plugins/full-orchestration/skills/swe_status/SKILL.md
Show the current state of an /swe pipeline run. Use when checking pipeline progress, resuming after an interruption, or reviewing what stage a ticket has reached. Accepts a ticket ID or lists all active pipelines if no argument given.
npx skillsauth add shouenlee/ghcp-dev-plugin swe_statusInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Quick view of where a ticket is in the /swe pipeline.
/swe_status PROJ-123 # Status for a specific ticket
/swe_status # List all active pipelines
With ticket ID: Read .claude/swe-state/{ticket-id}.json. If not found, report "No pipeline state found for {ticket-id}" and exit.
Without ticket ID: List all .json files in .claude/swe-state/ (excluding subdirectories). For each, read and display a one-line summary: {ticket-id} | {current_stage} | {status}. If none found, report "No active pipelines" and exit. If multiple found, show the list and ask the user to pick one. If exactly one found, use it automatically.
Read the full state file and present:
## Pipeline: {ticket-id}
**Status:** {status} **Stage:** {current_stage} **Branch:** {feature_branch} → {target_branch}
### Stage Progress
| Stage | Status | Details |
|-------|--------|---------|
| Intake | {icon} | {details} |
| Spec | {icon} | {details} |
| Implement | {icon} | {details} |
| Review | {icon} | {details} |
| PR | {icon} | {details} |
donein progress (current_stage matches)pendingfailed / abortedIntake: ticket source and title (read ticket.json if it exists).
Spec: review iterations used. Example: spec review: 2/5 rounds, impl review: 1/5 rounds.
Implement: test result counts if available. Example: 12 new tests, suite PASS, 85% coverage.
Review: iteration count, phase, and findings summary. Example: 3/5 rounds, converged — 0 critical, 2 major fixed, 1 dismissed. If dismissed findings exist, list them: Dismissed: {id} — {summary} ({rationale}).
PR: PR URL if created. Example: #42 — https://github.com/org/repo/pull/42.
List all pipeline artifacts that exist on disk:
### Artifacts
- Ticket: .claude/swe-state/{ticket-id}/ticket.json
- Context: .claude/specs/{ticket-id}-context.md
- Spec: .claude/specs/{ticket-id}.md
- Impl Plan: .claude/specs/{ticket-id}-impl.md
- Impl Summary: .claude/swe-state/{ticket-id}/impl-summary.md
- Review: .claude/swe-state/{ticket-id}/review-iteration.json
- Review Summary: .claude/swe-state/{ticket-id}/review-summary.md
Only show files that actually exist. Read paths from the state file — do not hardcode them. Mark missing files that should exist for the current stage (e.g., spec file missing but spec stage is completed).
tools
Decomposes feature descriptions or GitHub issues into ordered subtasks with file-level scope, acceptance criteria, and optional gh issue create. Use when asked to "break down task", "decompose feature", "create subtasks", "plan implementation", "break this into tasks", "task list", or "implementation plan".
documentation
Generates changelogs from conventional commits, bumps semantic versions in pyproject.toml or package.json, and publishes GitHub releases. Use when asked to "create release", "release notes", "changelog", "bump version", "semantic version", "tag release", "publish release", or "what changed since last release".
development
Runs ruff, mypy, and bandit on changed Python files — explains violations and auto-fixes with ruff check --fix. Use when asked to "lint", "fix lint", "check types", "type check", "run mypy", "run ruff", "python quality", or "lint python files".
development
Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities with bundled resources. Generates SKILL.md files with proper frontmatter, directory structure, and optional scripts/references/assets folders.