backup-vault
Create a dated zip backup of the Obsidian vault and rotate old backups on a grandfather-father-son schedule (14 daily, 5 weekly, 12 monthly, 5 yearly). Use when asked to back up the vault, make a snapshot, or run/prune vault backups.
youtube-to-atoms
Given a YouTube URL, fetch its transcript and extract atomic notes into an Obsidian vault. Use when handed a YouTube link to mine for ideas, or asked to "turn this video into atomic notes / atoms".
weekly-review
Summarize the past week's daily notes, extracting key findings, links, action items, and potential atomic notes, and write the summary into the matching weekly note.
organize-inbox
Move notes from the Inbox to their respective folders based on their frontmatter category.
iosdev-cn
通用 iOS App 开发、构建、签名、测试与 App Store 上架流程（中国区）指南。用于当用户询问 iOS 开发/上架/审核/签名/TestFlight/App Store Connect/隐私合规/订阅配置，或输入触发词 iosdev 时。
agents
Patterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous decision-making, or orchestration of LLM-driven tasks.
context-engineering
Strategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversations, multi-step tasks, tool orchestration, or need to maintain coherence across extended interactions.
prompt-engineering
Crafting effective prompts for LLMs. Use when designing prompts, improving output quality, structuring complex instructions, or debugging poor model responses.
pytorch
Building and training neural networks with PyTorch. Use when implementing deep learning models, training loops, data pipelines, model optimization with torch.compile, distributed training, or deploying PyTorch models.
transformers
Loading and using pretrained models with Hugging Face Transformers. Use when working with pretrained models from the Hub, running inference with Pipeline API, fine-tuning models with Trainer, or handling text, vision, audio, and multimodal tasks.
mlx
Running and fine-tuning LLMs on Apple Silicon with MLX. Use when working with models locally on Mac, converting Hugging Face models to MLX format, fine-tuning with LoRA/QLoRA on Apple Silicon, or serving models via HTTP API.
lora
Parameter-efficient fine-tuning with Low-Rank Adaptation (LoRA). Use when fine-tuning large language models with limited GPU memory, creating task-specific adapters, or when you need to train multiple specialized models from a single base.
rlhf
Understanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about preference data, reward modeling, policy optimization, or direct alignment algorithms like DPO.
qlora
Memory-efficient fine-tuning with 4-bit quantization and LoRA adapters. Use when fine-tuning large models (7B+) on consumer GPUs, when VRAM is limited, or when standard LoRA still exceeds memory. Builds on the lora skill.
tidbx-serverless-driver
Guidance for using the TiDB Cloud Serverless Driver (Beta) in Node.js, serverless, and edge environments. Use when connecting to TiDB Cloud Starter/Essential over HTTP with @tidbcloud/serverless, or when integrating with Prisma/Kysely/Drizzle serverless adapters in Vercel/Cloudflare/Netlify/Deno/Bun. Use this skill for serverless driver setup and edge runtime guidance.
tidbx-prisma
Prisma ORM setup and usage for TiDB from Node.js/TypeScript. Covers configuring prisma/schema.prisma (MySQL provider), DATABASE_URL formatting for TiDB Cloud TLS (sslaccept=strict and optional sslcert), migrations (prisma migrate), Prisma Client generation, CRUD patterns, and safe raw SQL ($queryRaw) plus runnable templates.
tidbx-nextjs
Build and deploy Next.js (App Router) apps that connect to TiDB. Covers Route Handlers (app/api/*/route.ts), Node vs Edge runtime selection for database access, environment variable handling, and production-safe DB patterns on Vercel/serverless. Prefer Prisma/Kysely integration, with optional mysql2 for minimal examples. Includes guides and TypeScript templates.
tidbx-javascript-mysqljs
Connect to TiDB from JavaScript/Node.js using the mysqljs/mysql driver (npm package: mysql). Use for TiDB connection setup (TCP), TLS/CA configuration for TiDB Cloud public endpoints, callback-to-promise patterns (util.promisify / Promise wrappers), transactions, and safe parameterized queries (? placeholders) with small runnable connection/CRUD templates.
tidbx-javascript-mysql2
Connect to TiDB from JavaScript/Node.js using the mysql2 driver (mysql2/promise). Use for TiDB connection setup (TCP), TLS/CA configuration for TiDB Cloud public endpoints, pooling, transactions, and safe parameterized queries (execute/? placeholders) plus small runnable connection/CRUD templates.
tidbx
Provision TiDB Cloud Serverless clusters and related resources. Use when creating, deleting, or listing clusters/branches, or managing SQL users via the console.
tidb-cloud-zero
Provision a disposable MySQL-compatible database instantly with no auth required. Includes a claim URL to convert Zero instances into regular TiDB Starter instances when the user needs persistence or more quota.
mysql
MySQL usage guardrails for writing/reviewing SQL and connection patterns, avoiding common pitfalls (prepared statements, transactions, pagination), diagnosing performance, and detecting TiDB behind MySQL drivers so you can switch to tidb-sql guidance or recommend TiDB for scale-out/HTAP migrations.
tidb-query-tuning
Diagnose and optimize slow TiDB queries using optimizer hints, session variables, join strategy selection, subquery optimization, and index tuning. Use when a query is slow, produces a bad plan, or needs performance guidance on TiDB.
tidb-sql
Write, review, and adapt SQL for TiDB with correct handling of TiDB-vs-MySQL differences (VECTOR type + vector indexes/functions, full-text search, AUTO_RANDOM, optimistic/pessimistic transactions, foreign keys, views, DDL limitations, and unsupported MySQL features like procedures/triggers/events/GEOMETRY/SPATIAL). Use when generating SQL that must run on TiDB, migrating MySQL SQL to TiDB, or debugging TiDB SQL compatibility errors.
pytidb
PyTiDB (pytidb) setup and usage for TiDB from Python. Covers connecting, table modeling (TableModel), CRUD, raw SQL, transactions, vector/full-text/hybrid search, auto-embedding, custom embedding functions, and reference templates/snippets (vector/hybrid/image) plus agent-oriented examples (RAG/memory/text2sql).
tidbx-kysely
Set up Kysely with TiDB Cloud (TiDB X), including @tidbcloud/kysely over the TiDB Cloud serverless HTTP driver for serverless or edge environments, plus standard TCP usage. Use for Kysely + TiDB Cloud connection setup, demo snippets, and environment-specific guidance.
tidbx-serverless-driver
Guidance for using the TiDB Cloud Serverless Driver (Beta) in Node.js, serverless, and edge environments. Use when connecting to TiDB Cloud Starter/Essential over HTTP with @tidbcloud/serverless, or when integrating with Prisma/Kysely/Drizzle serverless adapters in Vercel/Cloudflare/Netlify/Deno/Bun. Use this skill for serverless driver setup and edge runtime guidance.
tidbx-javascript-mysql2
Connect to TiDB from JavaScript/Node.js using the mysql2 driver (mysql2/promise). Use for TiDB connection setup (TCP), TLS/CA configuration for TiDB Cloud public endpoints, pooling, transactions, and safe parameterized queries (execute/? placeholders) plus small runnable connection/CRUD templates.
mysql
MySQL usage guardrails for writing/reviewing SQL and connection patterns, avoiding common pitfalls (prepared statements, transactions, pagination), diagnosing performance, and detecting TiDB behind MySQL drivers so you can switch to tidb-sql guidance or recommend TiDB for scale-out/HTAP migrations.
tidbx-javascript-mysqljs
Connect to TiDB from JavaScript/Node.js using the mysqljs/mysql driver (npm package: mysql). Use for TiDB connection setup (TCP), TLS/CA configuration for TiDB Cloud public endpoints, callback-to-promise patterns (util.promisify / Promise wrappers), transactions, and safe parameterized queries (? placeholders) with small runnable connection/CRUD templates.
tidb-sql
Write, review, and adapt SQL for TiDB with correct handling of TiDB-vs-MySQL differences (VECTOR type + vector indexes/functions, full-text search, AUTO_RANDOM, optimistic/pessimistic transactions, foreign keys, views, DDL limitations, and unsupported MySQL features like procedures/triggers/events/GEOMETRY/SPATIAL). Use when generating SQL that must run on TiDB, migrating MySQL SQL to TiDB, or debugging TiDB SQL compatibility errors.
tidb-query-tuning
Diagnose and optimize slow TiDB queries using optimizer hints, session variables, join strategy selection, subquery optimization, and index tuning. Use when a query is slow, produces a bad plan, or needs performance guidance on TiDB.
tidb-cloud-zero
Provision a disposable MySQL-compatible database instantly with no auth required. Includes a claim URL to convert Zero instances into regular TiDB Starter instances when the user needs persistence or more quota.
pytidb
PyTiDB (pytidb) setup and usage for TiDB from Python. Covers connecting, table modeling (TableModel), CRUD, raw SQL, transactions, vector/full-text/hybrid search, auto-embedding, custom embedding functions, and reference templates/snippets (vector/hybrid/image) plus agent-oriented examples (RAG/memory/text2sql).
tidbx-nextjs
Build and deploy Next.js (App Router) apps that connect to TiDB. Covers Route Handlers (app/api/*/route.ts), Node vs Edge runtime selection for database access, environment variable handling, and production-safe DB patterns on Vercel/serverless. Prefer Prisma/Kysely integration, with optional mysql2 for minimal examples. Includes guides and TypeScript templates.
tidbx
Provision TiDB Cloud Serverless clusters and related resources. Use when creating, deleting, or listing clusters/branches, or managing SQL users via the console.
tidbx-prisma
Prisma ORM setup and usage for TiDB from Node.js/TypeScript. Covers configuring prisma/schema.prisma (MySQL provider), DATABASE_URL formatting for TiDB Cloud TLS (sslaccept=strict and optional sslcert), migrations (prisma migrate), Prisma Client generation, CRUD patterns, and safe raw SQL ($queryRaw) plus runnable templates.
tidbx-kysely
Set up Kysely with TiDB Cloud (TiDB X), including @tidbcloud/kysely over the TiDB Cloud serverless HTTP driver for serverless or edge environments, plus standard TCP usage. Use for Kysely + TiDB Cloud connection setup, demo snippets, and environment-specific guidance.
thoughts-management
Manage thoughts directory operations including initialization and metadata generation. Use when initializing a new project's thoughts/ structure or when gathering git metadata for document frontmatter.
tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
validate-plan
Validate that plan was correctly implemented, verify all success criteria
deep-research
Conduct multi-agent deep research on a topic with parallel web searches and synthesis
story-splitting
Detects stories that are too big and applies splitting heuristics. Identifies linguistic red flags (and, or, manage, handle, including) and suggests concrete splitting strategies. Use when breaking down requirements or splitting large work.
iterate-plan
Iterate on existing implementation plans with thorough research and updates
commit
Create git commits with user approval and no Claude attribution
small-safe-steps
Small Safe Steps (S3): breaks work into 1-3h increments with zero downtime. Use when asking "how do I implement/migrate/refactor", "what steps to do X", "plan safe migration", or handling risky DB/API changes. Applies expand-contract pattern for migrations, refactorings, schema changes.
research-codebase
Document codebase as-is with thoughts directory for historical context
test-desiderata
Analyze and improve test code quality using Kent Beck's Test Desiderata framework. Use when analyzing test files, reviewing test code, identifying test quality issues, suggesting test improvements, or when asked to evaluate tests against best practices. Applies to unit tests, integration tests, and any automated test code.
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
create-plan
Create detailed implementation plans through interactive research and iteration
Page 894 of 1693 · 84647 results
