Claude Code Slash Commands · page 9

Map attack surface, trace data flows, hunt vulnerability variants

Validate that vulnerability findings are real, reachable, and exploitable

Web application security scanner (alpha)

One-shot MAXIMAL autonomous pentest — the full scan+validate pipeline PLUS a parallel red-team agent war-game, adversarially verified and stitched into a kill-chain Red Team Report.

Run the blueprint-validator against an existing blueprint and report PASS/FAIL with specifics. Blueprints written before v2 will FAIL — they have no acceptance criteria. That is expected, not a bug. / Audita un blueprint existente con el validador; los blueprints v1 fallan porque no tienen criterios de aceptación.

Design a change against an existing codebase — maps the repo's stack, conventions, structure and tests, then emits a blueprint for a feature, refactor, or migration instead of a from-scratch build. / Diseña un cambio sobre un repo existente — mapea stack y convenciones y emite un blueprint de cambio, no de proyecto nuevo.

Resume a build — reads tasks.json from a bundle, finds the first pending task whose dependencies are all done, and prints it with its epic, acceptance criteria, and every verify command. This is what lets a long build survive across sessions. / Reanuda una construcción desde tasks.json y muestra la siguiente tarea desbloqueada.

Fast-track blueprint — three questions, smart defaults for everything else, still validator-gated. For when you just want it built. / Blueprint express — tres preguntas, defaults inteligentes, con el mismo validador.

Re-verify every pinned version in an existing blueprint against the live registries and report what moved, what breaks, and what to change — un-rots a months-old blueprint without a redesign. / Reverifica cada versión fijada en un blueprint contra los registros y reporta qué cambió y qué romper.

Quick job evaluation. Paste a JD and get a score plus one-paragraph summary. Faster than a full evaluate. Use when someone says 'quick eval', 'quick score', or 'just give me a number'.

Set up your job search profile. Paste your resume or answer a few questions. Takes 5 minutes. Needed before evaluating jobs.

Control thinking token limits via environment variable

Run complete two-agent validation on module+tests (contract extraction + test validation). Binary pass/fail with specific issues.

Pick up an open issue from the amux issue tracker, mark it doing, work it, and mark it done.

Use when the user says "add to board", "create a task", or wants to track a todo on the amux kanban board

Use when you need to interact with the amux system — manage board tasks, check sessions, send emails, automate browsers, or work with CRM contacts

Use when the user asks to interact with a web page, take a screenshot of a site, click or type in Chrome, scrape content, or debug a web UI. Connects to real Chrome tabs with existing logins.

Scaffold a closed orchestrator loop — creates the mission note, state/constraints notes, and a scheduler entry from the v2 template.

Use when the user needs to log into a website for browser automation, save auth cookies, or sync browser profiles to cloud

Use when you need to test the amux dashboard UI, investigate a visual bug, or verify a frontend change works correctly

Use when the user wants to record a video of a browser task, create a screen recording, or produce an MP4 demo

Use when the user asks what a session did, wants to review session history, or needs to find errors in a session log

Use after making changes to the amux server or dashboard to verify the dashboard and APIs are working correctly

Perform comprehensive data analysis on specified dataset

自动化完成整个数据分析工作流程，从数据质量检查到最终报告生成

Generate analysis code in specified language and analysis type

Generate research hypotheses and experimental designs based on data patterns

Perform data quality validation, checks, and monitoring for specified dataset

Generate comprehensive analysis reports for specified dataset

Create data visualizations for the specified dataset

Competitive intelligence analysis with keyword gaps and opportunities identification

Complete ASO audit with keyword research, competitor intelligence, metadata optimization, and launch planning

Quick metadata optimization for Apple App Store and Google Play Store with copy-paste ready content

Generate comprehensive pre-launch checklist and timeline with specific dates for app store submission

Create smart commit with quality checks and conventional format

Create pull request with proper validation

Initialize ClaudeForge CI/CD system

Create GitHub release with automated notes

|

Smart router: classify requests and route to the correct agent + skill

Generate project-specific CLAUDE.md from repo analysis.

Triage GitHub notifications: fetch, classify, report actions needed.

Verify installation, diagnose issues, and guide first-time setup

Comprehensive PR review using specialized agents, with automatic retro knowledge capture

Learning system interface: stats, search, graduate learnings. Backed by learning.db (SQLite + FTS5).

|

Run the complete 34-stage implementation workflow for a large, multi-system, multi-wave, or CPU-delegated 5 Star Booker GM program.

Diagnose and prune bloated Claude Code context. Run to slim down the current session before compacting or resuming.

Commit what is already staged — runs the commit subagent in the background, following the ATLAS commit convention.

Interview Boss about the project, then reason from first principles to design the ideal ATLAS operating identity/system-prompt for it — free to drop KISS/YAGNI/DRY/clean-architecture entirely when the project (and the LLM's own distribution) calls for a different mindset

Initialize project context — understand the project, configure conventions, and set up project rules

Brainstorm an idea into a clickable multi-screen React prototype — model the mind (Theory of Mind), interview to kill ambiguity, build a no-build CDN-React prototype under misc/prototypes/, run it, iterate until it matches Boss's vision.

Quickly sketch a standalone low-fidelity wireframe as self-contained HTML — gray boxes, dashed borders, no framework. Lighter than /plan:create-phase, static unlike /brainstorm:prototype.

Discover the project's visual identity, prototype 3 HTML design variants for Boss to compare in a browser, iterate, then lock in DESIGN.md (Stitch-format, machine + human readable). The single source of truth AI coding agents read before generating UI.

Show recent git commits with a brief summary and continual context tied to the working directory / staging area.

Stage and commit all working-directory changes — runs the commit subagent in the background until the tree is clean.

Create a development phase the lean way — resolve ambiguity through Q&A, then capture it as a self-contained low-fidelity wireframe HTML document you implement from in plan mode

Guided feature development with codebase understanding and architecture focus

Author human-readable manual test cases (markdown) into docs/living-test-cases/ — the living artifact that /qa:manual-test-run executes

One-shot an app autonomously — free-will the founding fork, build with deliberate decisions at every trigger, then adversarial review and a conscious final pass before delivery

Plan any change the lean way — resolve ambiguity through Q&A, optionally explore the codebase, then capture the result as a single self-contained, visual HTML document (diagrams, wireframes, matrices) you implement from in plan mode

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...

Check the daily pipeline's state — last run, today's report files, Sonnet quota, recent failures

Trigger the daily digest now (background via OS scheduler) and monitor until completion

Assess your Claude Code level (0-10) and get a personalized roadmap to the next one

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

Очеловечить русский AI-текст (полное редактирование по скиллу humanizer-ru)

Cancel a running background Antigravity (agy) delegation job.

Diagnose a failing Cloud Run service — Antigravity (agy/Gemini) digests the error logs cheaply, Claude infers the root cause and proposes a fix. Read-only by default; --apply writes the fix to a branch.

Delegate a well-scoped subtask to Antigravity (agy/Gemini) under cost discipline, then verify.

Understand an audio / video / image file — Antigravity (agy/Gemini) transcribes and analyzes it, returning a timestamped digest while the full transcript goes to a file.

Migrate an existing Claude Code setup (skills, memory, CLAUDE.md, MCP, plugins, permissions) to the Antigravity CLI.

Claude-orchestrated deep research — Antigravity (agy/Gemini) does the grounded web legwork; Claude plans, verifies the citations, and synthesizes.

Fetch the output of a finished background Antigravity (agy) job, then verify it.

Get an independent cross-model review of the current diff from Antigravity (Gemini), then reconcile as the final judge.

Verify the Antigravity (agy) CLI is installed and authenticated and the plugin is ready to use.