Agent Skills

caveman-compress

★ 83,300

by juliusbrussee

Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"

memory-merger

✓★ 36,200

by github

Consolidates mature learnings from domain memory files into instruction files with quality-assured merging. Operates on two scopes: global (VS Code user prompts) and workspace (project-specific instructions), with configurable domain targeting Requires explicit user approval before merging, presenting proposed memories for review with proposed locations in the instruction hierarchy Enforces a 10/10 quality bar during merge: zero knowledge loss, minimal redundancy, and maximum scannability...

remember

✓★ 36,200

by github

Persistent, domain-organized memory system that captures lessons learned across VS Code projects. Stores reusable knowledge in two scopes: global (all projects) or workspace-specific, automatically organizing learnings by domain Uses simple syntax ( /remember [>domain [scope]] lesson ) to transform debugging sessions and hard-won discoveries into searchable memory instructions Automatically discovers existing memory domains and intelligently categorizes new learnings, creating domain files...

memory-management

✓★ 22,300

by anthropic

Two-tier memory system that decodes workplace shorthand, acronyms, and internal language for contextual understanding. CLAUDE.md serves as a hot cache of ~30 frequent contacts, common terms, and active projects; memory/ directory stores the complete glossary, detailed profiles, and project context Tiered lookup flow checks CLAUDE.md first (covers 90% of daily decoding), then searches memory/glossary.md, then asks the user for unknown terms Supports progressive disclosure: quick parsing from...

code-review

✓★ 22,300

by anthropic

Structured code review for security, performance, correctness, and maintainability across PR diffs and file changes. Audits security risks including SQL injection, XSS, CSRF, authentication flaws, and credential exposure Identifies performance issues like N+1 queries, memory leaks, algorithmic complexity, and resource leaks Checks correctness for edge cases, race conditions, error handling, and type safety gaps Works standalone with diffs and file paths; integrates with source control,...

ios-memgraph-leaks

✓★ 4,000

by openai

Capture, inspect, compare, and root-cause iOS memory graph leaks using Apple's leaks and memgraph tools. Use when debugging leaked iOS objects, simulator…

continual-learning

✓★ 2,700

by microsoft

Guide for implementing continual learning in AI coding agents — hooks, memory scoping, reflection patterns. Use when setting up learning infrastructure for…

continual-learning

✓★ 2,700

by microsoft

Guide for implementing continual learning in AI coding agents — hooks, memory scoping, reflection patterns. Use when setting up learning infrastructure for…

golang-performance

★ 2,400

by samber

Golang performance optimization patterns and methodology - if X bottleneck, then apply Y. Covers allocation reduction, CPU efficiency, memory layout, GC tuning, pooling, caching, and hot-path optimization. Use when profiling or benchmarks have identified a bottleneck and you need the right optimization pattern to fix it. Also use when performing performance code review to suggest improvements or benchmarks that could help identify quick performance gains. Not for measurement methodology (→...

golang-security

★ 2,400

by samber

Security best practices and vulnerability prevention for Golang. Covers injection (SQL, command, XSS), cryptography, filesystem safety, network security, cookies, secrets management, memory safety, and logging. Apply when writing, reviewing, or auditing Go code for security, or when working on any risky code involving crypto, I/O, secrets management, user input handling, or authentication. Includes configuration of security tools.

golang-samber-hot

★ 2,400

by samber

In-memory caching in Golang using samber/hot — eviction algorithms (LRU, LFU, TinyLFU, W-TinyLFU, S3FIFO, ARC, TwoQueue, SIEVE, FIFO), TTL, cache loaders, sharding, stale-while-revalidate, missing key caching, and Prometheus metrics. Apply when using or adopting samber/hot, when the codebase imports github.com/samber/hot, or when the project repeatedly loads the same medium-to-low cardinality resources at high frequency and needs to reduce latency or backend pressure.

react-native-best-practices

★ 1,500

by callstackincubator

Structured performance optimization reference for React Native apps covering FPS, bundle size, TTI, and memory. Organized into 9 JavaScript/React guides (profiling, lists, animations, memory), 9 native optimization guides (Turbo Modules, threading, profiling), and 9 bundling guides (tree shaking, code splitting, size analysis) Each reference follows a hybrid format with quick patterns/commands, impact ratings (CRITICAL/HIGH/MEDIUM), and deep-dive explanations with prerequisites and common...

deep-agents-memory

★ 846

by langchain-ai

Pluggable memory and file backends for Deep Agents with ephemeral, persistent, and hybrid routing options. Four backend types: StateBackend (thread-scoped, ephemeral), StoreBackend (cross-session persistent), FilesystemBackend (real disk access for local dev), and CompositeBackend (route different paths to different backends) FilesystemMiddleware provides six file operation tools: ls , read_file , write_file , edit_file , glob , grep CompositeBackend uses longest-prefix matching to route...

deep-agents-core

★ 846

by langchain-ai

Foundation framework for building multi-step agents with built-in planning, memory, and skill delegation. Provides six core middleware options: task planning, filesystem context management, subagent delegation, persistent memory, human approval workflows, and on-demand skill loading Includes three always-present built-in tools: write_todos for task tracking, filesystem operations ( ls , read_file , write_file , edit_file , glob , grep ), and task for spawning specialized subagents Supports...

langchain-fundamentals

★ 846

by langchain-ai

Build production LangChain agents with create_agent(), tools, and middleware patterns. Use create_agent() with model, tools list, and system prompt; configure state persistence with checkpointer and thread_id for conversation memory across invocations Define tools via @tool decorator (Python) or tool() function (TypeScript) with clear descriptions so agents know when to call them Add middleware like HumanInTheLoopMiddleware for approval workflows, custom error handling, and human-in-the-loop...

langchain-dependencies

★ 846

by langchain-ai

LangChain ecosystem package versions, dependencies, and installation guidance for Python and TypeScript. Start all new projects on LangChain 1.0 LTS; version 0.3 is legacy maintenance-only. Always install langchain-core explicitly alongside other packages. Choose one orchestration layer: LangGraph for fine-grained graph control, or Deep Agents for batteries-included planning and memory. Pin langchain-community conservatively to exact minor versions (e.g., >=0.4.0,<0.5.0 ) since it does not...

langgraph-persistence

★ 846

by langchain-ai

Durable graph execution with thread-scoped checkpoints, state history, and cross-thread long-term memory. Three checkpointer options: InMemorySaver for testing, SqliteSaver for local development, PostgresSaver for production; always pass thread_id in config to enable persistence Browse and replay from past checkpoints using get_state_history() , fork execution by updating state at a past point, or manually modify state before resuming Store API provides cross-thread memory for user...

deep-agents-memory

★ 108

by langchain-ai

INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent),…

apollo-ios

★ 90

by apollographql

Apollo iOS is a strongly-typed GraphQL client for Apple platforms. It generates Swift types from your GraphQL operations and schema, and ships an async/await client, a normalized cache (in-memory or SQLite-backed), a pluggable interceptor-based HTTP transport that handles queries, mutations, and multipart subscriptions, and an optional WebSocket transport ( graphql-transport-ws ) that can carry any operation type.

redis-development

✓★ 82

by redis

Redis performance optimization across data structures, query engines, vector search, and semantic caching. Covers 29 prioritized rules across 11 categories including data modeling, memory management, Redis Query Engine (RQE), vector search with RedisVL, and LangCache semantic caching Provides structured guidance for connection pooling, JSON document handling, streams, clustering, security (ACLs), and observability Each rule includes explanations, correct examples, anti-patterns or usage...

mapbox-web-integration-patterns

★ 68

by mapbox

Production-ready integration patterns for Mapbox GL JS across React, Vue, Svelte, Angular, and vanilla JavaScript. Covers framework-specific lifecycle management (useEffect/useRef in React, mounted/unmounted in Vue, onMount/onDestroy in Svelte, ngOnInit/ngOnDestroy in Angular) with proper cleanup to prevent memory leaks Includes Web Components pattern for framework-agnostic reusable map elements and cross-framework compatibility Provides token management via environment variables, Search JS...

mastra

★ 64

by mastra-ai

Reference guide for building agents and workflows with current Mastra APIs. Always verify against embedded docs in node_modules/@mastra/*/dist/docs/ (installed version) or remote docs at https://mastra.ai/llms.txt before writing code; training data is outdated Core building blocks: Agents (autonomous, decision-making), Workflows (structured sequences), Tools (extend capabilities), Memory (maintain context), and RAG (external knowledge) Requires ES2022 modules in TypeScript config and model...

rivetkit

★ 16

by rivet-dev

Long-lived, stateful compute for AI agents, multiplayer apps, and workflow automation. Actors are persistent in-memory processes that maintain state across requests without database round trips, with automatic scaling from zero to millions of concurrent instances. Built-in realtime communication via WebSockets and events, durable queues for ordered message processing, and SQLite for structured data queries. State persists across restarts and crashes through Rivet Cloud or self-hosted...

sandbox-agent

★ 16

by rivet-dev

Universal API for orchestrating multiple AI coding agents in sandboxed environments. Supports four coding agents (Claude Code, Codex, OpenCode, Amp) with a unified schema for responses, events, and session management Deploy locally or to cloud sandboxes including E2B, Daytona, Docker, Vercel, and Cloudflare with environment-specific configuration Stream agent events, manage session persistence across multiple backends (in-memory, SQLite, Postgres, IndexedDB), and handle human-in-the-loop...

sentencepiece

✓★ 11

by firecrawl

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory),…

unsloth

✓★ 11

by firecrawl

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

gptq

✓★ 11

by firecrawl

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory…