer | internal code review |
| pr | default | create/update PR |
| spec-review | spec-reviewer | verify PR achieves issue goals |
| code-review | code-reviewer | final code quality check |
| complete | default | post summary |
Located in .claude/scripts/schemas/implement-issue-*.json
Logs written to logs/implement-issue/issue-N-timestamp/:
orchestrator.log — main logstages/ — per-stage Claude outputcontext/ — parsed outputs (tasks.json, etc.)status.json — final status snapshot| Code | Meaning |
|---|---|
| 0 | Success, PR created and approved |
| 1 | Error during a stage |
| 2 | Max iterations exceeded |
| 3 | Configuration/argument error |
Tasks are assigned to specialist agents based on the issue type:
| Agent | Use For |
|---|---|
| patch-engineer | Minified JS patches in build.sh, sed/regex patterns |
| packaging-specialist | .deb, .rpm, AppImage packaging, control files |
| electron-linux-specialist | BrowserWindow, Wayland/X11, DBus tray, native theme |
| ci-workflow-architect | GitHub Actions workflows, release automation |
| bash-script-craftsman | Shell scripts, launcher, build system |
Called by handle-issues via batch-orchestrator.sh.