Claude Code Slash Commands · page 9

Launch the ShadCN UI builder agent for component-based UI development

Launch the TDD specialist for test-driven development

Alternative command for TDD specialist focusing on test-first approach

Run tests and fix failures

Launch the ShadCN UI builder agent for interface design and implementation

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)

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

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

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

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.

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.

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)

Install pitchcraft skill for structured persuasion and executive reporting

安装 pitchcraft skill（结构化说服与汇报）

Build from the plan

Onboard Claude Code into the codebase

Load Obsidian plugin development guidelines and best practices

Interactive guide for creating a new Obsidian plugin with best practices

Аудит текста на признаки AI без правки (сканер + разбор по скиллу)

Очеловечить русский AI-текст (полный рерайт по скиллу humanizer-ru)

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.

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

Analyze user corrections and log them into the error notebook

Review the error notebook — flip through past corrections before working

Create a handoff file for another session to pick up

翻錯題本 — 複習之前被改過的地方

Audit recurring context files and suggest usage-limit optimizations.

Explain or summarize Governor vs Caveman performance benchmark results.

Automatically compress CLAUDE.md or other memory files with protected-span safety. One-command token savings.

Temporarily ask Governor to avoid compacting tool output for the next diagnostic step.

Check current changes against the latest approved implementation contract.

Install Governor compact-mode rule files into a project for Codex, Gemini, Cursor, Windsurf, or Cline.

Disable Governor compact response mode while keeping telemetry/tool hooks available.

Enable Governor compact professional mode for all prompts in this Claude Code session.

Create a compact implementation contract before broad app/site/game/refactor work.

Show Claude Code Governor usage dashboard and waste heat map.

Enable strict governance behavior for the current task.

Execute validated plans with isolated agents and two-stage review

Iterative planning with human checkpoints at every phase

Final shipping gate. PR creation, documentation updates, and merge with human approval.

Post-execution verification gate. Tests, lint, type-check, then see it working.

Activate Nemp Pro with your license key

View captured activity log

Enable or disable automatic activity capture

Enable or disable automatic cross-provider memory export

Enable or disable automatic syncing to CLAUDE.md

Search memories by keyword and show relevant context

Nemp Cortex — memory intelligence layer (Pro)