Discover AI Agent Skills

Runs a focused 15–30 minute rehearsal loop on a single weakness from a prior mock-interview debrief (or a free-text gap description). Decomposes the weakness into 3–5 testable micro-goals, drills each with in-character probes, gives tight corrective feedback after each answer, and re-verifies understanding from a fresh angle. Ends with an updated dimension score and a "ready / keep practicing" verdict. Use when the user says rehearse weakness N, drill weakness N, 复盘短板 N, 针对性补短板, practice gap, or references a prior debrief file and asks to drill one gap.

This skill provides the foundational framework for AI Constitutional governance. Use this when establishing AI agent behavioral standards, creating new constitutional provisions, interpreting fundamental AI rights and duties, resolving conflicts between AI operational rules, or amending constitutional principles. This skill encompasses the Preamble, Amendment procedures, definitions, interpretation guidelines, and the supreme law principles that govern all AI constitutional matters.

Scan a folder of deployed skills and regenerate a one-pager Markdown inventory and an HTML catalogue. Each entry shows the challenge the skill addresses and the solution it provides, hyperlinked to the skill directory. Re-run on command to keep the catalogue current.

小红书每日爆款笔记是追踪小红书各领域每日趋势，监测不同领域的实时热度变化，识别正在起量的内容方向，预判下一波流量风口。最终基于当日爆款内容，提炼可复用的选题、话术与呈现形式，生成创作灵感。支持分类查询当日热门笔记，按美妆、穿搭、美食等分类检索小红书当天热度最高的笔记，快速掌握各赛道头部内容。

Compact the current conversation into a handoff document so a fresh agent can pick up the work.

Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via headless `claude -p` subprocesses, aggregate results into a polished report file. Use for systematic web/document research, competitive or industry analysis, batch link/dataset processing, and long-form evidence synthesis. Triggers: "深度调研", "deep research", "wide research", "多 Agent 调研", "系统调研".

Applies QML best practices when producing or working with QML source code. Use whenever QML code is the primary subject: writing, reviewing, fixing, refactoring, optimizing, or debugging QML files, components, or bindings. Do NOT trigger for purely conversational QML questions where no code is produced or examined (e.g. "explain how anchors work").

Astro content-focused web framework. Covers islands architecture, content collections, and multi-framework support. Use when building content-heavy or static websites. USE WHEN: user mentions "Astro", asks about "islands architecture", "content collections", "Astro components", "client directives", "Astro.glob", "static site generation with Astro", "multi-framework in Astro" DO NOT USE FOR: Next.js - use `nextjs-app-router` instead; Nuxt - use `nuxt3` instead; SvelteKit - use `sveltekit` instead; Gatsby - use Astro as modern alternative; pure React/Vue/Svelte - use respective framework skills

Terraform task patterns — common workflows and pipeline steps. PROACTIVELY activate for: (1) terraform init/plan/apply/destroy workflows, (2) terraform fmt and validate in CI, (3) workspace management (terraform workspace), (4) remote state backends (Azure Storage, S3, Terraform Cloud), (5) state locking and DynamoDB locks, (6) terraform import for existing resources, (7) terraform refresh and drift detection, (8) -target and -replace use cases, (9) version pinning (required_version, required_providers), (10) tfvars file conventions for environments. Provides: workflow templates, backend configuration examples, state-locking setup, import recipes, and CI pipeline patterns.

Generates comprehensive GitHub activity reports across all authenticated accounts. Gathers repos, PRs, features, and themes for configurable time periods (1/5/7/30/90 days). Produces shareable markdown with tables, mermaid charts, and executive summaries. Can create a private repo with GitHub Actions automation and GitHub Pages aggregation site. Use when: "github report", "work report", "activity summary", "what did I work on", "gh-work-report", "show my github activity".

Discover bounded OpenAQ air-quality monitoring locations and retrieve raw, hourly, or daily measurements for one known sensor through the Tiangong CLI. Use when a task needs OpenAQ location, provider, sensor, parameter, license, coverage, or time-series context; do not use for arbitrary API paths, S3 archive downloads, AQI calculation, health or regulatory decisions, forecasting, source attribution, or cross-sensor analysis.

Master modern SQL with cloud-native databases, OLTP/OLAP optimization, and advanced query techniques. Expert in performance tuning, data modeling, and hybrid analytical systems. Use PROACTIVELY for database optimization or complex analysis.

Crypto market data from AiCoin Open API v3 — 200+ exchanges, real-time. Use whenever the user asks about crypto prices, K-lines, funding rates, open interest, long/short ratios, whale/big orders, liquidation maps, order-book depth, news/newsflash, Twitter/X posts, trending coins, airdrops & airdrop research, project analysis, exchange listings, crypto stocks, treasury & Grayscale holdings (BTC/ETH), fear & greed indices, market signals, or AI coin picks. Triggers: 'BTC price', '查行情', '看价格', '大饼多少钱', 'K线', '资金费率', '多空比', '持仓量', '鲸鱼单', '大单', '清算', 'liquidation map', '深度', '快讯', '推特', '热门币', 'trending', '空投', '空投研报', '项目分析', '上了哪些交易所', 'ETF', '监管', '灰度', '国库', '上市公司持币', '恐慌贪婪指数'. ALWAYS run the script for real data — NEVER invent prices or use web_search/web_fetch/browser for crypto data. Use aicoin-hyperliquid for HL whale/trader analytics, aicoin-trading for CEX orders, aicoin-freqtrade for bots, aicoin-onchain for DEX swaps.

Walk the guided 6-gate release runbook (G0 readiness, G1 adversarial review, G2 version bump and CHANGELOG, G2.5 commit and re-verify, G3 tag and push, G4 post-tag hygiene) via the pm-release-conductor sub-agent. Refuses gate bypasses and tags only the re-verified SHA. Use when cutting a pm-skills release.

Use when users need ESP32 FreeRTOS or RP2040 multicore patterns for task creation, queues, synchronization, memory checks, task notifications, or cross-core coordination.

Execute this skill empowers AI assistant to perform regression analysis and modeling using the regression-analysis-tool plugin. it analyzes datasets, generates appropriate regression models (linear, polynomial, etc.), validates the models, and provides performa... Use when analyzing code or data. Trigger with phrases like 'analyze', 'review', or 'examine'.

蒸馏Steve Jobs思维模式的实用框架。当需要极简设计、用户体验偏执、产品哲学式思考时激活。

Creates algorithmic music composition systems using procedural generation, Markov chains, L-systems, and neural approaches for ambient, adaptive, and experimental music.