Slash Commands de Claude Code · página 8

Extract design patterns from code into specs and wiki

Guided reading of code or wiki to extract patterns

Investigate questions with hypothesis testing and evidence logging

Get alternative perspectives — review, challenge, or consult

Generate overlays to fix workflow command deficiencies

Use when a topic needs structured multi-dimensional investigation before planning or decision-making

Generate formal specification package (Product Brief, PRD, Architecture, Epics) through 6-phase document chain

Use when exploring ideas, evaluating approaches, or needing multi-perspective analysis before implementation

Use when a question needs cross-verification from multiple CLI tools or diverse analytical perspectives

Compose reusable workflow templates from natural language

Use when a confirmed plan is ready for implementation

Use when stress-testing a plan, idea, or requirement against codebase reality before brainstorming

Audit current milestone for cross-phase integration gaps

Archive completed milestone and prepare for next

Bump version, generate changelog, tag milestone

Use when creating, revising, or verifying an execution plan for a phase or task

Play workflow templates with checkpoint resume

Quick task execution, skip optional agents

Self-running loop controller for adaptive maestro workflow — build, tick, decide in one skill

Execute next pending step in ralph session

Generate roadmap with milestone/phase structure from requirements or upstream context

Parallel workflow accelerator — route intent to fixed Workflow scripts for multi-agent concurrent execution

Load and execute tool specs by category or name

Register tool specs - extract, generate, or optimize

Extract design system from code, generate reference package, persist as knowledge assets

Dynamic adversarial workflow generator — scan library, match or generate, execute, persist

Rebuild all codebase documentation from scratch

Extract knowledge from artifacts into wiki/spec/issues

Discover issues via multi-perspective analysis

Create, query, update, close, and link issues

Analyze codebase patterns and generate .workflow/kg/extractors.yaml for custom symbol extraction

Capture reusable knowledge as templates, recipes, or tips

Manage knowhow entries (workflow and system)

Audit and prune knowledge across spec / knowhow / artifact stores

Show project dashboard with progress and next steps

Manage wiki graph — health, cleanup, search, stats

Long-running debug cycle — archaeology, diagnosis, fix, confirmation, generalization, discovery, and knowledge persistence

Long-running codebase improvement cycle — multi-dimensional audit, deep diagnosis, targeted fix, verify, generalize, and engineering knowledge persistence

Requirement-driven iterative cycle — plan, execute, strict verify, fix loop until acceptance criteria met

Deep review + fix cycle — archaeology, exploration, multi-dimensional review, targeted fix, generalization, discovery, and knowledge persistence

Long-running UI optimization cycle — visual survey, multi-dimensional audit, divergent exploration, fix, verify, generalize, and design knowledge persistence

Use when test coverage needs automated expansion or existing tests need iterative convergence

Use when bugs, test failures, or unexpected behavior need systematic root cause investigation

Use when accumulated tech debt needs systematic identification and safe reduction

Use after completing a phase to extract lessons, patterns, and improvement opportunities

Use after execution to evaluate code quality across correctness, security, performance, and architecture

Sync codebase docs by tracing git diff impact

Register a domain term into project glossary

Detect and realign .workflow/ artifact drift against code reality after refactoring

Analyze git changes and create a commit without Claude Code attribution

Run ad-hoc PostgreSQL analytics queries against dev/test database

Commit changes with auto-generated message showing command context, timestamp, and change count

Add a new Claude Code hook event with sounds, config, settings, scripts, and docs

Track Claude Code changelog and find what needs updating in this repo

Guided version bump — validate, tag, and create GitHub release

Run pre-release validation checks on all SKILL.md files and JSON databases

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

Generate a custom checklist for the current feature based on user requirements.

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.

Execute the implementation plan by processing and executing all tasks defined in tasks.md

Execute the implementation planning workflow using the plan template to generate design artifacts.

Create or update the feature specification from a natural language feature description.

Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.

Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.

Configure OAuth providers, auth hooks, JWT lifetimes, and service keys for a Butterbase app

Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase

Develop, deploy, or debug a Butterbase serverless function

Stage 1 of the journey: concrete one-question-at-a-time idea brainstorm with inline Butterbase capability tagging.

Stage 2 of the journey: translate the idea + capability map into a concrete Butterbase plan (tables, RLS, auth, functions, storage, frontend).

Build a RAG knowledge base on Butterbase: ingest documents, run semantic search, generate synthesized answers

Design or modify a Butterbase database schema using the declarative DSL

Hackathon submission: assemble metadata from journey artifacts and call prep_and_submit_hackathon_entry.

Engage. Interrogate the brief. Name who signs done.

Transfer operations. They operate it without you.

Capture the meeting. Notes into the record.

Diagnose. Check the brief is the real job.

Realize. Promised, measured, accepted.

Align. Sequence the work. Work backwards from success.

Prepare the meeting. One page from the record.

Report the outcome. Promised, measured, accepted.

Find the receipt. A dated line, or it did not happen.

Deliver the increment. Then go live with a rollback you have run.

Diagnose trust. Process gap, or they stopped trusting you.

Implement tasks from an OpenSpec change (Experimental)

Archive a completed change in the experimental workflow

Enter explore mode - think through ideas, investigate problems, clarify requirements

Propose a new change - create it and generate all artifacts in one step

Look up library documentation using Context7 MCP tools for a specific task

Scrape and integrate documentation from provided URLs using Firecrawl tools

Full autonomous security workflow — scan, dedup, prep, analyse, consensus, judge, exploit, patch, group

Analyze existing SARIF findings with LLM

Add, list, edit, or remove per-function annotations attached to source files

Audit authentication (JWT, cookies) and security logging coverage automatically

CodeQL deep static analysis with dataflow validation

List all available MANTISHACK commands

Autonomous crash root-cause analysis for C/C++ bugs

CVE patch discovery — find, acquire, and diff the fix commit for a CVE

Generate Mermaid visual maps from /understand or /validate output directories

Generate exploit proof-of-concepts for vulnerabilities (beta)