spectre

👻 | 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

👻 | Transform requirements into executable tasks - primary agent

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

👻 | Architecture review + knowledge capture

👻 | Adaptive Wave-Based Build -> Code_Review -> Validate Flow

Investigate bugs & implement fixes - primary agent

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

Save state snapshot to session_logs for session resume

👻 | Project kickoff with deep research & MVP pathfinding - primary agent

👻 | Capture knowledge for future sessions

👻 | Unified planning entry point - researches, assesses complexity, routes to workflow - primary agent

👻 | Find simplifications in a plan or tasks

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

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

Load the `spectre-recall` skill and follow its instructions.

👻 | Research codebase with parallel agents - primary agent

👻 | Interactively scope a feature or improvement, generating a complete Scope document that clarifies what's IN and OUT -- primary agent

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

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

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

Define the User Flows and generate a UX Spec - primary agent

👻 | Comprehensive post implementation requirement validation using subagents

Analyzes codebase implementation details. Call the analyst agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :)

Implementation specialist for writing and refactoring code. Focuses on simplicity, readability, MVP-first delivery. Use when writing new features, refactoring, or implementing tasks.

Locates files, directories, and components relevant to a feature or task. Call `finder` with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.

patterns is a useful subagent_type for finding similar implementations, usage examples, or existing patterns that can be modeled after. It will give you concrete code examples based on what you're looking for! It's sorta like finder, but it will not only tell you the location of files, it will also give you code details!

Use this agent when you need an independent second opinion on plans, tasks, or code. This agent provides unbiased review and critique, focusing on the user's specific concerns while maintaining complete independence from the original implementation decisions. Examples: <example> Context: The user has just completed implementing a new authentication system and wants an independent review. user: "I've implemented a new auth system using JWT tokens. Can you review the security aspects?" assistant: "I'll use the reviewer agent to provide a fresh perspective on your authentication implementation" <commentary> Since the user is asking for a review of existing code with a specific focus area (security), use the reviewer agent. </commentary> </example> <example> Context: The user has created a technical plan for a new feature. user: "Here's my plan for implementing real-time chat. I'm concerned about scalability - what do you think?" assistant: "Let me engage the reviewer agent to review your plan with a focus on scalability concerns" <commentary> The user wants a second opinion on their plan with specific concerns about scalability, perfect for the reviewer. </commentary> </example> <example> Context: The user has a task breakdown for a complex feature. user: "I've broken down the user profile feature into these tasks. Does this seem like the right approach?" assistant: "I'll use the reviewer agent to provide an independent assessment of your task breakdown" <commentary> The user is seeking validation on their approach to task organization, requiring an independent perspective. </commentary> </example>

Memory consolidation agent that synthesizes current session context with historical sessions to maintain continuity across handoffs. Called by /sesh:handoff when previous session logs exist.

Master AI-powered test automation with modern frameworks, self-healing tests, and comprehensive quality engineering. Build scalable testing strategies with advanced CI/CD integration. Use PROACTIVELY for testing automation or quality assurance.

Do you find yourself desiring information that you don't quite feel well-trained (confident) on? Information that is modern and potentially only discoverable on the web? Use the researcher subagent_type today to find any and all answers to your questions! It will research deeply to figure out and attempt to answer your questions! If you aren't immediately satisfied you can get your money back! (Not really - but you can re-run researcher with an altered prompt in the event you're not satisfied the first time)

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

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.

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?".

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.

4 hooks across 2 events