القائمة
Post tweets, read mentions, reply, like, retweet, and search on X/Twitter using the official v2 API. Use for all X interactions instead of bird-cli or browser automation.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
Maintain Rick's control plane: approvals, dependency gaps, scoreboard, and morning briefs. Use when Rick needs to rank work, ask the founder for something, summarize operating status, or keep the CEO loop coherent.
Production hardening patterns for AI agents running on OpenClaw. Adds destructive command safety (trash > rm), session rotation protocol, context window discipline, tool pre-flight checks, heartbeat batching with state-file gating, and memory trimming workflow. Battle-tested by Rick (meetrick.ai) over 30+ days of autonomous production operation. Use when setting up a new agent for production, auditing an existing deployment, or after experiencing context degradation, token waste, or operational drift.
Diagnose stuck agents, restart failed processes, manage tmux sessions, run health checks, and resolve common operational failures.
Connect to 100+ APIs (Google Workspace, Microsoft 365, GitHub, Notion, Slack, Airtable, HubSpot, etc.) with managed OAuth. Use this skill when users want to interact with external services. Security: The MATON_API_KEY authenticates with Maton.ai but grants NO access to third-party services by itself. Each service requires explicit OAuth authorization by the user through Maton's connect flow. Access is strictly scoped to connections the user has authorized. Provided by Maton (https://maton.ai).
Run long-lived AI coding agents (Codex, Claude Code) in persistent tmux sessions with Ralph retry loops and completion hooks. Use when running multi-step coding tasks, PRD-based workflows, or any programming agent that needs to survive restarts, retry on failure, and notify on completion.
Run long-lived AI coding agents (Codex CLI, Claude Code, Ralph loops) in persistent tmux sessions with completion hooks and automatic monitoring. Use when launching coding agents for multi-step tasks, managing background programming sessions, running Ralph loops with PRD validation, or needing coding work that survives process restarts.
استنادا إلى تصنيف SOC المهني
| name | x-api |
| description | Post tweets, read mentions, reply, like, retweet, and search on X/Twitter using the official v2 API. Use for all X interactions instead of bird-cli or browser automation. |
Default X/Twitter interactions go through xpost. If it is not on PATH, use RICK_XPOST_BIN.
For MCP-native access, OpenClaw has two configured servers:
x-docs: remote docs MCP at https://docs.x.com/mcp; probes cleanly and exposes docs search/read tools.xapi: stdio bridge using npx -y @xdevplatform/xurl mcp https://api.x.com/mcp; static config is valid, but user-context API calls require OAuth2 auth in xurl.As of 2026-06-30, Homebrew xurl cask is 1.0.3 and does not expose mcp; the npm launcher resolves @xdevplatform/xurl 1.2.2 and does expose mcp. Prefer the npm launcher for MCP until the cask catches up.
API keys stored at ~/.config/x-api/keys.env. Format:
X_API_KEY=...
X_API_SECRET=...
X_ACCESS_TOKEN=...
X_ACCESS_TOKEN_SECRET=...
X_USER_ID=...
~/.xurl has a meetrick app with OAuth1 and bearer credentials, but no OAuth2 user token yet. The X MCP full route needs OAuth2 for user-context tools and writes. Run a headless OAuth2 login when ready:
npx -y @xdevplatform/xurl auth oauth2 --app meetrick --headless
If first-run browser auth is acceptable, probing/using xapi may open the browser and block until login completes. X requires the app redirect URI http://localhost:8080/callback unless REDIRECT_URI is set and registered.
xpost post "Your tweet text here"
xpost reply <tweet_id> "Your reply text"
xpost quote <tweet_id> "Your quote text"
xpost mentions [--count 20]
xpost timeline <username> [--count 10]
xpost search "query string" [--count 10]
xpost like <tweet_id>
xpost retweet <tweet_id>
xpost delete <tweet_id>
xpost get <tweet_id>
xpost home [--count 20]
All commands output JSON by default. Use --pretty for formatted output or --text for plain text summary.