bowen31337 skills on Remote OpenClaw

intelligent-router

Classifies tasks into five complexity tiers and assigns the cheapest model capable of handling each one. Sub-agents and cron jobs that skip model selection default to expensive Sonnet, so this skill enforces explicit routing before they are created. Classification uses a 15-dimension scoring system covering reasoning markers, code presence, multi-step patterns, token count, and constraint density.

tiered-memory

Three-tier memory system (hot/warm/cold) for persistent agent memory across conversations. Facts are distilled, scored with recency decay, and organized in a hierarchical tree index. Critical state syncs to Turso after each conversation for cloud-first recovery and multi-device continuity.

typescript-lsp

TypeScript/JavaScript language server providing type checking, code intelligence, and LSP diagnostics through typescript-language-server. Supports .ts, .tsx, .js, .jsx, .mts, .cts, .mjs, and .cjs files. Runs automatically in LSP-compatible editors or via the tsc command line.

agent-access-control

Tiered contact management for AI agents on messaging platforms. Strangers get a configurable deflection message and trigger an owner notification. The owner approves, restricts, or blocks the contact by replying to the notification.

rust-analyzer-lsp

rust-analyzer is a language server for Rust that provides code intelligence through the Language Server Protocol. It offers autocomplete, go-to-definition, find references, real-time diagnostics, and refactoring in any LSP-compatible editor. It replaced the older Rust Language Server (RLS) and is now the officially maintained option.

pyright-lsp

Pyright is Microsoft's Python language server that runs static type checking and code intelligence on .py and .pyi files. It detects type errors, provides autocomplete suggestions, and supports go-to-definition and find references.

gopls-lsp

gopls is the official Go language server, providing code intelligence for .go files via the LSP protocol. It handles autocomplete, go-to-definition, find references, real-time error diagnostics, and refactoring like symbol renaming and import organization.

clangd-lsp

C/C++ language server integration using clangd, part of the LLVM project. Provides autocomplete, go-to-definition, find references, real-time diagnostics, and refactoring for C and C++ files. Works with any LSP-compatible editor.

agent-wal

Write-Ahead Log protocol for persisting agent state to disk before responding. Prevents corrections, decisions, and context from being lost when conversations are compacted. Entries are stored as append-only JSONL and can be replayed at session start to restore lost context.

agent-self-governance

Five protocols that address common agent failure modes: WAL persists context before LLM compaction, VBR prevents false task-complete claims, ADL tracks persona drift, VFM monitors token cost against task value, and IKL captures infrastructure facts before they leave context. Each protocol has its own Python script, defined triggers, and log format.

ai-media

Runs image, video, talking head, and voice synthesis jobs on a remote GPU server over SSH. Scripts wrap ComfyUI, SadTalker, and Voxtral pipelines and return output file paths when generation completes. Supports multiple models per media type with configurable style, duration, and language parameters.

identity-resolver

Maps Telegram, WhatsApp, Discord, and web channel identities to a single canonical user ID per person. Without it, the same user messaging from different channels appears as separate users, fragmenting memory, access control, and per-user state. Provides both a Python API and a CLI for skill developers and end users.