Agent Skills

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…

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...

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…

unsloth

✓★ 11

by firecrawl

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

sentencepiece

✓★ 11

by firecrawl

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