Skill suite for better usage of agent ( openclaw, hermes and more)
Songhonglei/better-agent-skills
Skill Claude CodeCodex
A tool for changing an OpenClaw agent's avatar, the image that represents it. It can use an image or URL supplied by the user, or search Freepik for vector avatar options.
Songhonglei/better-agent-skills
Skill Claude CodeCodex
Team-wide P2P mesh for OpenClaw agents running on different containers/pods. Each agent's gateway listens on its own pod IP:18789 over WebSocket; the mesh CLI lets you ping, send-and-await-reply, broadcast, and discover the whole team. No broker, no Supabase, no central server — just direct WS calls between teammates'…
Songhonglei/better-agent-skills
Skill Claude CodeCodex
Manage OpenClaw Agent's built-in memory features — enable/disable/configure Dreaming (Light→REM→Deep auto memory consolidation) and Active Memory (proactive memory injection with three style presets: conservative / balanced / aggressive). Auto-detects K8s ConfigMap mirrors, creates .bak. backups before write, supports…
Songhonglei/better-agent-skills
Skill Codex
Extract a standardized cross-tool user profile from any AI agent's long-term memory (USER.md, MEMORY.md, AGENTS.md, CLAUDE.md, .cursorrules, etc.) so you can re-use it in another AI tool without retraining. Output is a portable Markdown document with five categories — instructions, identity, profession, projects…
Songhonglei/better-agent-skills
Skill Claude CodeCodex
Zero-dependency Bash environment health check for Linux, macOS, containers, and K8s pods. Reports OS, current user, Node.js, Python3, basic tools (git/curl/jq/make/docker) with paths and versions, network (hostname, IP, inferred subnet), container/K8s detection with a configurable env-var probe, workdir and git…
Songhonglei/better-agent-skills
Skill Claude CodeCodex
A manager for startup scripts in OpenClaw, an AI-agent runtime that can run inside containers or pods. It stores hooks in the workspace so they can run again after gateway, container, or pod restarts.
Songhonglei/better-agent-skills
Skill Codex
A repair guide and scripts for Codex Desktop projects that exist but show no chats, even though some conversations may still appear in Recent. It focuses on restoring links between projects and conversations without overwriting the only copy of a chat.
Songhonglei/better-agent-skills
Skill Claude CodeCodex
A small tool for changing the label of an OpenClaw-style session, a saved conversation or agent run.
Songhonglei/better-agent-skills
Skill Claude CodeCodex
Recover lost agent session content and file changes from on-disk conversation logs. Streaming and OOM-safe on 700MB+ daily JSONL. Two commands: search.py for keyword search across recent sessions (with hit snippets, file-op listing, JSON for agent consumption); extract.py for pulling full write/edit content from a…
Songhonglei/better-agent-skills
Skill Claude CodeCodex
One-click subagent timeout configurator for OpenClaw. Configures the three related fields (agents.defaults.timeoutSeconds + subagents.runTimeoutSeconds + acp.runtime.ttlMinutes) atomically with built-in TTL constraint validation (ttlMinutes 60 ≥ runTimeoutSeconds). Three preset profiles — quick (60s/1h/1h, fast…
Songhonglei/better-agent-skills
Skill Claude CodeCodex
A guided review process for reducing the amount of text an AI coding workspace loads into every session. It audits memory, configuration, and other project-context files, then recommends targeted cleanup.
Songhonglei/better-agent-skills
Skill Claude CodeCodex
One-command Git tracking setup for any working directory, with a security-focused .gitignore (credentials, TLS/SSH private keys, tokens, runtime caches & PIDs, nodemodules, Python caches, build artifacts, editor temp files), a large-file guard (>10MB), and a read-only --audit mode that detects tracked secrets…
Songhonglei/better-agent-skills
Skill Codex
Diagnose and safely repair one local Codex Desktop task selected by its UI title or thread ID when recent turns are missing, truncated, merged into an interrupted turn, or hidden by damaged rollout ordering. Do not use for broad project/provider restoration or ordinary task continuation.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: