plugins/spectre/skills/spectre-ship/SKILL.md
--- name: spectre-ship description: 👻 | Autonomous end-to-end: brain dump -> scope -> TDD -> commit -> rebase -> PR user-invocable: true --- # ship ## Input Handling Treat the current command arguments as this workflow's input. When invoked from a slash command, use the forwarded `$ARGUMENTS` value. # ship: Autonomous End-to-End Delivery Take a brain dump and autonomously produce a reviewable PR. Zero confirmation gates — scope, implement with TDD, sweep, rebase, and open a PR. **Executio
npx skillsauth add codename-inc/spectre plugins/spectre/skills/spectre-shipInstall 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.
Treat the current command arguments as this workflow's input. When invoked from a slash command, use the forwarded $ARGUMENTS value.
Take a brain dump and autonomously produce a reviewable PR. Zero confirmation gates — scope, implement with TDD, sweep, rebase, and open a PR.
Execution Style: Fully autonomous. No user approval gates. Parse intent, build it, ship the PR.
<ARGUMENTS> $ARGUMENTS </ARGUMENTS>
INTENT_TYPE: feat or fix (infer from context — new behavior = feat, broken behavior = fix)TARGET_BRANCH: Extract if specified (e.g., "rebase onto develop"), default origin/mainSCOPE_SUMMARY: 1-2 sentence distillation of what to build/fixRELEVANT_FILES: Any files, components, or areas mentionedCONTEXT: Remaining context, constraints, preferencesgit rev-parse --abbrev-ref HEAD
main, not master) → use current context, proceedmain or master → use EnterWorktree to create an isolated worktreeBRANCH_NAME for artifact pathsAction — DispatchResearch: Spawn parallel lightweight agents:
@spectre:finder — Locate files related to RELEVANT_FILES and SCOPE_SUMMARY@spectre:analyst — Understand the relevant code area, key interfaces, existing patternsAction — WriteScopeDoc: Create docs/tasks/{BRANCH_NAME}/concepts/scope.md:
# Scope: {SCOPE_SUMMARY}
## Objective
{1-2 sentences from brain dump}
## Type
{feat or fix}
## In Scope
- {bullet list of what will be done}
## Out of Scope
- {what this explicitly won't touch}
## Target Branch
{TARGET_BRANCH}
## Key Files
{from research — relevant files and their roles}
Keep it ~20 lines. This is a lightweight scope, not full /spectre:scope.
TaskCreate to create 3-8 tasks proportional to scope complexity.
subject (imperative), description (what to do + acceptance criteria), activeForm (present continuous)Action — ExecuteLoop: For each task sequentially:
TaskUpdate → in_progress@skill-spectre:spectre-tdd for TDD methodology{INTENT_TYPE}({scope}): {description}TaskUpdate → completedRules:
Inline sweep — same checklist as /spectre:sweep, no subagents:
chore({scope}): sweep cleanupgit fetch origingit branch backup/ship-$(date +%Y%m%d-%H%M%S)git rebase {TARGET_BRANCH}
Action — PushBranch: git push -u origin {BRANCH_NAME}
Action — CreatePR: gh pr create with:
Title: {INTENT_TYPE}({scope}): {SCOPE_SUMMARY} (under 70 chars)
Body:
## Summary
{From scope doc — objective and what was done}
## Changes
{Bulleted list derived from completed tasks}
## Test Plan
{Bulleted checklist — what was tested, what to verify manually}
Shipped autonomously via `/spectre:ship`
Action — OutputPRUrl: Display the PR URL as the final deliverable
Use @skill-spectre:spectre-guide skill to render the Next Steps footer.
testing
👻 | Independent multi-lens review of plan.md and/or tasks.md — finds overengineering, missing verification, hallucinated deps, weak references
data-ai
👻 | Unified planning entry point - researches, assesses complexity, routes to workflow - primary agent
data-ai
👻 | Transform requirements into executable tasks - primary agent
testing
👻 | Independent multi-lens review of plan.md and/or tasks.md — finds overengineering, missing verification, hallucinated deps, weak references