发现 Skills
为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。
lindy-rate-limits
Manage and optimize Lindy AI rate limits. Use when hitting rate limits, optimizing API usage, or implementing rate limit handling. Trigger with phrases like "lindy rate limit", "lindy quota", "lindy throttling", "lindy API limits".
missing-protections
Audits a contract against type-specific protection checklists to find gaps, then provides ready-to-insert clause language for each missing protection. Use when a user wants to know what protections are absent from their contract. Trigger with "/missing-protections" or "what protections is this contract missing".
obsidian-performance-tuning
Optimize Obsidian plugin performance for smooth operation in large vaults. Use when experiencing lag, memory issues, slow startup, or optimizing plugin code for vaults with thousands of files. Trigger with phrases like "obsidian performance", "obsidian slow", "optimize obsidian plugin", "obsidian memory usage", "obsidian lag".
perplexity-architecture-variants
Choose and implement Perplexity architecture blueprints for different scales: direct search widget, cached research layer, and multi-query pipeline. Trigger with phrases like "perplexity architecture", "perplexity blueprint", "how to structure perplexity", "perplexity project layout".
podium-core-workflow-a
Podium core workflow a — business messaging and communication platform integration. Use when working with Podium API for messaging, reviews, or payments. Trigger with phrases like "podium core workflow a", "podium-core-workflow-a".
replit-multi-env-setup
Configure Replit dev/staging/production environments with separate databases, secrets, and deployment tiers. Use when setting up multi-environment deployments, managing per-environment secrets, or implementing environment-specific Replit configurations. Trigger with phrases like "replit environments", "replit staging", "replit dev prod", "replit environment setup", "replit separate databases".
replit-webhooks-events
Handle Replit deployment events, build Replit Extensions, and set up Agents & Automations. Use when integrating with Replit deployment lifecycle, building workspace extensions, or creating automated workflows with Replit Agent. Trigger with phrases like "replit webhook", "replit events", "replit extension", "replit automation", "replit notifications", "replit agent automation".
request-body-validator
Request Body Validator - Auto-activating skill for API Development. Triggers on: request body validator, request body validator Part of the API Development skill category.
request-validator-generator
Request Validator Generator - Auto-activating skill for Backend Development. Triggers on: request validator generator, request validator generator Part of the Backend Development skill category.
sentry-multi-env-setup
Configure Sentry across development, staging, and production environments with separate DSNs, environment-specific sample rates, per-environment alert rules, and dashboard filtering. Use when setting up Sentry for dev/staging/production, managing environment-specific configurations, isolating data between environments, or configuring .env files for per-environment DSNs. Trigger: "sentry environments", "sentry staging setup", "multi-environment sentry", "sentry dev vs prod", "sentry DSN per env".
snowflake-core-workflow-a
Execute Snowflake primary workflow: data loading via stages and COPY INTO. Use when loading data from S3/GCS/Azure into Snowflake tables, setting up Snowpipe for continuous ingestion, or bulk loading files. Trigger with phrases like "snowflake load data", "snowflake COPY INTO", "snowflake stage", "snowflake ingest", "snowflake S3 load", "snowpipe".
stackblitz-core-workflow-a
Build a browser-based code editor with WebContainers: file tree, editor, terminal, and preview. Use when creating interactive coding environments, building educational tools, or embedding development environments in web apps. Trigger: "webcontainer IDE", "browser IDE", "stackblitz editor", "code playground".
supabase-hello-world
Run your first Supabase query — insert a row and read it back. Use when starting a new Supabase project, verifying your connection works, or learning the basic insert-then-select pattern with @supabase/supabase-js. Trigger with phrases like "supabase hello world", "first supabase query", "supabase quick start", "test supabase connection", "supabase insert and select".
together-cost-tuning
Together AI cost tuning for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together cost tuning".
tweetclaw
X/Twitter automation plugin. Post tweets, reply, like, retweet, follow, unfollow, send DMs, search tweets, look up users, extract bulk data, monitor accounts, run giveaway draws, and compose algorithm-optimized tweets via Xquik REST API. Use when the user asks about Twitter, X, tweets, followers, social media automation, tweet analytics, or giveaway management. Trigger with "post tweet", "search tweets", "extract followers", "run giveaway", "monitor account", "compose tweet", "trending topics".
twinmind-common-errors
Diagnose and fix TwinMind common errors and exceptions. Use when encountering transcription errors, debugging failed requests, or troubleshooting integration issues. Trigger with phrases like "twinmind error", "fix twinmind", "twinmind not working", "debug twinmind", "transcription failed".
twinmind-sdk-patterns
Apply production-ready TwinMind SDK patterns for TypeScript and Python. Use when implementing TwinMind integrations, refactoring API usage, or establishing team coding standards for meeting AI integration. Trigger with phrases like "twinmind SDK patterns", "twinmind best practices", "twinmind code patterns", "idiomatic twinmind".
vercel-common-errors
Diagnose and fix common Vercel deployment and function errors. Use when encountering Vercel errors, debugging failed deployments, or troubleshooting serverless function issues. Trigger with phrases like "vercel error", "fix vercel", "vercel not working", "debug vercel", "vercel 500", "vercel build failed".
zero-tech-debt
Rebuild a feature as if the correct product architecture existed from day one — remove compatibility cruft, dead abstractions, and historical compromises instead of preserving them. Use when the operator says "refactor properly," "clean up," "rewrite," "modernize," "remove legacy," "simplify," "rethink," "pay down tech debt," or signals frustration with accumulated complexity. Do NOT use for hotfixes, bug repros, surgical patches, or security backports — blast-radius minimization wins there. Trigger with "/zero-tech-debt", "do it right this time", "the way it should have been built", "refactor toward intent".
school
School assignment concierge for UNIR master's coursework. Triggers: '/school', '/homework', 'tengo nueva tarea', 'nueva tarea', 'new homework', 'new assignment', 'school project', 'tarea de la escuela', 'asignación nueva'. Walks the user end-to-end through: project selection (new or resume) → file intake → media preprocessing (video→text via Whisper, .pages→.md via LibreOffice) → deep maximize-score analysis with adversarial review pass → outline → drafting → Word document export. Maintains progress.md so any future session can resume. Auto-commits to git at checkpoints. Default output language is Spanish.
create-an-asset
Generate tailored sales assets (landing pages, decks, one-pagers, workflow demos) from your deal context. Describe your prospect, audience, and goal — get a polished, branded asset ready to share with customers.
nano-banana-pro
Nano Banana Pro / Gemini Image Ultra - Prompt Engineering Guide
afc:validate
Artifact consistency validation (read-only) — auto-invoked to verify spec, plan, and task artifacts are consistent with each other
merge-pr
Merge a GitHub PR via squash after /preparepr. Use when asked to merge a ready PR. Do not push to main or modify code. Ensure the PR ends in MERGED state and clean up worktrees after success.