技能列表

Integrate Stripe usage-based billing with idempotent event ingestion, late-event handling, and pre-invoice reconciliation. Use when implementing usage metering, tracking API calls or seats, pushing usage to Stripe, handling billing drift, or building usage-based pricing.

>

>

Precision decisioning, agentic trust, and verifiable identity for autonomous agents"

Query, optimize, and administer ClickHouse OLAP databases with schema design, performance tuning, and data ingestion patterns.

macOS 只读查询：Mail 未读、Calendar 日程、Notes 搜索、Stocks 行情（输出 JSON）。

Coach de IA personalizado. Proporciona retroalimentación, establece metas y te motiva a mejorar continuamente.

Daily GitHub repo health check + safe Dependabot auto-merge. Outputs markdown report.

Diagnoses and auto-heals BlueBubbles ↔ OpenClaw iMessage connectivity. Use when: iMessages stop arriving after a gateway restart, webhook connection is broken, or user reports messages not coming through. Runs a 4-step diagnostic and auto-fixes webhook backoff, stale registrations, and gateway issues.

Convert Telegram chat exports into a long screenshot-style image. Supports Telegram Desktop JSON exports with bubble-style message rendering, avatars, timestamps, and proper text wrapping. Use when user wants to generate a visual image of Telegram conversations, create chat screenshots, or share conversation history as a single long image.

Analyze outbound campaign performance, reply rates, open-to-reply conversion, follow-up prioritization, platform attribution, and deliverability using OutboundSync engagement signals in HubSpot or Salesforce. Use this skill when someone asks about campaign replies, which sequences are working, who to follow up with, bounce or unsubscribe trends, or how platforms like Instantly, Smartlead, EmailBison, or HeyReach are performing. Also handles exploratory HeyReach social signal analysis. Read-only,

Comprehensive skill review and validation. Use when you need to audit an OpenClaw skill for correctness, completeness, and compliance with OpenClaw specifications. Performs three levels of review: (1) Format validation via package_skill.py, (2) Content quality assessment of SKILL.md structure and writing, (3) Functional verification that generated templates/scripts match actual OpenClaw specifications.