Menu
Unified SuperClaude workflow with subcommands. Use for structured development workflows.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Kimi WebBridge lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's actual login sessions. Use this skill whenever the user wants to interact with websites, automate browser tasks, scrape web content, or perform any action requiring a real browser. Also use when the user mentions "browser", "webpage", "open URL", "screenshot", or asks to read/interact with any website. Use even for simple-sounding browser requests — the daemon handles all complexity.
Record demo GIFs/MP4s of agent TUI sessions (Claude Code, Codex CLI, other agent CLIs), synchronized via a Stop-hook sentinel so the recording knows exactly when each response finishes. Two modes - scripted (VHS tape, repeatable) and live/adaptive (tmux + asciinema, where the outer Claude reads each inner response and decides the next prompt). Use when the user wants to record, capture, or make a demo/GIF/video of a Claude Code or Codex session, create a .tape file, drive a nested agent session interactively, or asks about VHS/asciinema recording of an agent CLI.
Put a website behind a Cloudflare Access (Zero Trust) login gate, or remove one, entirely from the CLI — no dashboard GUI. Use when the user wants to password/email-protect a hostname, gate a Cloudflare Pages or Workers site, restrict a site to specific emails, set up Zero Trust Access, or asks about "cf-gate". Manages Access applications and allow-email policies via the Cloudflare API using a token in the skill's .env. Note: wrangler does NOT manage Access — this uses the Cloudflare REST API directly.
Defer execution of a slash-command or prompt until a timer elapses. Starts a background polling timer that prints "TIMER DONE" on stdout, then executes the deferred prompt.
Generate an image via Codex CLI (OpenAI gpt-image-1) and save to a local path. Use when user asks to create/draw/generate an image AND save it (e.g. "draw X, save to images/y.png", "用 codex 生圖"). Requires `codex login` + `$OPENAI_API_KEY`.
DeepSeek client via the private chat.deepseek.com API (browser-exported userToken), not the official platform.deepseek.com API. Use for personal webgui automation, `x-ds-pow-response` / DeepSeekHashV1 POW solving, or SSE THINK/TOOL_SEARCH stream parsing.
| name | sc |
| description | Unified SuperClaude workflow with subcommands. Use for structured development workflows. |
Comprehensive workflow system with 17 subcommands for structured development tasks.
/sc [command] [target] [options]
| Command | Purpose | Key Options |
|---|---|---|
analyze | Code quality, security, performance analysis | --focus quality|security|performance|architecture, --depth quick|deep |
build | Build, compile, package projects | --type dev|prod|test, --clean, --optimize |
cleanup | Remove dead code, optimize structure | --type code|imports|files|all, --safe|--aggressive, --dry-run |
design | System architecture, API design | --type system|api|component, --document |
document | Create documentation for components | --type inline|external|api|guide, --style brief|detailed |
estimate | Time/effort/complexity estimates | --format brief|detailed, --include-risks |
explain | Explain code, concepts, behavior | --depth overview|detailed|deep, --audience beginner|intermediate|expert |
git | Git operations with smart commits | --smart-commit, --branch-strategy |
implement | Feature and code implementation | --type component|api|service|feature, --with-tests, --safe |
improve | Quality, performance improvements | --focus quality|performance|security, --scope file|module|project |
index | Project documentation and knowledge base | --type readme|api|structure, --format markdown|json |
load | Load and analyze project context | --scope files|dependencies|config|all |
spawn | Break tasks into coordinated subtasks | --sequential|--parallel, --validate |
task | Workflow management with persistence | --strategy systematic|agile|enterprise, --persist, --hierarchy |
test | Execute tests, generate reports | --type unit|integration|e2e|all, --coverage, --watch |
troubleshoot | Diagnose and resolve issues | --type bug|build|performance|deployment, --trace, --fix |
workflow | Generate implementation workflows | --strategy systematic|agile|mvp, --output roadmap|tasks|detailed |
Analyze code quality, security, performance, and architecture.
/sc analyze [target] [--focus quality|security|performance|architecture] [--depth quick|deep]
Build, compile, and package projects.
/sc build [target] [--type dev|prod|test] [--clean] [--optimize]
Clean up code, remove dead code, optimize structure.
/sc cleanup [target] [--type code|imports|files|all] [--safe|--aggressive] [--dry-run]
Design system architecture, APIs, and component interfaces.
/sc design [target] [--type system|api|component] [--document]
Create focused documentation for components or features.
/sc document [target] [--type inline|external|api|guide] [--style brief|detailed]
Provide development estimates for tasks.
/sc estimate [task] [--format brief|detailed] [--include-risks]
Provide clear explanations of code, concepts, or behavior.
/sc explain [target] [--depth overview|detailed|deep] [--audience beginner|intermediate|expert]
Git operations with intelligent commit messages.
/sc git [operation] [--smart-commit] [--branch-strategy]
Feature and code implementation.
/sc implement [feature] [--type component|api|service|feature] [--with-tests] [--safe]
Apply systematic improvements to code.
/sc improve [target] [--focus quality|performance|security] [--scope file|module|project]
Generate project documentation and knowledge base.
/sc index [target] [--type readme|api|structure] [--format markdown|json]
Load and analyze project context.
/sc load [target] [--scope files|dependencies|config|all]
Break complex tasks into coordinated subtasks.
/sc spawn [task] [--sequential|--parallel] [--validate]
Execute tasks with workflow management and persistence.
/sc task [action] [target] [--strategy systematic|agile|enterprise] [--persist] [--hierarchy]
create - Create task hierarchyexecute - Execute with orchestrationstatus - View task statusanalytics - Performance dashboarddelegate - Multi-agent delegationExecute tests and generate reports.
/sc test [target] [--type unit|integration|e2e|all] [--coverage] [--watch]
Diagnose and resolve issues.
/sc troubleshoot [issue] [--type bug|build|performance|deployment] [--trace] [--fix]
Generate structured implementation workflows from PRDs.
/sc workflow [prd|description] [--strategy systematic|agile|mvp] [--output roadmap|tasks|detailed]
| Option | Effect |
|---|---|
--think | Enable extended analysis (4K tokens) |
--think-hard | Deep analysis mode (10K tokens) |
--c7 | Enable Context7 for framework patterns |
--seq | Enable Sequential thinking |
--safe | Conservative approach with extra validation |
--verbose | Detailed output |
/sc analyze src/ --focus security --depth deep
/sc build --type prod --clean --optimize
/sc cleanup --type imports --dry-run
/sc implement user-auth --type feature --with-tests
/sc workflow docs/prd.md --strategy agile --output tasks
/sc troubleshoot "build failing" --type build --trace