Loading...
Loading...
Found 110 Skills
Core patterns for AI coding agents based on analysis of Claude Code, Codex, Cline, Aider, OpenCode. Triggers when: Building an AI coding agent or assistant, implementing tool-calling loops, managing context windows for LLMs, setting up agent memory or skill systems, or designing multi-provider LLM abstraction. Capabilities: Core agent loop with while(true) and tool execution, context management with pruning and compression and repo maps, tool safety with sandboxing and approval flows and doom loop detection, multi-provider abstraction with unified API for different LLMs, memory systems with project rules and auto-memory and skill loading, session persistence with SQLite vs JSONL patterns.
Token-efficient persistent memory system for Claude Code that extends your session limits by 3-5x. Layered architecture with progressive loading, compact encoding, branch-aware context, smart compression, session diffing, conflict detection, session continuation protocol, and recovery mode. Activates at session start (if MEMORY.md exists), on "remember this", "pick up where we left off", "what were we doing", "wrap up", "save progress", "don't forget", "switch context", "hand off", "memory health", "save state", "continue where I left off", "context budget", "how much context left", or any session start on a project with existing memory files. This skill solves two problems at once: Claude forgetting everything between sessions, AND sessions hitting context limits too fast. It replaces thousands of wasted re-explanation tokens with a compact, structured memory load that gives Claude full project context in under 2,000 tokens.
Use when context is growing large (50k+ tokens), performance is degrading, instructions are being ignored mid-conversation, or planning multi-agent workflows. Triggers on "lost context", forgotten instructions, or sessions exceeding 30 minutes.
Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and multi-agent conversations.
Compress documentation, prompts, and context into minimal tokens for AGENTS.md and CLAUDE.md. Achieves 80%+ token reduction while preserving agent accuracy.
Scan a Cargo workspace or package monorepo and refresh per-member `CLAUDE.md` files plus a thin root `CLAUDE.md`. User-only maintenance workflow for keeping workspace-local AI context accurate after refactors, member additions, export changes, or major architectural shifts.
Automatically activates before chapter writing to enforce a 9-item mandatory file reading checklist, which prevents AI focus degradation in long-form fiction by ensuring all context is loaded before each writing session
Context management skill providing discovery, fetching, harvesting, extraction, compression, organization, cleanup, and guided workflows for project context
Append project fragment knowledge that is "too short to warrant a separate file but needs to be known by AI every time" to fixed sections of AGENTS.md / CLAUDE.md — such as special compilation flags, services that must be started before running, path pitfalls, command aliases, and environment variable conventions. Triggers: When the user says "make a note", "add to AGENTS", "save to CLAUDE.md", "the project requires X to compile", "must do Y every time from now on", or just encountered a project-specific setting that can be explained in one sentence.
Advanced token optimization and context management strategies.
Saves, retrieves, and searches structured context (reasoning, decisions, trade-offs) behind AI-generated code, linked to git commits. Use when the developer says "save this session with GitWhy", asks about past context or decisions, or wants to push context to a PR. Also use after significant implementation work, debugging sessions, or architecture decisions.
Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.