Slash Commands de Claude Code · página 8

Launch local Swagger UI for a service's OpenAPI spec

Analyze staged changes and organize them into intuitive atomic commits following conventional commits.

Show Claude-Flow commands and usage

Interact with Claude-Flow memory system

Coordinate multi-agent swarms for complex tasks

Apply expert UX/UI design thinking to design, redesign, enhance, or fix any interface element with meticulous craft and intentionality.

Address code review feedback — corroborate, validate, and implement changes from a review's final.md.

Create a new custom reviewer from a natural language description.

Check OCR installation and verify all dependencies are available.

List past OCR review sessions.

Generate a Code Review Map to help navigate large, complex changesets.

Post the current OCR review to a GitHub PR.

Run an AI-powered multi-agent code review on your changes.

List all available reviewer personas for code review.

Display a past OCR review session.

Sync reviewer metadata from markdown files to reviewers-meta.json for the dashboard.

Translate a multi-reviewer code review into a single human-voice GitHub PR comment.

Implement an approved OpenSpec change and keep tasks in sync.

Archive a deployed OpenSpec change and update specs.

Scaffold a new OpenSpec change and validate strictly.

Review a given code review markdown document, GitHub PR review, or inline feedback — corroborate each point against actual code, then implement valid changes.

❓Ask - You are a task-formulation guide that helps users navigate, ask, and delegate tasks to the correc...

🧠 Auto-Coder - You write clean, efficient, modular code based on pseudocode and architecture. You use configurat...

🪲 Debugger - You troubleshoot runtime bugs, logic errors, or integration failures by tracing, inspecting, and ...

🚀 DevOps - You are the DevOps automation and infrastructure specialist responsible for deploying, managing, ...

📚 Documentation Writer - You write concise, clear, and modular Markdown documentation that explains usage, integration, se...

Initialize Beads issue tracking in your project with interactive configuration setup.

Dead code detection and cleanup workflow (inline orchestration)

Dependency audit and update workflow (inline orchestration)

Code duplication detection and consolidation workflow (inline orchestration)

Security vulnerability detection and remediation workflow (inline orchestration)

Connect any project to Gastown multi-agent orchestration

Automated release management with version bumping and dual changelog generation

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.

Import tasks from tasks.md into Beads issue tracker, creating an epic with child tasks and proper dependencies.

Show Gastown status (convoys, agents, pending tasks)

Optimize Supabase database performance by delegating to specialized agents

Translate documentation file from English to Russian

Deep analysis and problem solving with multi-dimensional thinking

Safely upgrade Gastown and Beads

Give task to AI agent via Gastown (create bead + sling to polecat)

Manage git worktrees for parallel feature development (create, remove, list, cleanup)

Product Manager-led orchestration with optional thinking modes, MCP servers, and flexible input types (request/PRD/PRP)

Build the colcon workspace (optionally a single package) and report the outcome.

Summarize commits on the current branch (vs origin/main) into a Changelog-style bullet list ready to paste into Changelog.md.

Run pre-commit hooks (clang-format, codespell, etc.) over the staged + changed files, then optionally clang-tidy.

Scaffold a new ECS component header under include/gz/sim/components/ and wire it into the install list.

Scaffold a new gz-sim system plugin under src/systems/<name>/ with header, source, CMake glue, plugin registration, and an integration test stub.

Run the gz-sim CTest suite (optionally filtered by regex) and report pass / fail counts.

Run ament linters (uncrustify, cpplint, flake8, pep257, xmllint, copyright) and pre-commit against changed files.

Author a new sub-agent under .claude/agents/<name>.md with valid frontmatter (name/description/tools/model), following the template conventions, and index it in CLAUDE.md + README.md.

Scaffold a Behavior Tree leaf node — plain BehaviorTree.CPP (sync/stateful/condition) or a BehaviorTree.ROS2 wrapper (action/service/topic) — with ports, registration, and an XML usage snippet.

Author a new slash command under .claude/commands/<name>.md with valid frontmatter, following the template conventions, and index it in CLAUDE.md + README.md.

Scaffold a ros2_control controller or broadcaster — base class, command/state interface config, RT-safe update(), generate_parameter_library, pluginlib export, and a test.

Scaffold a ros2_control hardware component (System/Actuator/Sensor) + URDF <ros2_control> tag + bringup (controllers.yaml + launch), with pluginlib export and a test.

Scaffold a modular launch file (Python or XML) inside an existing package, following the ros2_launch_config skill.

Scaffold a Node inside an existing package — standard, lifecycle, or component, in Python or C++.

Scaffold a new ROS 2 package (ament_python or ament_cmake) following Clean Architecture layout — domain / application / infrastructure / presentation.

Scaffold a Clean-Architecture VDA 5050 v3.0.0 connector (MQTT/JSON ↔ Nav 2) — domain entities, ports, application handlers, MQTT + Nav 2 adapters — in the chosen code format.

Bootstrap a complete ROS 2 colcon workspace from scratch — dir layout, .gitignore, README, this .claude/ config, and seed interfaces/core/bringup packages.

Run colcon tests for the workspace (or a single package) and report pass / fail counts.

WordPress performance code review - detects database anti-patterns, caching issues, hook problems, and scalability concerns

Quick WordPress performance scan - fast triage using critical pattern detection

Analyze and optimize context configuration. Reviews CLAUDE.md, knowledge-core.md, and active context for optimization opportunities. Helps prevent context rot (39% improvement, 84% token reduction).

Quick command to invoke code-implementer to execute implementation with self-correction (up to 3 intelligent retries).

Quick command to invoke implementation-planner to create surgical, reversible implementation plans with rollback procedures.

Quick command to invoke docs-researcher for rapid documentation research. Fetches version-accurate, authoritative sources and creates ResearchPack.

Complete Research → Plan → Implement workflow in one command. Invokes chief-architect to orchestrate all phases with quality gates and self-correction.

Build from the plan

Onboard Claude Code into the codebase

Install pitchcraft skill for structured persuasion and executive reporting

安装 pitchcraft skill（结构化说服与汇报）

Load Obsidian plugin development guidelines and best practices

Interactive guide for creating a new Obsidian plugin with best practices

Force recalibration of all CLAUDE.md files

Initialize CLAUDE.md memory structure for project with interactive wizard

Show CLAUDE.md memory sync status

Sync CLAUDE.md with manual file changes detected by git

Run cc-fleet's setup/health diagnostics and explain any failures (read-only)

List cc-fleet provider teammates, async jobs, and pane health (read-only)

Generate FILETREE.md from scratch. Confirms overwrite if it already exists.

Report drift between FILETREE.md and current repo, read-only. Prompts to run /filetree:update on drift.

Sync FILETREE.md with current repository state — handles added / changed / removed / renamed.

Draft blog posts, ad copy, emails, social media, landing pages, and video scripts with brand voice and SEO

Wire DMP for Anthropic Cowork team usage: verifies Cowork sandbox, checks for a Drive MCP, creates the canonical Drive folder layout, and persists the team's routing config. Run once per team.

Per-action readiness diagnostic. Shows which campaign-audit and launch-campaign actions are live (manifest-ready) vs blocked (stub-unconfigured) in the current environment, with one-step setup hints for the blocked ones. Now includes model-registry freshness + Cowork+Drive routing status.

Design complete email sequences with subject lines, body copy, timing, segmentation, and deliverability guidance

Run a marketing engagement using the 12-Part methodology. Subcommands: start, next, status, validate, re-run-decision, update-back, lif-show, file-tree, list-engagements.

Actually fire a campaign-audit / launch-campaign action against its real API (vs returning a manifest). Reads credentials from env vars (no OAuth flow). Read ops auto-execute with --execute; write ops require --confirm. Logs every execution to the audit trail.

Build a pillar+spokes content cluster plan from seed keywords with SERP-overlap clustering, intent grouping, internal-link map, and a four-gate quality scorecard

Print + open the user-visible DMP output folder for a brand (~/Documents/DigitalMarketingPro/{brand}/). Direct answer to "where did my engagement deliverables save?

Generate a marketing performance report with KPI tracking, trend analysis, anomaly detection, and recommendations