Monitors token usage and context load to prevent interruption, automatically switching to backup models when thresholds are exceeded.

Reference tool for devtools — covers intro, quickstart, patterns and more. Quick lookup for Cc Switch concepts, best practices, and implementation patterns.

Simple model router for OpenClaw. Switch between available models based on task type. No manual config needed — just use natural language.

Switch between LLM models on the Huddle01 GRU gateway. Use this skill whenever the user mentions switching models, changing models, upgrading, downgrading, "...

Switch AI models on-the-fly between local LM Studio and cloud Kimi API in OpenClaw with simple commands and automatic gateway restart.

Switch between configured LLM API providers including MiniMax, SCNET, OpenRouter, and Volcano Engine using OpenClaw CLI commands.

Switch OpenClaw ElevenLabs TTS voices by updating ~/.openclaw/openclaw.json, keeping Chinese-safe defaults, and restarting the gateway.

Switch between AI models dynamically to optimize costs and performance. Use when the user says mode commands like "eco mode", "balanced mode", "smart mode", or "max mode", or when they want to check their current mode with "/modes status" or configure modes with "/modes setup".

Use when the user wants Codex to speed test Clash Verge Rev or Mihomo proxies, auto-detect currently used Clash groups from the live controller, switch a sel...

Switches OpenClaw between life modes (Work/Focus, Personal, Creative, Do Not Disturb). Triggered by natural language or calendar events. Each mode reshapes n...

Self-healing infrastructure guardian. Monitors services, diagnoses failures, executes recovery playbooks, and learns from incidents.

Zero-friction RealmRouter model manager for OpenClaw. Chat-first workflow for setting API key, guided model picking, switching with availability check, rollb...

tmux for AI Agents — Orchestrate multiple AI coding agents in parallel with one command. Run Claude Code, Codex CLI, and Gemini CLI simultaneously on isolate...

Indexed by skills.sh from aradotso/devtools-skills

Indexed by skills.sh from forcedotcom/sf-skills

Indexed by skills.sh from wind-information-co-ltd/wind-skills

Indexed by skills.sh from ar9av/obsidian-wiki

Indexed by skills.sh from max-sixty/worktrunk

Maintains and transfers context across sessions, models, and time to avoid repeating information on every new interaction or model switch.

Watches your desktop activity, maintains a real-time task stack, detects when you forget what you were doing after interruptions, and gently reminds you. You...

Automatically save, restore, and switch project session contexts to retain tasks, decisions, file states, blockers, and environment details across work sessi...

Get comprehensive context about a location including nearby places, area description, and optional weather. Use when you need to understand what's around a l...

Control ClashX VPN via Peekaboo to test latency and switch to the US proxy node with the lowest latency using menu bar automation.

Manage how OpenClaw routes Telegram messages to different Claude model backends. Switch between CLI and API providers with simple config changes.

Local OpenClaw skill for managing multiple OpenAI Codex accounts through auth snapshots. Use when the user wants to add a Codex account, switch between Codex...

Emergency kill switch for OpenClaw agents. Instantly halts all running agents, pauses scheduled jobs, kills active sessions, and logs everything — triggered...

Automatically switch between different AI models based on task complexity. Supports all available models in your OpenClaw setup. Triggers when detecting comp...

Switch the OpenClaw default model safely. Triggers: switch model, change model, 切换模型, 换模型, switch to XX model. Use when the user wants to change the default...

Instantly switch the current OpenClaw session model; supports gpt, claude, qianwen, minimax, current model status, configured model listing, and restoring th...

Create and switch between AI assistant personalities. Use /personality to list and activate saved personalities. Use /create-personality to design new personas with auto-filled SOUL and IDENTITY. Personalities persist across session boundaries and conversation compacting with …

Add 8 security governance layers to your OpenClaw agent — budget controls, permissions, audit logging, kill switch, identity signing, skill vetting, process isolation, and gateway protection.

Activate when: user asks why customers don't switch to a better product, how to make a product stickier or build a moat, how to compete against an entrenched...

Universal Model Switcher V7.1.0 - Only switch within your existing models.

Organize and switch between named skill groups to keep context focused, list available groups, and manage skill assignments efficiently.

Automatically selects the best model based on task type and requirements. Use when: (1) Task requires specific capabilities (coding, analysis, multimodal, wr...

Manage multiple OpenAI Codex accounts by capturing current login tokens, switching between saved accounts, and auto-selecting the best one based on quota bud...

Orchestrates a virtual engineering team with 7 roles working sequentially: Think, Plan, Build, Review, Test, Ship, and Reflect via shared memory coordination.

Seamless model handoff for OpenClaw agents. Ensures continuity when the gateway switches to a fallback model mid-session.

Enforces MFA by requiring a secret word to access protected sensitive data and allows emergency reset with a super secret word.

Automatically monitors model health and switches between primary and fallback models to maintain stability and recover when possible.

Safely configure OpenClaw AI models by validating roles, autoloading backups, blocking unsafe changes, and managing via CLI or Canvas UI.

Use CCAPI unified AI API gateway to access 60+ models (GPT-5.2, Claude, Gemini, DeepSeek, Sora 2, Kling 3.0, Seedance 2.0, Suno, etc.) across text, image, vi...

Web-first, publishable OpenClaw skill for OpenAI OAuth account switching. Use when you need a reusable public-track workflow for first-run takeover, environm...

Source-distributed deterministic execution service with pinned dependencies. Runs only with a signed approval artifact (ClawShield mode) and emits verifiable...

Teach an agent to install Prompt Switchboard's local MCP sidecar, connect it in a host, and run a compare-first browser workflow.

Universal Smart Model Switcher V3 - Multi-Provider, Multi-Model intelligent switching. Automatically selects the best model from ALL your purchased API plans...

Universal Smart Model Switcher V3 - Multi-Provider, Multi-Model intelligent switching. Automatically selects the best model from ALL your purchased API plans...

Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default): factual Q&A, greetings, reminders, status checks, lookups, simple file ops, heartbeats, casual chat, 1-2 sentence tas…

Cost-optimize AI agent operations by routing tasks to appropriate models based on complexity. Use this skill when: (1) deciding which model to use for a task...

Control and query SwitchBot devices using the official OpenAPI (v1.1). Use when the user asks to list SwitchBot devices, get device status, send commands, qu...

Autonomous operator for Switchboard on-demand feeds, Surge streaming, and randomness. Designs jobs, simulates via Crossbar, and deploys/updates/reads feeds across Solana/SVM, EVM, Sui, and other Switchboard-supported chains—with user-controlled security, spend limits, and allo…

Control SwitchBot smart home devices (curtains, plugs, lights, locks, etc.) via SwitchBot Cloud API. Use when user asks to open/close curtains, turn on/off l...

Switchgear specification manager. Use when json switchgear tasks, csv switchgear tasks, checking switchgear status.

Verify the optional local Switchyard runtime path without changing Campus-owned response semantics.

Guide to install, connect, and use Switchyard's read-only MCP runtime diagnostics for analyzing provider or runtime boundaries safely.

Indexed by skills.sh from forcedotcom/afv-library

Context window hygiene for long-running LLM agents. Decision rules for when and how to compress, mask, switch, or delegate context — backed by research (JetB...

Automatically detects and manages the active project context based on user messages to provide relevant project-aware assistance.

Dynamic context preprocessor for OpenClaw agents. Selects relevant memory, collapses timelines, detects forbidden patterns, and injects task-specific context...

Persistent context survival for OpenClaw. Writes file-based anchors to memory/anchors/ to preserve critical context across sessions. Reads MEMORY.md and dail...

Optimize OpenClaw agent context files by reducing token usage 30-50% with backups, preview, rollback, and preserving core functionality on request.

Automatic context compression for OpenClaw sessions. Summarizes long conversations into structured digests (decisions, facts, pending items, technical detail...

Prevent context overflow with automatic session truncation and memory preservation.

Use Context Hub (chub) to fetch versioned API docs/skills before coding, then persist learnings with annotations.

Caches and manages frequently used context fragments to avoid redundant processing by saving, listing, and clearing cached data.

Skill that restores conversation context when users want to "continue where we left off".

See exactly what's eating your context window. Analyzes prompts, conversations, and system instructions to show where every token goes. Actionable compressio...

Continuous session event recording for inter-session memory survival. Use when you want to persist conversation context between sessions, prevent memory loss...

Deterministic memory/context pipeline with semantic retrieval checks, compression/lint, safe fallback, and memory watchdog.

This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentio...

Compresses older OpenClaw agent session history into a bounded, lane-change-aware context capsule — keeps recent messages verbatim, flags abandoned directions, quarantines injected instructions, and redacts secrets. Local, deterministic, any model.

Compress OpenClaw session context to reduce token usage and extend session lifetime. Uses NLP summarization (Sumy) to intelligently compact conversation history while preserving essential context. Triggers on mentions of session compression, token reduction, context cleanup, o…

Fetches recent Telegram messages at session start to maintain conversation context across sessions, with toggle and manual fetch commands.

Memory management system with automated tiered storage (hot/warm/gist/forgotten), time-decay organization, promotion engine, layer-search protocol, and sessi...

Pure Python memory manager for preserving and retrieving multi-layered AI memories across sessions, topics, and time without external dependencies.

Know the file you're editing is the file you think it is — verify integrity before you act

Memory management system powered by ReMe. Enables cross-session memory persistence, automatic user preference application, and intelligent context compressio...

This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding…

Agent Context Manager: Manage reusable Agent Context documents -- structured. Use when an agent needs agent context manager, define a brand voice and style g...

Cross-agent context sharing via shared files. Agents write trends, highlights, and signals to a shared folder. Other agents read before acting — creating coo...

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, o...

OpenClaw wrapper for Muratcan Koylan's Agent Skills for Context Engineering. 13 skills covering context optimization, multi-agent patterns, memory systems, t...

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, o...

Coder-agent working-file budget discipline: keep the editable working set (files you /add into writable context) under ~25k tokens, separate "read" from "edi...

Slash OpenClaw token costs and prevent context overflow. Use whenever the user mentions high API costs, expensive tokens, context truncation, context overflo...

Shared production context, operational paths, orchestration policies, agent routing, approvals, deployment and execution standards for all Alazab Portal AI agents, models, sessions and nodes.

Automatically read relevant context before major actions. Loads TODO.md, roadmap.md, handoffs, task plans, and other project context files so the AI operates with full situational awareness. Use when starting a task, implementing a feature, refactoring, debugging, planning, or…

Inspect and edit the workspace's git-backed context repository (the GTM knowledge base of markdown/MDX files) and its runtime sandbox using the Cargo CLI. Us...

Token-efficient agent behavior — response sizing, context pruning, tool efficiency, and delegation

Give isolated sessions (cron jobs, sub-agents, event handlers) full conversation context from your main session using sessions_history. Run cheap background...

Recover from context compaction by scanning memory files and surfacing where you left off. Use when waking up fresh, after compaction, or when you feel lost about what you were doing.

Use this skill when managing long-context conversations and tasks. Provides intelligent compression, key extraction, context enhancement, memory retrieval, a...

Audits your agent’s context token usage to identify waste and provides a 3-week actionable roadmap to reduce AI cost by 30-40% without quality loss.

Manage and optimize OpenClaw context window usage via partitioning, pre-compression checkpointing, and information lifecycle management. Use when the session context is near its limit (>80%), when the agent experiences "memory loss" after compaction, or when aiming to reduce t…

Manage and optimize OpenClaw context window usage via partitioning, pre-compression checkpointing, and information lifecycle management. Use when the session...

Generate LLM-optimized codebase context from any directory using context-builder CLI

Analyze and archive low-value memory notes in OpenClaw workspace to reduce context bloat and improve responsiveness. 适用于上下文冗余、维护整理场景；默认流程为 analyze → plan → c...

Token-based context compaction for local models (MLX, llama.cpp, Ollama) that don't report context limits.

Use this skill whenever the conversation context is getting long, when a user asks to "compress", "summarize", or "clean up" the conversation, or when you de...