La interfaz está localizada; las descripciones y documentos de las Skills se traducen automáticamente con IA a su idioma. El código, los comandos, rutas y términos técnicos se mantienen en el original, y prevalece el documento del autor.
Explorar Skills
Desarrollo · SKILL.md

do-issue

do-issue

Implements GitHub or GitLab issues via parallel subagents with review gates between task batches. Use when resolving multi-step issues end-to-end.

Independent GitHub snapshot · Automated classification · Original documentation governs

Documentación de la Skill

GitHub

name: do-issue role: entrypoint description: Implements GitHub or GitLab issues via parallel subagents with review gates between task batches. Use when resolving multi-step issues end-to-end. alwaysApply: false category: workflow-automation tags:

  • github
  • gitlab
  • issues
  • subagents
  • parallel
  • automation
  • cross-platform dependencies:
  • leyline:git-platform
  • superpowers:subagent-driven-development
  • superpowers:writing-plans
  • superpowers:test-driven-development
  • superpowers:requesting-code-review
  • superpowers:finishing-a-development-branch tools: [] usage_patterns:
  • issue-discovery
  • task-planning
  • parallel-execution
  • quality-gates complexity: advanced model_hint: deep estimated_tokens: 2500 modules:
  • modules/issue-discovery.md
  • modules/task-planning.md
  • modules/parallel-execution.md
  • modules/quality-gates.md
  • modules/completion.md
  • modules/troubleshooting.md

When NOT To Use

  • A single-file fix obvious enough to make directly
  • Preparing the PR once the work is done (use sanctum:pr-prep)

Fix Issue(s)

Retrieves issue content from the detected git platform (GitHub, GitLab, or Bitbucket) and uses subagent-driven-development to systematically address requirements, executing tasks in parallel where dependencies allow.

Platform detection is automatic via the leyline:git-platform SessionStart hook. Check session context for git_platform: to determine which CLI to use.

Key Features

  • Cross-Platform: Automatically detects GitHub/GitLab/Bitbucket and uses appropriate CLI
  • Flexible Input: Single issue number, platform URL, or space-delimited list
  • Parallel Execution: Independent tasks run concurrently via subagents
  • One PR: All issues produce one consolidated PR (never per-issue PRs)
  • Quality Gates: Code review between task groups
  • Fresh Context: Each subagent starts with clean context for focused work

Workflow Overview

PhaseDescriptionModule
1. DiscoveryParse input, fetch issues, extract requirementsissue-discovery
2. PlanningAnalyze dependencies, create task breakdowntask-planning
3. ExecutionDispatch parallel subagents for independent tasksparallel-execution
4. QualityCode review gates between task batchesquality-gates
5-6. CompletionSequential tasks, final review, issue updatescompletion

Required TodoWrite Items

  1. do-issue:discovery-complete
  2. do-issue:tasks-planned
  3. do-issue:parallel-batch-complete
  4. do-issue:review-passed
  5. do-issue:sequential-complete
  6. do-issue:issues-updated

Forge CLI Commands

Use the platform detected in session context (git_platform:). See Skill(leyline:git-platform) for full mapping.

OperationGitHub (gh)GitLab (glab)
Fetch issuegh issue view <N> --json title,body,labels,commentsglab issue view <N>
Commentgh issue comment <N> --body "msg"glab issue note <N> --message "msg"
Closegh issue close <N> --comment "reason"glab issue close <N>
Searchgh issue list --search "query"glab issue list --search "query"

Verification: Run the command with --help flag to verify availability.

Agent Teams (Default Execution Mode)

Agent teams is the default parallel execution backend for do-issue. Teammates coordinate via filesystem-based messaging, enabling real-time communication when shared files or dependencies are discovered mid-implementation.

Automatic downgrade: For single issues with --scope minor, agent teams is skipped (Task tool or inline execution is used instead). Use --no-agent-teams to force Task tool dispatch for any invocation.

Requires: Claude Code 2.1.32+, tmux, CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. If prerequisites are missing, silently falls back to Task tool dispatch.

# Agent teams configuration
fix_issue:
  agent_teams:
    enabled: true           # on by default; --no-agent-teams to disable
    max_teammates: 4        # limit concurrent workers
    model: sonnet           # teammate model (lead uses current model)
    auto_downgrade: true    # skip agent teams for --scope minor

See modules/parallel-execution.md for detailed agent teams patterns.

Configuration

fix_issue:
  parallel_execution: true
  max_parallel_subagents: 3
  review_between_batches: true
  auto_close_issues: false
  commit_per_task: true

Verification: Run the command with --help flag to verify availability.

Detailed Resources

Exit Criteria

  • All 6 required TodoWrite items (do-issue:discovery-complete through do-issue:issues-updated) are created before execution starts and each marked complete when its phase finishes
  • Issue requirements fetched using the correct forge CLI (gh for GitHub, glab for GitLab) as detected in session context
  • Exactly one consolidated PR is opened covering all issues; no per-issue PRs are created
  • Code review gate runs between parallel task batches and must pass before the next batch is dispatched
  • All specified issues are commented on or closed with a reference to the PR after it is ready for review
Skills guardadas