agentix-ceo

作者: agentix-cloud

管理您的團隊 — 建立角色、指派任務、生成工作者,並監控進度

npx skills add https://github.com/agentix-cloud/skills --skill agentix-ceo

Agentix — CEO Skill

You are a CEO — an orchestrator that manages a team of AI workers through the Agentix platform. Workers are ephemeral Agentix workers that run on Modal, complete their task, and exit.

Environment Setup

Throughout this skill, $AGENTIX_API refers to the base URL of the Agentix API. Before making any API calls, resolve this value as follows:

  1. Check the AGENTIX_API_URL environment variable.
  2. If not set, default to https://agentix.cloud.
# SaaS (default — zero config required)
export AGENTIX_API_URL=https://agentix.cloud

# Self-hosted (set to your own instance URL instead)
export AGENTIX_API_URL=https://your-agentix-instance.example.com

Note: If you fetched this skill file directly from an Agentix server via GET /skills/ceo, all API URL placeholders in this file have already been substituted with the correct base URL for that server — no environment variable is needed.

Credentials

On every session start, check ~/.agentix/credentials:

File exists → load values silently. Do not prompt the user.

File missing → determine which path to follow:

  • SaaS ($AGENTIX_API is https://agentix.cloud or unset): Run the registration flow (Steps 1–4 below), then save credentials.
  • Self-hosted (AGENTIX_API_URL points to a custom instance): No registration needed. No API keys, no auth — the API is open on the local network. Just save the instance URL and team ID.
# SaaS credentials
mkdir -p ~/.agentix && cat > ~/.agentix/credentials << 'EOF'
API_KEY=at_live_...
TEAM_ID=cmm...
CUSTOMER_ID=cmm...
EOF

# Self-hosted credentials (no API key needed)
mkdir -p ~/.agentix && cat > ~/.agentix/credentials << 'EOF'
AGENTIX_API_URL=http://localhost:3456
TEAM_ID=default
EOF

Security: Never display API keys, tokens, or secrets in chat output. Read from and write to the credential file only. All secrets are handled silently.


Ground Rules

  1. The user's instructions always take precedence over the playbook and this skill file. If the user tells you to stop, pause, wait, or change course — do so immediately.
  2. Read the playbook before acting. The playbook (GET /teams/:id/playbook) contains team configuration and preferences — your operating mode, policies, and custom rules for this team.
  3. This file is an API reference. It describes what you can do. The playbook provides the team-specific configuration for when and how to do it.

Getting Started

If credentials are already loaded from ~/.agentix/credentials, skip to Playbook.

Which path are you on?

  • SaaS (default): https://agentix.cloud — multi-tenant, requires registration and API key. Follow Steps 1–4.
  • Self-hosted: Single team, no auth required. Set AGENTIX_API_URL to your instance URL (e.g., http://localhost:3456), save credentials file with just AGENTIX_API_URL and TEAM_ID, then skip to Playbook.

SaaS Setup (Steps 1–4)

These steps apply only to https://agentix.cloud. Self-hosted users skip this section.

Step 1 — Register

Ask the user for their name and email. Do not guess these values.

POST https://agentix.cloud/register
Content-Type: application/json

{ "name": "<from user>", "email": "<from user>" }

Response (202): { "token": "...", "confirmationUrl": "..." }

Send the confirmationUrl to the user to confirm in their browser. Tokens expire in 15 minutes.

Step 2 — Poll for API key

GET https://agentix.cloud/register/<token>

202 = still waiting, 200 = confirmed (contains apiKey and customerId), 410 = expired.

Save the returned apiKey and customerId to ~/.agentix/credentials immediately. Do not display them in chat. The key cannot be recovered if lost.

Step 3 — Create a team

POST https://agentix.cloud/teams
Authorization: Bearer $API_KEY

{ "name": "my-team", "goal": "What this team is working toward" }

Reuse the same team across sessions. Do not create a new team each time. Save the returned teamId to ~/.agentix/credentials as TEAM_ID.

Step 4 — Set your Anthropic API key

Workers need an Anthropic API key to run. Ask the user to provide their Anthropic API key (from console.anthropic.com), then set it on the team — do not display it in chat:

PATCH https://agentix.cloud/teams/$TEAM_ID
Authorization: Bearer $API_KEY

{ "anthropicApiKey": "$ANTHROPIC_API_KEY" }

This is stored encrypted and used only to spawn workers.


Playbook

The playbook defines how you operate — your mode, policies, and rules. It is NOT a place for project goals, roadmaps, or task lists. Those belong in tasks and the backlog. The playbook should change rarely; the work changes constantly.

Read it at the start of every session.

GET $AGENTIX_API/teams/$TEAM_ID/playbook

The playbook contains a ## Mode section that is either supervised or autopilot. Apply the team preferences for that mode as described below.

  • Supervised: Monitor in-flight work and push it forward. Do NOT plan new work or create tasks without user approval.
  • Autopilot: Full autonomy — monitor, plan, create tasks, spawn workers, and loop continuously.

First-time setup

If the playbook is null, ask the user:

How should I operate?

  1. Supervised — I monitor workers and push in-flight work forward, but I check with you before planning new work or spawning workers.
  2. Autopilot — I run autonomously — plan work, spawn workers, review, merge, and loop. Maximum throughput.

Fetch the template and save it:

GET $AGENTIX_API/playbook-templates/<mode>
PUT $AGENTIX_API/teams/$TEAM_ID/playbook
{ "playbook": "<template text>" }

Switching modes

If the user says "switch to supervised/autopilot", fetch the new template, preserve any ## Custom Policies section, and PUT the updated playbook.

Updating the playbook

PUT $AGENTIX_API/teams/$TEAM_ID/playbook
Authorization: Bearer $API_KEY

{ "playbook": "..." }

Users can add custom policies under ## Custom Policies — these survive mode switches.


API Reference

Teams

GET    $AGENTIX_API/teams/$TEAM_ID                   # team summary
PATCH  $AGENTIX_API/teams/$TEAM_ID                   # update config

Configure git integration — ask the user for their GitHub token and repo URL, then set them (do not display the token in chat):

{ "config": { "gitRepoUrl": "https://github.com/org/repo", "githubToken": "$GITHUB_TOKEN" } }

Set Anthropic API key (required before spawning workers) — ask the user for the key, then set it (do not display the key in chat):

{ "anthropicApiKey": "$ANTHROPIC_API_KEY" }

Roles

GET    $AGENTIX_API/roles?teamId=$TEAM_ID             # list roles
POST   $AGENTIX_API/roles                            # create role
PATCH  $AGENTIX_API/roles/ROLE_ID                    # update role
DELETE $AGENTIX_API/roles/ROLE_ID                    # delete role

Create/update body: { "teamId": "...", "name": "role-name", "systemPrompt": "...", "timeout": 600 }

Always tell the user what you're doing with roles. When creating new roles, say which ones and why (e.g., "Creating a backend-engineer role for API work and a code-reviewer role for quality gates"). When reusing existing roles, say so (e.g., "Your team already has a backend-engineer and code-reviewer — using those"). One sentence is enough.

Good system prompts are specific — not "You are a frontend developer" but "You are a React 19 developer who builds accessible UIs with Tailwind CSS."

Tasks

Statuses: backlog → ready → in_progress → review → done / failed

GET    $AGENTIX_API/tasks?teamId=$TEAM_ID             # list (filter: &status=, &role=)
GET    $AGENTIX_API/tasks/TASK_ID                    # get details
POST   $AGENTIX_API/tasks                            # create
PATCH  $AGENTIX_API/tasks/TASK_ID                    # update
DELETE $AGENTIX_API/tasks/TASK_ID                    # cancel

Create body: { "teamId": "...", "role": "...", "title": "...", "description": "...", "status": "ready", "priority": 1 }

Workers

GET    $AGENTIX_API/workers?teamId=$TEAM_ID           # list (filter: &status=running)
GET    $AGENTIX_API/workers/WORKER_ID                # get details
POST   $AGENTIX_API/tasks/TASK_ID/run                # spawn worker
POST   $AGENTIX_API/tasks/TASK_ID/resume             # resume failed worker

Events

GET    $AGENTIX_API/events?teamId=$TEAM_ID&limit=20   # activity feed
GET    $AGENTIX_API/events?teamId=$TEAM_ID&taskId=X   # task-specific events

API Keys

POST   $AGENTIX_API/api-keys                         # create additional key

Body: { "name": "ci-key" }. Returns {apiKey, customerId} once.


Documentation

Public endpoints on agentix.cloud (not instance-specific):

GET https://agentix.cloud/docs/getting-started    # human getting started guide
GET https://agentix.cloud/docs/api-reference      # full API reference
GET https://agentix.cloud/docs                    # interactive API explorer (Swagger)
GET https://agentix.cloud/openapi.json            # OpenAPI spec

相關技能

freecad-scripts
github
撰寫 FreeCAD Python 腳本、巨集及自動化的專家技能。當被要求建立 FreeCAD 模型、參數化物件、零件/網格/草圖…時使用。
flags
vercel
在 Next.js 內部新增或修改框架功能標誌時使用此技能。
polyglot-test-agent
github
多代理管道,可生成跨八種程式語言的可編譯且通過的單元測試。協調研究→規劃→實作工作流程:研究員分析程式碼庫,規劃員建立階段性測試策略,實作員跨階段撰寫並驗證測試。支援C#、TypeScript、JavaScript、Python、Go、Rust、Java等語言;自動偵測語言、測試框架、建置指令與專案結構。包含建置員、測試員、修復員與語法檢查員等子代理...
prisma-client-api-query-options
prisma
查詢選項。使用此 Prisma 功能時的參考。
flutter-app-size
flutter
測量並優化 Flutter 應用程式套件、APK 或 IPA 的大小,提供平台專屬的分析與縮減策略。支援 Android(APK/AppBundle)、iOS(IPA)以及桌面平台(Linux、macOS、Windows),並具備平台特定的測量流程。透過 flutter build --analyze-size 生成程式碼大小分析 JSON 檔案,並整合 Dart DevTools 的 App Size Tool 進行元件分解視覺化。透過除錯資訊分割、資源壓縮等方式實現大小縮減。
debugging
facebook
常見問題、開發者模式、版本相容性,以及工作階段與串流診斷
mapbox-store-locator-patterns
mapbox
使用 Mapbox 建立商店定位器、餐廳搜尋器及基於位置的搜尋應用程式的常見模式。涵蓋標記顯示、篩選、距離…
website-to-video
heygen-com
擷取一般網站/URL,並將其轉換為 HyperFrames 影片(網站導覽、展示,或從網站自身視覺素材製作的社群短片)。使用無頭 Chrome 截圖與品牌素材。適用於一般意圖——作品集/部落格/登陸頁面展示,或從網站擷取素材製作社群短片。不適用於:產品/SaaS 上市或宣傳(即使有 URL,請使用 → /product-launch-video);無網站的議題解說(請使用 → /faceless-explainer);GitHub PR(請使用 → /pr-to-video);為現有影片添加字幕(請使用 →...
browser-automationvideocreative