通过脚本直连 Google Maps Platform API 完成地理编码、逆地理编码、路线规划、地点搜索、地点详情、海拔查询和时区查询。
Unified hotel comparison across Chase Edit, Amex FHR/THC, metasearch, and Airbnb, highlighting benefits and benefit-adjusted pricing.
Create daily notes and manage morning, midday, and evening routines, structuring daily planning, task review, and end-of-day reflection.
Evidence-based health research using tiered trusted sources with GRADE-inspired evidence ratings, personalized with Apple Health data.
Search flights, hotels, attractions, concerts, and travel deals with natural language via the Fliggy MCP connection.
Connect to Garmin Connect and query personal health/fitness data — steps, sleep, heart rate, HRV, body battery, training readiness…
Track progress toward 3-year, yearly, monthly, and weekly goals, calculate completion percentages, and surface stalled goals.
Search Google Flights for flight prices and schedules using browser automation.
Personal GTD (Getting Things Done) coach that helps users achieve their annual goals by breaking objectives into actionable daily steps.
Query the Apple Health SQLite database for vitals, activity, sleep, and workouts, with Markdown, JSON, and FHIR R4 output.
Best practices for Home Assistant automations, helpers, scripts, and dashboards.
Plan weekly meals interactively and generate combined shopping lists.
Nudge the user with time-based reminders (stopping times, meetings, break suggestions) that surface via a prompt-submission hook.
Guided trip planning workflow — asks destination, dates, travelers, class, and flexibility, then runs parallel flight/hotel search with…
Time-blind friendly planning, executive function support, and daily structure for ADHD brains.
分析营养数据、识别营养模式、评估营养状况,并提供个性化营养建议。支持与运动、睡眠、慢性病数据的关联分析。
Personal knowledge management for Obsidian combining GTD, Zettelkasten, and PARA across capture, inbox processing, daily planning, and…
分析睡眠数据、识别睡眠模式、评估睡眠质量,并提供个性化睡眠改善建议。支持与其他健康数据的关联分析。
分析旅行健康数据、评估目的地健康风险、提供疫苗接种建议、生成多语言紧急医疗信息卡片。
Lifestyle & Local agent skills on mcprush, filed under one heading so the shelf can be read in one pass. The kinds are workflow, expertise, output format, voice & style and guardrail, and the one a skill belongs to is the fastest way to guess what it will do to your prompt.
What to look at before installing one is what it costs in context and what it takes away: a guardrail that refuses an action and a voice that rewrites a sentence are both skills, and only one of them will stop the agent doing something. Every skill here says which kind it is, what it costs in context, what it needs beside it to work and the licence it is published under, next to the publisher it came from and whether that publisher has been verified. The filters on the left narrow it further and the sort at the top decides what comes first.
A skill is not connected to anything: there is no endpoint to authorise and nothing routed through the gateway. Installing one drops a folder of instructions into the client’s own skill folder, and uninstalling it is deleting that folder. The exact line for each client is on the skill’s own page, because it differs by client rather than by skill.