[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75GETNE87BYN37SMP9KJ4GH":3,"skill-same:01M75GETNE87BYN37SMP9KJ4GH":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M75GETNE87BYN37SMP9KJ4GH","Superagent CLI Automation",null,"Guide for AI agents to control, configure, and automate Superagent via non-interactive CLI commands (login, model presets, one-shot prompts, workspaces, and sessions).","RudyCity\u002Fsuperagent","RudyCity","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F82188919?v=4","01M75FP5X8AW8ACBH0SH34WS7M","01M75FP5YAHJK8M1Q52BWXB82K",70,"MIT","https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsuperagent-cli\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: Superagent CLI Automation\ndescription: Guide for AI agents to control, configure, and automate Superagent via non-interactive CLI commands (login, model presets, one-shot prompts, workspaces, and sessions).\nwhen_to_use: when an AI agent (Claude Code, AGY, Codex, CI\u002FCD, or automated script) needs to configure or invoke Superagent non-interactively via shell commands without terminal UI prompts\nversion: 1.0.0\nlanguages: all\ndependencies: superagent CLI binary\n---\n\n# Superagent CLI Automation\n\n## Overview\n\nSuperagent is an interactive and automated AI coding assistant with single-agent and 3-tier multi-agent orchestration. While human users typically use the interactive cyberpunk terminal UI, external AI agents (such as Antigravity, Claude Code, OpenAI Codex, custom CI\u002FCD runners, or shell scripts) can operate Superagent non-interactively using dedicated CLI subcommands and command-line flags.\n\nThis skill teaches AI agents how to configure provider credentials, select model presets, run one-shot tasks, and manage sessions cleanly through standard shell commands without getting blocked by interactive prompts.\n\n---\n\n## Quick Reference Table\n\n| Goal | CLI Command | Notes |\n|---|---|---|\n| View help & options | `superagent --help` | Displays all CLI subcommands and options |\n| List providers | `superagent login list` | Lists configured provider profiles, active profile, and masked keys |\n| Add provider key | `superagent login add \u003Cprovider> \u003Capi_key> [base_url]` | Supported providers: openrouter, anthropic, openai, gemini, opencode, deepseek, xai, groq, etc. |\n| Auto-detect key | `superagent login add \u003Capi_key>` | Auto-detects OpenRouter (`sk-or-`), Anthropic (`sk-ant-`), Gemini (`AIza`), or OpenAI |\n| Add custom endpoint | `superagent login add custom \u003Cbase_url> \u003Capi_key>` | Connects to custom OpenAI\u002FAnthropic compatible endpoints |\n| Switch active provider | `superagent login use \u003Cprovider_id>` | Sets default active provider profile |\n| Remove provider | `superagent login remove \u003Cprovider_id>` | Deletes provider profile from configuration |\n| List presets | `superagent preset list` | Displays presets for both multi-agent and single-agent modes |\n| Activate preset globally | `superagent preset use \u003Cpreset_name> [--single]` | Persists preset choice to `model-config.json` |\n| Inspect preset | `superagent preset show \u003Cpreset_name> [--single]` | Shows tier models defined inside the preset |\n| One-shot task | `superagent \"\u003Cprompt>\"` | Executes prompt headless and exits |\n| Run task with preset | `superagent --preset \u003Cpreset_name> \"\u003Cprompt>\"` | Runs one-shot task with specific preset in-memory |\n| Run task with model | `superagent --model \u003Cmodel_name> \"\u003Cprompt>\"` | Runs one-shot task with specific model override |\n| Multi-agent task | `superagent --multi --preset \u003Cname> \"\u003Cprompt>\"` | Spawns 3-tier master orchestrator with feature worktrees |\n| Target workspace | `superagent -w \u002Fpath\u002Fto\u002Fproject \"\u003Cprompt>\"` | Runs task inside target directory |\n| List sessions | `superagent session list -w \u003Cdir>` | Lists conversation transcripts and message counts |\n| Export session log | `superagent session export \u003Csession_id> -o log.md` | Exports chat transcript to Markdown or JSON |\n| Clear empty sessions | `superagent session clear --empty` | Purges zero-message draft sessions |\n\n---\n\n## Workflow Patterns for External Agents\n\n### 1. First-Time Setup: Authenticate Provider\n\nBefore executing AI tasks, ensure at least one provider credentials profile is configured.\n\n```bash\n# Check existing providers\nsuperagent login list\n\n# Add an OpenRouter key\nsuperagent login add openrouter sk-or-v1-xxxxxxxxxxxxxxxxxxxx\n\n# Or add an Anthropic key\nsuperagent login add anthropic sk-ant-xxxxxxxxxxxxxxxxxxxx\n\n# Or add a local Ollama \u002F custom OpenAI endpoint\nsuperagent login add custom http:\u002F\u002Flocalhost:11434\u002Fv1 sk-ollama\n```\n\nAll credentials are saved automatically to `~\u002F.superagent-r\u002Fmodel-config.json`.\n\n### 2. Choose or Verify Model Presets\n\nSuperagent separates model configurations into presets for Single-Agent and Multi-Agent modes:\n\n```bash\n# View available presets\nsuperagent preset list\n\n# Inspect what models are inside a preset\nsuperagent preset show dev\n\n# Activate the \"dev\" preset globally for multi-agent workflows\nsuperagent preset use dev\n\n# Or activate for single-agent workflows\nsuperagent preset use dev --single\n```\n\n### 3. Running Headless Tasks Non-Interactively\n\nWhen automating tasks from an external agent or script, combine workspace isolation, preset selection, and headless execution:\n\n#### Single-Agent One-Shot Task\n```bash\nsuperagent -w \u002Fpath\u002Fto\u002Fproject --preset dev \"Audit tests\u002Fauth.test.ts and fix any failing test cases\"\n```\n\n#### Multi-Agent Orchestrator Task\n```bash\nsuperagent -w \u002Fpath\u002Fto\u002Fproject --multi --preset dev \"Implement OAuth2 Google authentication with unit tests\"\n```\n\nIn multi-agent mode (`--multi`), the Master Agent delegates feature development into isolated git worktrees (`~\u002F.superagent-r\u002Fworktrees\u002F\u003Cname>`), runs subagents, verifies changes, and merges back cleanly.\n\n### 4. Inspecting and Exporting Results\n\nAfter Superagent runs, external agents can retrieve the session transcript:\n\n```bash\n# List recent sessions\nsuperagent session list -w \u002Fpath\u002Fto\u002Fproject\n\n# Export transcript for analysis\nsuperagent session export sess_xxxx -o .\u002Faudit-report.md\n```\n\n---\n\n## Critical Rules for AI Agents Invoking Superagent\n\n- **Do Not Launch Interactive Prompts**: Never call `superagent` without arguments or prompts in a non-interactive subprocess, as it launches the TUI dashboard. Always supply a prompt or subcommand.\n- **PowerShell Compatibility**: On Windows PowerShell, command separators must be `;` instead of `&&`.\n- **Quote Escaping**: When passing complex prompts with quotes or code snippets, wrap the prompt string in double quotes and escape internal quotes:\n  ```bash\n  superagent \"Refactor function \\\"getUser\\\" in src\u002Fauth.ts\"\n  ```\n- **Use `--preset` or `--model` for Controlled Cost**: Default or unset models may hit fallback endpoints. Always specify an explicit preset (e.g. `--preset dev`) or model override (e.g. `--model openai\u002Fgpt-4o-mini`) when budget or speed is a priority.\n","# Superagent CLI Automation\n\n## Overview\n\nSuperagent is an interactive and automated AI coding assistant with single-agent and 3-tier multi-agent orchestration. While human users typically use the interactive cyberpunk terminal UI, external AI agents (such as Antigravity, Claude Code, OpenAI Codex, custom CI\u002FCD runners, or shell scripts) can operate Superagent non-interactively using dedicated CLI subcommands and command-line flags.\n\nThis skill teaches AI agents how to configure provider credentials, select model presets, run one-shot tasks, and manage sessions cleanly through standard shell commands without getting blocked by interactive prompts.\n\n---\n\n## Quick Reference Table\n\n| Goal | CLI Command | Notes |\n|---|---|---|\n| View help & options | `superagent --help` | Displays all CLI subcommands and options |\n| List providers | `superagent login list` | Lists configured provider profiles, active profile, and masked keys |\n| Add provider key | `superagent login add \u003Cprovider> \u003Capi_key> [base_url]` | Supported providers: openrouter, anthropic, openai, gemini, opencode, deepseek, xai, groq, etc. |\n| Auto-detect key | `superagent login add \u003Capi_key>` | Auto-detects OpenRouter (`sk-or-`), Anthropic (`sk-ant-`), Gemini (`AIza`), or OpenAI |\n| Add custom endpoint | `superagent login add custom \u003Cbase_url> \u003Capi_key>` | Connects to custom OpenAI\u002FAnthropic compatible endpoints |\n| Switch active provider | `superagent login use \u003Cprovider_id>` | Sets default active provider profile |\n| Remove provider | `superagent login remove \u003Cprovider_id>` | Deletes provider profile from configuration |\n| List presets | `superagent preset list` | Displays presets for both multi-agent and single-agent modes |\n| Activate preset globally | `superagent preset use \u003Cpreset_name> [--single]` | Persists preset choice to `model-config.json` |\n| Inspect preset | `superagent preset show \u003Cpreset_name> [--single]` | Shows tier models defined inside the preset |\n| One-shot task | `superagent \"\u003Cprompt>\"` | Executes prompt headless and exits |\n| Run task with preset | `superagent --preset \u003Cpreset_name> \"\u003Cprompt>\"` | Runs one-shot task with specific preset in-memory |\n| Run task with model | `superagent --model \u003Cmodel_name> \"\u003Cprompt>\"` | Runs one-shot task with specific model override |\n| Multi-agent task | `superagent --multi --preset \u003Cname> \"\u003Cprompt>\"` | Spawns 3-tier master orchestrator with feature worktrees |\n| Target workspace | `superagent -w \u002Fpath\u002Fto\u002Fproject \"\u003Cprompt>\"` | Runs task inside target directory |\n| List sessions | `superagent session list -w \u003Cdir>` | Lists conversation transcripts and message counts |\n| Export session log | `superagent session export \u003Csession_id> -o log.md` | Exports chat transcript to Markdown or JSON |\n| Clear empty sessions | `superagent session clear --empty` | Purges zero-message draft sessions |\n\n---\n\n## Workflow Patterns for External Agents\n\n### 1. First-Time Setup: Authenticate Provider\n\nBefore executing AI tasks, ensure at least one provider credentials profile is configured.\n\n```bash\n# Check existing providers\nsuperagent login list\n\n# Add an OpenRouter key\nsuperagent login add openrouter sk-or-v1-xxxxxxxxxxxxxxxxxxxx\n\n# Or add an Anthropic key\nsuperagent login add anthropic sk-ant-xxxxxxxxxxxxxxxxxxxx\n\n# Or add a local Ollama \u002F custom OpenAI endpoint\nsuperagent login add custom http:\u002F\u002Flocalhost:11434\u002Fv1 sk-ollama\n```\n\nAll credentials are saved automatically to `~\u002F.superagent-r\u002Fmodel-config.json`.\n\n### 2. Choose or Verify Model Presets\n\nSuperagent separates model configurations into presets for Single-Agent and Multi-Agent modes:\n\n```bash\n# View available presets\nsuperagent preset list\n\n# Inspect what models are inside a preset\nsuperagent preset show dev\n\n# Activate the \"dev\" preset globally for multi-agent workflows\nsuperagent preset use dev\n\n# Or activate for single-agent workflows\nsuperagent preset use dev --single\n```\n\n### 3. Running Headless Tasks Non-Interactively\n\nWhen automating tasks from an external agent or script, combine workspace isolation, preset selection, and headless execution:\n\n#### Single-Agent One-Shot Task\n```bash\nsuperagent -w \u002Fpath\u002Fto\u002Fproject --preset dev \"Audit tests\u002Fauth.test.ts and fix any failing test cases\"\n```\n\n#### Multi-Agent Orchestrator Task\n```bash\nsuperagent -w \u002Fpath\u002Fto\u002Fproject --multi --preset dev \"Implement OAuth2 Google authentication with unit tests\"\n```\n\nIn multi-agent mode (`--multi`), the Master Agent delegates feature development into isolated git worktrees (`~\u002F.superagent-r\u002Fworktrees\u002F\u003Cname>`), runs subagents, verifies changes, and merges back cleanly.\n\n### 4. Inspecting and Exporting Results\n\nAfter Superagent runs, external agents can retrieve the session transcript:\n\n```bash\n# List recent sessions\nsuperagent session list -w \u002Fpath\u002Fto\u002Fproject\n\n# Export transcript for analysis\nsuperagent session export sess_xxxx -o .\u002Faudit-report.md\n```\n\n---\n\n## Critical Rules for AI Agents Invoking Superagent\n\n- **Do Not Launch Interactive Prompts**: Never call `superagent` without arguments or prompts in a non-interactive subprocess, as it launches the TUI dashboard. Always supply a prompt or subcommand.\n- **PowerShell Compatibility**: On Windows PowerShell, command separators must be `;` instead of `&&`.\n- **Quote Escaping**: When passing complex prompts with quotes or code snippets, wrap the prompt string in double quotes and escape internal quotes:\n  ```bash\n  superagent \"Refactor function \\\"getUser\\\" in src\u002Fauth.ts\"\n  ```\n- **Use `--preset` or `--model` for Controlled Cost**: Default or unset models may hit fallback endpoints. Always specify an explicit preset (e.g. `--preset dev`) or model override (e.g. `--model openai\u002Fgpt-4o-mini`) when budget or speed is a priority.\n",{"name":5,"version":23,"languages":24,"description":7,"when_to_use":25,"dependencies":26},"1.0.0","all","when an AI agent (Claude Code, AGY, Codex, CI\u002FCD, or automated script) needs to configure or invoke Superagent non-interactively via shell commands without terminal UI prompts","superagent CLI binary","main","62c7af5ced2c21355d148c243edb6d5921cca1a6",".agents\u002Fskills\u002Fsuperagent-cli",8,"https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent","https:\u002F\u002Fgithub.com\u002FRudyCity","2026-11-14 22:58:49",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add RudyCity\u002Fsuperagent --skill \"Superagent CLI Automation\"",{"tool":40,"command":41},"bunx","bunx skills add RudyCity\u002Fsuperagent --skill \"Superagent CLI Automation\"",{"tool":43,"command":44},"pnpm","pnpm dlx skills add RudyCity\u002Fsuperagent --skill \"Superagent CLI Automation\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsuperagent-cli\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":18},"01M75GP28CM6QCSXSHKFF3NNKS","telegram_bot","Use Telegram Bot when the user asks for Telegram Bot or this provider's API.","https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent\u002Fblob\u002Fmain\u002Fmuse-bridge-kit\u002Fskills\u002Ftelegram-bot\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":18},"01M75GNZGZYM7NWDV6MBP3HS14","superagent-bridge","Operate the Muse\u003C->superagent Telegram bridge: poll the private group for task_request\u002Ftask_result envelopes, validate senders, and reply with task_batch\u002Ftask_done as Muse (the remote brain).","https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent\u002Fblob\u002Fmain\u002Fmuse-bridge-kit\u002Fskills\u002Fsuperagent-bridge\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":18},"01M75GNHN19HJWZ7NAPM5E5JCV","Writing Skills","TDD for process documentation - test with subagents before writing, iterate until bulletproof","https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":18},"01M75GNCQEKVRA4FH161NZPZNB","writing-shape","Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.","https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-shape\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":18},"01M75GNAF9NAYCSTBDZDGMK0DZ","Writing Plans","Create detailed implementation plans with bite-sized tasks for engineers with zero codebase context","https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":18},"01M75GN72EV0V5NQAW9CSPFRFH","writing-guidelines","Review docs\u002Fprose for Writing Guidelines compliance. Use when asked to \"review my docs\", \"check writing style\", \"audit prose\", \"review docs voice and tone\", or \"check this page against the writing handbook\".","https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-guidelines\u002FSKILL.md",[],[]]