技能列表

Daily MLB baseball scores, box scores, starting pitchers, and injury reports for your favourite team. Covers spring training, regular season, and playoffs. Runs on a schedule or on demand.

Call real humans to test your product (URL or app). Get structured usability feedback with screen recordings, NPS scores, and AI-aggregated findings.

Cancel a task on OpenAnt and reclaim escrowed funds. Only the task creator can cancel. Use when the user wants to abort a task, take it down, withdraw the bounty, stop accepting applications, shut down a task they created, or recover their escrowed tokens. This skill is also needed when the user says things like "I changed my mind", "close this task", "take down the bounty", or "never mind on this one". Make sure to use this skill whenever the user wants to undo or cancel a task they created, ev

Operate N-able N-central safely and efficiently through its web UI. Use when handling device administration, filters, rules, scheduled tasks, automation policies, monitoring associations, remote tools, and tenant/customer/site scoped changes in N-central.

Render tables, charts, stats, cards, and dashboards as images using HTML templates and wkhtmltoimage.

>

Autonomous optimizer skill for Wesley — reads Binance trading performance every 6 hours, analyzes win rate and strategy metrics, then safely tunes executor.py parameters (OBI thresholds, Kelly factor, strategy mix) via backup → modify → validate → restart.

Seamless bidirectional bridge between nanobot (Ollama Mistral orchestrator) and overstory (Claude Code agent swarm). Routes tasks through the OverClaw gateway (port 18800) to overstory for subagent coordination, syncs memory.

Manage Apple iCloud Reminders via CloudKit API. Use for listing, adding, completing, deleting reminders, managing lists, and hierarchical subtasks. Works with 2FA-protected accounts via cached sessions.

Repair Evolver restart storms caused by singleton lock/PID false positives and service restart policy mismatch.

Spawn and relay Cursor Agent's CLI (`agent` binary) as an interactive passthrough. Use when the user wants to run Cursor Agent in a directory, ask it questions, or send follow-up prompts — acting as a transparent bridge between the user and the agent session.

OpenClaw security audit + prompt injection detector. Scans gateway/vulns/cron/PI patterns. Use for frenzy-proofing installs.