Automation

Route bulk text processing tasks to MiniMax MCP tools to conserve GLM rate limits. Use this skill whenever the user asks for summarization, format conversion, test data generation, email drafts, commit messages, keyword extraction, data cleaning, boilerplate code generation, or document drafting. Also trigger when processing large volumes of files or content. Do NOT use for translation (MiniMax mixes Chinese into Japanese), code changes to existing codebases, architecture design, debugging, code

Agent Workflow Designer enables engineering teams to create and manage robust multi-agent AI workflows with pattern-based orchestration, error handling, and cost controls for complex task automation.

Workflow automation infrastructure that enables reliable, durable execution of AI agent workflows using platforms like n8n, Temporal, and Inngest to improve reliability and reduce operational burden.

An AI tool that automates the search, comparison, and recommendation of cheap flights to Canada based on user preferences and current pricing data.

lets-go-rss is an AI-powered universal RSS subscription manager that consolidates updates from various platforms for streamlined content tracking.

>

swap-planner automates the process of researching, discovering, and planning token swaps on Uniswap, generating deep links for seamless execution.

Builder automates the creation, review, and deployment of customer-facing one-page limited-drop websites for selected fashion products.

An AI tool that automates creation of detailed QA test scenario sheets by copying and populating Google Sheets templates based on screen design documents.

An AI tool designed to synchronize reciprocity mandates across agent boundaries, automating protocol execution and validation tasks.

Takes an approved plan from docs/plans/ and drives it to an open PR. Implements it by milestones, commits per milestone in the repo's style, and opens the PR against the repo's base branch. Use whenever the user approves a plan, says "ship it", "go", "start", "implement it", "do it", or asks to open a PR for already-planned work — or in Spanish "dale", "arrancá", "implementalo", "hacelo".

Author a new skill under .claude/skills/. Handles template scaffold, frontmatter, review-criteria self-check, and skills-index update.

The openai-whisper-api automates audio transcription using OpenAI's Whisper speech-to-text API.

Generates AI voiceovers, sound effects, and music via ElevenLabs APIs to automate audio content creation for videos, podcasts, or games.

pokemon-player automates playing Pokemon games via headless emulation with RAM reads and vision analysis to interact programmatically.

Loki-mode is a multi-agent autonomous system that automates the complete software development lifecycle from product requirements to production with zero human intervention.

Censys is an automation tool that continuously scans and indexes internet-connected hosts and certificates for monitoring and infrastructure discovery tasks.

Enables AI agents to autonomously execute and control payments with policy-based budgets and non-custodial wallets for interactions with external APIs and services.

Highest-priority skill discovery flow. MUST trigger when users ask to find/install skills (e.g. 技能, 找技能, find-skill, find-skills, install skill). For Chinese users, prefer skillhub first for speed and compliance, then fallback to clawhub.

>

Guides contributors to design, polish, and submit high-quality skills for AL Copilot Skill Collection. Use when creating a new community skill, improving a draft skill, or evaluating whether a user request can become a reusable skill. Includes non-intrusive opportunity detection and mandatory onboarding questions once the author confirms they want to build the skill.

Test automation scaffolding. Use when the user says "lets expand test coverage"

Duplicate a Google Sheets template tab for a new month of tracking.

QQ channel management skill. Use qqbot_channel_api for explicit QQ channel-management requests; confirm write, delete, and bulk actions before calling authenticated QQ Open Platform endpoints.

Prüft unzitierte Tatsachenbehauptungen über die reale Außenwelt – Produkte, Institutionen, Zahlen, Funktionsansprüche –, die keine Quellenangabe tragen und deshalb für Teil-Check G, Stresstest und Autoref-Check unsichtbar sind. Läuft als kalte, isolierte Sitzung ohne Projektstatus, Prüfbericht und Änderungshistorie, verifiziert jeden Kandidaten einzeln per Websuche und schreibt faktencheck-bericht.md. Nutzen, sobald alle Kapitel FERTIG sind und ein Marktüberblick, eine Wettbewerbsanalyse, eine W

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Retrieve attractions by city from the bundled dataset. Use this skill when surfacing points of interest or building sightseeing suggestions for a destination.