Skills
99,719 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: tool descriptions are more important than tool implementations.
A commit message format checker invoked by the git commit-msg hook. The authoritative source for conventions is conventions.yml in philtzjp/.github. Use when the hook stops with “no format checker,” when you disagree with the check results, or when configuring the hook. Follow the github skill for how to write the format itself.
Refer to this when designing, implementing, or verifying Git hook chains (especially commit-msg and adding or removing Co-authored-by) in the Cursor Cloud Agent environment. Defines the execution order for Cursor-managed hooks, the naming convention `commit-msg.cursor.co-author-strip`, install scripts, layered lefthook defenses, and test procedures.
When you have a decision to make and want a structured workflow that picks the load-bearing questions, walks through them, reaches a call (or "wait"), and archives the rationale for future reference. Based on the 37signals Guide to Making Decisions (38 questions) plus house additions like Q39 opportunity cost ("what does saying yes displace?"). Triages to 6–8 relevant questions per decision instead of forcing the full set. Archives every decision to ~/.config/makerskills/decide/archive/ with a revisit date so you can check later whether the call was right. Triggers on "/decide," "help me decide," "should I [X]," "I need to make a decision about," "stuck on a decision," "deciding between," "go/no-go on," "what should I do about." This is both the decision-making workflow AND the decision log — making the decision is the act of logging it.
Orderbook depth (5/10-level bid/ask), broker queue (HK only), and tick-by-tick trades for stocks via Longbridge Securities. Use for orderbook microstructure questions. Triggers: "盘口", "买卖盘", "5 档", "10 档", "深度", "经纪商队列", "逐笔", "tick", "成交明细", "盤口", "買賣盤", "5 檔", "10 檔", "經紀商隊列", "逐筆", "成交明細", "depth", "orderbook", "level 2", "broker queue", "tick data", "trades", "time and sales".
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also triggers for Next.js apps needing memory-augmented AI. DO NOT TRIGGER when: user asks about direct Python/TS SDK calls without Vercel (use mem0 skill), or CLI terminal commands (use mem0-cli skill).
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.
Main entry point for WeChat Official Account content: completes topic selection, material gathering, writing and review, and independently adds images, formatting, or draft-box publishing as requested by the user. Also responsible for dispatching style settings, learning edits, data reviews, and multi-platform rewrites to the corresponding wewrite-* modules. Trigger keywords: 公众号, 微信文章, 微信推文, 草稿箱, 微信排版, 写公众号, 写一篇. General articles, blogs, emails, short videos, and website SEO do not trigger it.
Writes and reviews Swift App Intents code that exposes app actions and data to Siri, Shortcuts, Spotlight, widgets, Control Center, and Apple Intelligence. Use when adding AppIntent, AppEntity, OpenIntent, AppShortcutsProvider, EntityQuery, Focus Filters, AssistantEntity/AssistantIntent schemas, on-screen awareness, LongRunningIntent/CancellableIntent, EntityCollection, SyncableEntity, AppIntentsTesting, or when wiring SwiftData/networked data into intents.
Converts Markdown to styled HTML with WeChat-compatible themes. Supports code highlighting, math, PlantUML, footnotes, alerts, and infographics. Use when user asks for "markdown to html", "convert md to html", "md转html", or needs styled HTML output from markdown.
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Database selection, schema definition, connections, and migrations. For Postgres, use Neon; for SQLite, use Cloudflare D1; for ORM, use Drizzle. Separate connection targets and roles with app_migrations and app_application. Migrate data in this order: get counts, dry run, validate, run in production, remove the API. Use when asked to change schemas, perform migrations, bulk-convert existing records, add or modify DB connection settings, or review them.
Methodically investigate a bug in 4 validated phases: locate/reproduce, 3 ranked root-cause hypotheses, targeted logs, minimal fix. Use on /investigue, or as soon as the user describes a symptom ("it crashes when…", "I see X but expect Y", "unexpected behavior", "why does it crash", "investigate this bug", "debug this", "analyze the bug"). Never propose an immediate fix — each phase stops and waits for explicit validation before proceeding to the next.
Industry supply-chain analysis via Longbridge Securities — maps upstream / midstream / downstream structure for a sector, identifies key bottleneck nodes, assesses bargaining power and profitability at each tier, and evaluates investment value of core supply-chain companies using Longbridge data. Triggers: "产业链", "供应链", "上中下游", "产业链分析", "供应链分析", "咽喉环节", "卡脖子", "产业链投资", "产业链研究", "產業鏈", "供應鏈", "上中下游", "產業鏈分析", "供應鏈分析", "咽喉環節", "supply chain", "value chain", "upstream midstream downstream", "supply chain analysis", "bottleneck", "industry chain", "supply chain investment".
Set up and use the PrimeVue UI component library in Vue/Vite projects with auto-import, theming, and component configuration. Use when working with PrimeVue components, setting up PrimeVue in a Vue project, configuring themes (Aura, Lara, etc.), or implementing auto-import for PrimeVue components.
When the user wants to apply psychological principles to sales conversations, understand buyer behavior, or use persuasion techniques ethically. Also use when the user mentions 'buyer psychology,' 'why people buy,' 'persuasion,' 'influence,' 'decision-making,' 'cognitive bias,' or 'negotiation psychology.' This skill provides 70+ mental models organized for sales application.
Download videos from 1800+ platforms (YouTube, Bilibili, Twitter/X, TikTok, Vimeo, Instagram, etc.) and generate complete resource package with video, audio, subtitles, and AI summary. Actions: summarize, download, transcribe, extract video content. Platforms: youtube.com, bilibili.com, twitter.com, x.com, tiktok.com, vimeo.com, instagram.com, twitch.tv. Outputs: MP4 video, MP3 audio, VTT subtitles with timestamps, TXT transcript, MD AI summary. Auto-installs uv, yt-dlp, ffmpeg. Python dependencies managed by uv.
Zig cross-compilation skill. Use when cross-compiling Zig programs to different targets, using Zig's built-in cross-compilation for embedded, WASM, Windows, ARM, or using zig cc to cross-compile C code without a system cross-toolchain. Activates on queries about Zig cross-compilation, zig target triples, zig cc cross-compile, Zig embedded targets, or Zig WASM.
Get a second opinion from leading AI models on code, architecture, strategy, prompting, or anything. Queries models via OpenRouter, Gemini, or OpenAI APIs. Supports single opinion, multi-model consensus, and devil's advocate patterns. Trigger with 'brains trust', 'second opinion', 'ask gemini', 'ask gpt', 'peer review', 'consult', 'challenge this', or 'devil's advocate'.
Complete bug bounty workflow — recon (subdomain enumeration, asset discovery, fingerprinting, HackerOne scope, source code audit), pre-hunt learning (disclosed reports, tech stack research, mind maps, threat modeling), vulnerability hunting (IDOR, SSRF, XSS, auth bypass, CSRF, race conditions, SQLi, XXE, file upload, business logic, GraphQL, HTTP smuggling, cache poisoning, OAuth, timing side-channels, OIDC, SSTI, subdomain takeover, cloud misconfig, ATO chains, agentic AI), LLM/AI security testing (chatbot IDOR, prompt injection, indirect injection, ASCII smuggling, exfil channels, RCE via code tools, system prompt extraction, ASI01-ASI10), A-to-B bug chaining (IDOR→auth bypass, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth), bypass tables (SSRF IP bypass, open redirect bypass, file upload bypass), language-specific grep (JS prototype pollution, Python pickle, PHP type juggling, Go template.HTML, Ruby YAML.load, Rust unwrap), and reporting (7-Question Gate, 4 validation gates, human-tone writing, templates by vuln class, CVSS 3.1, PoC generation, always-rejected list, conditional chain table, submission checklist). Use for ANY bug bounty task — starting a new target, doing recon, hunting specific vulns, auditing source code, testing AI features, validating findings, or writing reports. 中文触发词：漏洞赏金、安全测试、渗透测试、漏洞挖掘、信息收集、子域名枚举、XSS测试、SQL注入、SSRF、安全审计、漏洞报告
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.