spectre

👻 | Transform requirements into executable tasks - primary agent

👻 | 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

👻 | 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

Run the SPECTRE release workflow, including version bumps, Codex sync, global Codex install verification, GitHub release, manual npm publish handoff, npm verification, and final global Codex refresh.

Use when starting implementation, debugging, or feature work on a project with captured knowledge.

👻 | Conduct principal architecture review

👻 | Complete cleanup flow - clean, inspect, lint, test - primary agent

👻 | Independent LLM Code Review - subagent

👻 | Create implementation plan from PRD - primary agent

👻 | Generate right-sized manual test guides - primary agent

👻 | Architecture review + knowledge capture

👻 | Adaptive Wave-Based Build with Per-Wave Verification Gate

Investigate bugs & implement fixes - primary agent

Clear session memory - archive all session files so next session starts fresh

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.

Save state snapshot to session_logs for session resume

👻 | Project kickoff with deep research & MVP pathfinding - 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?".

👻 | Generate a self-contained HTML prototype to validate a feature visually before planning - primary agent

👻 | Quickly scope, research, & plan s/m tasks - primary agent

👻 | Safe guided rebase w/conflict handling - primary agent

👻 | Search Project Knowledge

👻 | Research codebase with parallel agents - primary agent

👻 | Interactively scope a feature or improvement, generating a complete Scope document with IN, OUT, and ANTI-SCOPE boundaries -- primary agent

👻 | Autonomous end-to-end: brain dump -> scope -> TDD -> commit -> rebase -> PR

👻 | Light pass cleanup - clean, lint, test, commit

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.

👻 | Risk-aware test coverage & commit - primary agent

👻 | Define user flows, components, and UX behavior — generates the UX spec for a feature - primary agent

👻 | Comprehensive post implementation requirement validation using subagents

Use when starting implementation, debugging, or feature work on a project with captured knowledge.

👻 | Conduct principal architecture review

👻 | Complete cleanup flow - clean, inspect, lint, test - primary agent

👻 | Independent LLM Code Review - subagent

👻 | Create implementation plan from PRD - primary agent

👻 | Generate right-sized manual test guides - primary agent

"\ud83d\udc7b | Architecture review + knowledge capture"