
👻 | Unified planning entry point - researches, assesses complexity, routes to workflow - primary agent
👻 | Independent multi-lens review of plan.md and/or tasks.md — finds overengineering, missing verification, hallucinated deps, weak references
👻 | Independent multi-lens review of plan.md and/or tasks.md — finds overengineering, missing verification, hallucinated deps, weak references
👻 | Unified planning entry point - researches, assesses complexity, routes to workflow - primary agent
👻 | Transform requirements into executable tasks - primary agent
👻 | Transform requirements into executable tasks - primary agent
👻 | Interactively scope a feature or improvement, generating a complete Scope document with IN, OUT, and ANTI-SCOPE boundaries -- primary agent
Use when rendering the Next Steps footer after any spectre command, suggesting next actions, or when users need guidance on which SPECTRE command to run.
👻 | Risk-aware test coverage & commit - primary agent
Load this skill when executing TDD (Test-Driven Development) methodology. Use when implementing features via strict RED-GREEN-REFACTOR cycles, or when a prompt instructs execution via TDD.
👻 | Interactively scope a feature or improvement, generating a complete Scope document with IN, OUT, and ANTI-SCOPE boundaries -- primary agent
👻 | Project kickoff with deep research & MVP pathfinding - primary agent
👻 | Quickly scope, research, & plan s/m tasks - primary agent
👻 | Create implementation plan from PRD - primary agent
Use when starting implementation, debugging, or feature work on a project with captured knowledge.
👻 | Research codebase with parallel agents - primary agent
👻 | Conduct principal architecture review
👻 | Complete cleanup flow - clean, inspect, lint, test - primary agent
👻 | Architecture review + knowledge capture
👻 | Generate right-sized manual test guides - primary agent
👻 | Define user flows, components, and UX behavior — generates the UX spec for a feature - primary agent
👻 | Generate right-sized manual test guides - primary agent
👻 | Generate a self-contained HTML prototype to validate a feature visually before planning - primary agent
👻 | Risk-aware test coverage & commit - primary agent
👻 | Light pass cleanup - clean, lint, test, commit
👻 | Define user flows, components, and UX behavior — generates the UX spec for a feature - primary agent
👻 | Autonomous end-to-end: brain dump -> scope -> TDD -> commit -> rebase -> PR
Clear session memory - archive all session files so next session starts fresh
👻 | Research codebase with parallel agents - primary agent
👻 | Architecture review + knowledge capture
👻 | Conduct principal architecture review
👻 | Create implementation plan from PRD - primary agent
👻 | Quickly scope, research, & plan s/m tasks - primary agent
👻 | Adaptive Wave-Based Build with Per-Wave Verification Gate
👻 | Complete cleanup flow - clean, inspect, lint, test - primary agent
👻 | Independent LLM Code Review - subagent
Save state snapshot to session_logs for session resume
Clear session memory - archive all session files so next session starts fresh
👻 | Comprehensive post implementation requirement validation using subagents
👻 | Safe guided rebase w/conflict handling - primary agent
Use when rendering the Next Steps footer after any spectre command, suggesting next actions, or when users need guidance on which SPECTRE command to run.
👻 | Project kickoff with deep research & MVP pathfinding - primary agent
👻 | Generate a self-contained HTML prototype to validate a feature visually before planning - primary agent
👻 | Independent LLM Code Review - subagent
👻 | Adaptive Wave-Based Build with Per-Wave Verification Gate
Investigate bugs & implement fixes - primary agent
👻 | Safe guided rebase w/conflict handling - primary agent
Use when user invokes /learn or wants to save patterns, decisions, gotchas, procedures, or feature knowledge from a conversation for later re-use. Look for user requests like "please remember" or "what did we learn from this?".
Investigate bugs & implement fixes - primary agent
👻 | Search Project Knowledge
👻 | Light pass cleanup - clean, lint, test, commit
👻 | Search Project Knowledge
Save state snapshot to session_logs for session resume
--- 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
👻 | Comprehensive post implementation requirement validation using subagents
👻 | Independent multi-lens review of plan.md and/or tasks.md — finds overengineering, missing verification, hallucinated deps, weak references
👻 | Independent multi-lens review of plan.md and/or tasks.md — finds overengineering, missing verification, hallucinated deps, weak references
👻 | Generate a self-contained HTML prototype to validate a feature visually before planning - primary agent
👻 | Define user flows, components, and UX behavior — generates the UX spec for a feature - primary agent
👻 | Define user flows, components, and UX behavior — generates the UX spec for a feature - primary agent
👻 | Create implementation plan from PRD - primary agent
👻 | Adaptive Wave-Based Build with Per-Wave Verification Gate
👻 | Independent LLM Code Review - subagent
👻 | Unified planning entry point - researches, assesses complexity, routes to workflow - primary agent
Use when rendering the Next Steps footer after any spectre command, suggesting next actions, or when users need guidance on which SPECTRE command to run.
👻 | Independent LLM Code Review - subagent
👻 | Transform requirements into executable tasks - primary agent
Use when rendering the Next Steps footer after any spectre command, suggesting next actions, or when users need guidance on which SPECTRE command to run.
👻 | Interactively scope a feature or improvement, generating a complete Scope document with IN, OUT, and ANTI-SCOPE boundaries -- primary agent
👻 | Unified planning entry point - researches, assesses complexity, routes to workflow - primary agent
👻 | Generate a self-contained HTML prototype to validate a feature visually before planning - primary agent
👻 | Interactively scope a feature or improvement, generating a complete Scope document with IN, OUT, and ANTI-SCOPE boundaries -- primary agent
👻 | Transform requirements into executable tasks - primary agent
👻 | Adaptive Wave-Based Build with Per-Wave Verification Gate
👻 | Create implementation plan from PRD - primary agent
Load this skill when executing TDD (Test-Driven Development) methodology. Use when implementing features via strict RED-GREEN-REFACTOR cycles, or when a prompt instructs execution via TDD.
👻 | Complete cleanup flow - clean, inspect, lint, test - primary agent
👻 | Search Project Knowledge
👻 | Generate right-sized manual test guides - primary agent
👻 | Safe guided rebase w/conflict handling - primary agent
👻 | Light pass cleanup - clean, lint, test, commit
👻 | Comprehensive post implementation requirement validation using subagents
👻 | Risk-aware test coverage & commit - primary agent
👻 | Quickly scope, research, & plan s/m tasks - primary agent
👻 | Autonomous end-to-end: brain dump -> scope -> TDD -> commit -> rebase -> PR
Use when starting implementation, debugging, or feature work on a project with captured knowledge.
👻 | Project kickoff with deep research & MVP pathfinding - primary agent
Clear session memory - archive all session files so next session starts fresh
👻 | Project kickoff with deep research & MVP pathfinding - primary agent
Save state snapshot to session_logs for session resume
Investigate bugs & implement fixes - primary agent
👻 | Quickly scope, research, & plan s/m tasks - primary agent
👻 | Architecture review + knowledge capture
👻 | Light pass cleanup - clean, lint, test, commit
👻 | Conduct principal architecture review
👻 | Search Project Knowledge
👻 | Risk-aware test coverage & commit - primary agent
Use when starting implementation, debugging, or feature work on a project with captured knowledge.
👻 | Research codebase with parallel agents - primary agent
--- name: 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. **Execution Style*
Save state snapshot to session_logs for session resume
👻 | Architecture review + knowledge capture
Investigate bugs & implement fixes - primary agent
Define the User Flows and generate a UX Spec - primary agent
👻 | Generate right-sized manual test guides - primary agent
👻 | Conduct principal architecture review
Clear session memory - archive all session files so next session starts fresh
Use when user invokes /learn or wants to save patterns, decisions, gotchas, procedures, or feature knowledge from a conversation for later re-use. Look for user requests like "please remember" or "what did we learn from this?".
👻 | Complete cleanup flow - clean, inspect, lint, test - primary agent
Load this skill when executing TDD (Test-Driven Development) methodology. Use when implementing features via strict RED-GREEN-REFACTOR cycles, or when a prompt instructs execution via TDD.
👻 | Research codebase with parallel agents - primary agent
Define the User Flows and generate a UX Spec - primary agent
👻 | Comprehensive post implementation requirement validation using subagents
👻 | Safe guided rebase w/conflict handling - primary agent
Use when user invokes /learn or wants to save patterns, decisions, gotchas, procedures, or feature knowledge from a conversation for later re-use. Look for user requests like "please remember" or "what did we learn from this?".
Use when user invokes /learn or wants to save patterns, decisions, gotchas, procedures, or feature knowledge from a conversation for later re-use. Look for user requests like "please remember" or "what did we learn from this?".
Use when starting implementation, debugging, or feature work on a project with captured knowledge.
Load this skill when executing TDD (Test-Driven Development) methodology. Use when implementing features via strict RED-GREEN-REFACTOR cycles, or when a prompt instructs execution via TDD.
Use when user wants to search for existing knowledge, recall a specific learning, or discover what knowledge is available.
Use when modifying the Codex SPECTRE install flow, SessionStart continuity, project skill syncing, registry injection, or Codex-specific runtime files.