← 返回 Skills 市场
bengii

Bengii Gemini Fix

作者 bengii · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
230
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install bengii-gemini-fix
功能描述
Comprehensive guide for installing, configuring, operating, and troubleshooting OpenClaw — a self-hosted, multi-channel AI agent gateway. Use when the user a...
使用说明 (SKILL.md)

OpenClaw Maintenance Skill

OpenClaw is a self-hosted, open-source (MIT) gateway that routes AI agents across WhatsApp, Telegram, Discord, Slack, iMessage, Signal, and 15+ other channels simultaneously. It runs on macOS, Linux, or Windows.

Reference Files

Reference Coverage
channels.md Per-channel setup (WhatsApp, Telegram, Discord, etc.)
channel_troubleshooting.md Per-channel failure signatures and walkthroughs
tools.md Tools inventory (profiles, groups, all built-in tools)
exec.md Exec tool: parameters, config, PATH, security, process tool
exec_approvals.md Exec approvals: allowlists, safe bins, approval flow
browser.md Browser tool: profiles, CDP, relay, SSRF, Control API
web_tools.md Web tools: Brave, Perplexity, Gemini search providers
pdf_tool.md PDF tool: native/fallback modes, config, page filtering
elevated.md Elevated mode: /elevated directives, sandbox breakout
lobster.md Lobster: typed workflow runtime with approvals
llm_task.md LLM Task: JSON-only LLM step for structured output
openprose.md OpenProse: multi-agent program runtime
plugins.md Plugins: official list, config, manifest, CLI, authoring
skills.md Skills: locations, config, ClawHub, watcher, token impact
providers.md Model provider setup
multi_agent.md Multi-agent routing
nodes.md Nodes (iOS/Android/macOS/headless)
security.md Security hardening
secrets.md Secrets management (SecretRef, vault)
sandboxing.md Sandboxing (Docker isolation)
config_reference.md Full config field reference
gateway_ops.md Gateway operations
remote_access.md Remote access, SSH, Tailscale, web dashboard
sessions.md Session management, DM isolation, lifecycle, compaction
hooks.md Hooks: internal event hooks, HTTP webhooks, authoring, CLI
automation.md Cron jobs, webhooks, Gmail Pub/Sub
acp_agents.md ACP agents: spawn external AI runtimes (Codex, Claude, etc.)
install.md Installation, updating, rollback, migration, uninstall
web_ui.md Web surfaces: Dashboard, Control UI, WebChat
slash_commands.md Chat slash commands (/new, /model, /acp, etc.)
platforms.md Platform-specific guides (macOS, iOS, Android, Linux, Windows)
diffs_firecrawl.md Diffs plugin + Firecrawl anti-bot fallback
subagents.md Sub-agents: nested spawning, thread binding, announce, tool policy
memory.md Memory system, vector search, hybrid BM25, compaction, QMD backend
architecture.md Gateway architecture, wire protocol, pairing, invariants
agent_runtime.md Agent runtime, bootstrap files, agent loop, hooks, timeouts
streaming.md Streaming + chunking: block streaming, coalescing, preview modes
queue.md Command queue: modes (steer/followup/collect), concurrency, per-session
model_failover.md Model failover, OAuth, auth profiles, cooldowns, billing disables
clawhub.md ClawHub: public skill registry, CLI commands, publish/install
thinking.md Thinking levels, verbose directives, reasoning visibility
polls.md Polls: Telegram, WhatsApp, Discord, MS Teams
voice.md Talk Mode (voice interaction) + Voice Wake (wake words)
presence_discovery.md Presence system, discovery (Bonjour/Tailscale), transports
gateway_internals.md Network model, gateway lock, health checks, doctor, logging, background exec
heartbeat.md Heartbeat: config, delivery, visibility, HEARTBEAT.md, per-agent
bonjour.md Bonjour/mDNS: TXT keys, wide-area DNS-SD, debugging, failure modes
pairing.md Gateway pairing: node approval, CLI, API, auto-approval, storage
tui.md TUI: keyboard shortcuts, slash commands, pickers, local shell, delivery
media.md Media: camera capture, images, audio/voice notes, transcription
channel_routing.md Channel routing, session keys, agent selection, Mattermost, BlueBubbles

Quick Reference

Key Paths

Path Purpose
~/.openclaw/openclaw.json Main config (JSON5)
~/.openclaw/.env Global env fallback
~/.openclaw/workspace Default agent workspace
~/.openclaw/agents/\x3Cid>/ Per-agent state + sessions
~/.openclaw/skills/ Managed/local skills
~/.openclaw/agents/\x3Cid>/qmd/ QMD memory backend state
~/.openclaw/agents/\x3Cid>/agent/auth-profiles.json Auth profiles + OAuth tokens
OPENCLAW_CONFIG_PATH Override config location
OPENCLAW_STATE_DIR Override state directory
OPENCLAW_HOME Override home directory

Essential Commands

openclaw status                    # Overall status
openclaw gateway status            # Gateway daemon status
openclaw gateway status --deep     # Deep scan including system services
openclaw doctor                    # Diagnose config/service issues
openclaw doctor --fix              # Auto-fix safe issues
openclaw logs --follow             # Tail gateway logs
openclaw channels status --probe   # Channel health check
openclaw security audit            # Security posture check
openclaw security audit --fix      # Auto-fix security issues
openclaw update                    # Self-update
openclaw dashboard                 # Open Control UI in browser
openclaw tui                       # Terminal UI (interactive REPL)
openclaw agent                     # Direct agent interaction via CLI
openclaw health                    # Health check
openclaw usage                     # Usage tracking
openclaw config validate           # Validate config file
openclaw config file               # Print active config path
openclaw sessions cleanup          # Session disk cleanup
openclaw agents bindings           # Agent-channel bindings
openclaw agents bind               # Bind agent to account
openclaw agents unbind             # Unbind agent
openclaw update --dry-run          # Preview update
openclaw system presence           # View connected clients/nodes
openclaw system heartbeat last     # Last heartbeat info
openclaw system heartbeat now      # Trigger heartbeat immediately
openclaw memory search \x3Cquery>     # CLI memory search
openclaw docs \x3Cquery>              # Search OpenClaw docs
openclaw nodes pending             # List pending pairing requests
openclaw nodes approve \x3Cid>        # Approve node pairing
openclaw nodes status              # Show all paired nodes
openclaw health --json             # Full health snapshot (JSON)
openclaw message send --media \x3Cp>  # Send media message

Default Gateway

  • Bind: 127.0.0.1:18789 (loopback)
  • Dashboard: http://127.0.0.1:18789/
  • Protocol: WebSocket (JSON text frames)

Core Workflow

Diagnosing Issues

Always follow this command ladder:

  1. openclaw status — quick overview
  2. openclaw gateway status — daemon running? RPC probe ok?
  3. openclaw logs --follow — watch for errors
  4. openclaw doctor — config/service diagnostics
  5. openclaw channels status --probe — per-channel health

Starting / Restarting Gateway

# Foreground with verbose logging
openclaw gateway --port 18789 --verbose

# Force-kill existing listener then start
openclaw gateway --force

# Service management (launchd on macOS, systemd on Linux)
openclaw gateway install
openclaw gateway start
openclaw gateway stop
openclaw gateway restart

Configuration

Edit config via any method:

# Interactive wizard
openclaw onboard                    # Full setup
openclaw configure                  # Config wizard

# CLI one-liners
openclaw config get \x3Cpath>          # Read value
openclaw config set \x3Cpath> \x3Cvalue>  # Set value (JSON5 or raw string)
openclaw config unset \x3Cpath>        # Remove value

# Direct edit
# Edit ~/.openclaw/openclaw.json (JSON5 format)
# Gateway hot-reloads on save (if gateway.reload.mode != "off")

Minimal config example:

{
  agents: { defaults: { workspace: "~/.openclaw/workspace" } },
  channels: { whatsapp: { allowFrom: ["+15555550123"] } },
}

Channel Setup

For detailed per-channel setup, see references/channels.md. For per-channel troubleshooting (failure signatures, setup walkthroughs), see references/channel_troubleshooting.md. For plugins adding new channels (Matrix, Nostr, MS Teams, etc.), see references/plugins.md.

Quick channel add:

# Interactive wizard
openclaw channels add

# Non-interactive
openclaw channels add --channel telegram --account default --name "My Bot" --token $BOT_TOKEN
openclaw channels login --channel whatsapp     # QR pairing for WhatsApp
openclaw channels status --probe               # Verify

Model Provider Setup

For detailed provider setup, see references/providers.md.

# Set default model
openclaw models set anthropic/claude-sonnet-4-5

# List available models
openclaw models list --all

# Check auth/token status
openclaw models status --probe

# Add auth interactively
openclaw models auth add

Config example:

{
  agents: {
    defaults: {
      model: {
        primary: "anthropic/claude-sonnet-4-5",
        fallbacks: ["openai/gpt-5.2"],
      },
    },
  },
}

Multi-Agent Routing

For detailed multi-agent config, see references/multi_agent.md.

openclaw agents add \x3Cid>                # Create agent
openclaw agents list --bindings         # Show agent-channel bindings
openclaw agents delete \x3Cid>             # Remove agent

Nodes (iOS / Android / macOS / Headless)

For detailed node setup, see references/nodes.md.

openclaw nodes status                   # List connected nodes
openclaw nodes describe --node \x3Cid>     # Node capabilities
openclaw devices list                   # Pending device approvals
openclaw devices approve \x3CrequestId>    # Approve a device
openclaw node run --host \x3Chost> --port 18789  # Start headless node host

Security

For detailed security hardening, see references/security.md. For secrets management (SecretRef, vault integration), see references/secrets.md. For sandboxing (Docker isolation for tools), see references/sandboxing.md. For full config field reference, see references/config_reference.md. For remote access (SSH, Tailscale, VPN), see references/remote_access.md.

openclaw security audit                 # Check posture
openclaw security audit --deep          # Live gateway probe
openclaw security audit --fix           # Auto-fix safe issues
openclaw secrets reload                 # Re-resolve secret refs
openclaw secrets audit                  # Scan for plaintext leaks

Update / Uninstall

For detailed installation, updating, rollback, and migration guide, see references/install.md.

# Install (recommended)
curl -fsSL https://openclaw.ai/install.sh | bash

# Update
openclaw update                    # Self-update command
# Or: npm install -g openclaw@latest
openclaw doctor                    # Run after update to apply migrations

# Uninstall
openclaw uninstall

Tools Reference

For detailed per-tool documentation, see references/tools.md.

For specific tools, see:

For ACP agents (Codex, Claude Code, Gemini CLI, etc.), see references/acp_agents.md. For Diffs plugin and Firecrawl anti-bot fallback, see references/diffs_firecrawl.md. For chat slash commands (/new, /model, /acp, etc.), see references/slash_commands.md. For thinking levels (/think, /verbose, /reasoning), see references/thinking.md. For polls (Telegram, WhatsApp, Discord, MS Teams), see references/polls.md. For Talk Mode and Voice Wake, see references/voice.md. For Gateway architecture and wire protocol, see references/architecture.md. For agent runtime and loop details, see references/agent_runtime.md. For command queue system, see references/queue.md. For model failover and OAuth, see references/model_failover.md. For ClawHub skill registry, see references/clawhub.md. For presence and discovery, see references/presence_discovery.md. For streaming and chunking, see references/streaming.md. For Gateway internals (network model, lock, health, doctor, logging), see references/gateway_internals.md. For heartbeat system, see references/heartbeat.md. For Bonjour/mDNS discovery details, see references/bonjour.md. For Gateway node pairing, see references/pairing.md. For Terminal UI (TUI), see references/tui.md. For media (camera, images, audio), see references/media.md. For channel routing and session keys, see references/channel_routing.md.

Tool profiles: minimal, coding, messaging, full (default).

Tool groups (for allow/deny):

  • group:runtime — exec, bash, process
  • group:fs — read, write, edit, apply_patch
  • group:sessions — sessions_list/history/send/spawn, session_status
  • group:memory — memory_search, memory_get
  • group:web — web_search, web_fetch
  • group:ui — browser, canvas
  • group:automation — cron, gateway
  • group:messaging — message
  • group:nodes — nodes
  • group:openclaw — all built-in OpenClaw tools (excludes provider plugins)

Common Failure Signatures

Error Cause Fix
refusing to bind gateway ... without auth Non-loopback bind without token Set gateway.auth.token or gateway.auth.password
another gateway instance is already listening / EADDRINUSE Port conflict openclaw gateway --force or change port
Gateway start blocked: set gateway.mode=local Local mode not enabled Set gateway.mode="local"
unauthorized / reconnect loop Token/password mismatch Check OPENCLAW_GATEWAY_TOKEN or config auth
device identity required Missing device auth Ensure client completes connect.challenge flow
No replies from bot Pairing/allowlist/mention gating Check openclaw pairing list, DM policy, mention patterns
Embedding provider authentication failed (401) .env has placeholder API key (e.g. your-jina-api-key-here) Replace with real API key in ~/.openclaw/.env, restart Gateway
config change requires gateway restart (plugins.*) Plugin config changes can't hot-reload Full openclaw gateway restart or launchctl kickstart -k
Bootstrap failed: 5: Input/output error LaunchAgent plist in stale/stuck state openclaw gateway install then launchctl kickstart -k gui/$(id -u)/ai.openclaw.gateway
Missing env var "X" referenced at config path: ... .env missing or variable not defined Add variable to ~/.openclaw/.env and restart Gateway

Environment Variables

Variable Purpose
OPENCLAW_GATEWAY_TOKEN Gateway auth token
OPENCLAW_GATEWAY_PASSWORD Gateway auth password
OPENCLAW_GATEWAY_PORT Override gateway port
OPENCLAW_CONFIG_PATH Override config file path
OPENCLAW_STATE_DIR Override state directory
OPENCLAW_HOME Override home directory
OPENCLAW_LOAD_SHELL_ENV Import shell env (set to 1)
OPENCLAW_VERBOSE Verbose logging
OPENCLAW_LOG_FILE File logging path
OPENCLAW_LOG_LEVEL Log level control
OPENCLAW_SHELL Set by OpenClaw in exec/acp/tui runtimes
BRAVE_API_KEY For web_search tool
FIRECRAWL_API_KEY For Firecrawl anti-bot fallback
ELEVENLABS_API_KEY For Talk Mode TTS
ELEVENLABS_VOICE_ID Default voice for Talk Mode
CLAWHUB_TOKEN ClawHub API token for CI/automation
CLAWHUB_WORKDIR ClawHub working directory override
OLLAMA_API_KEY For Ollama embeddings provider
安全使用建议
This skill is a large, documentation-heavy OpenClaw maintenance guide that can instruct an assistant to run commands and access local files (including gateway tokens). That is consistent with the advertised purpose, but: 1) the registry name ('Bengii Gemini Fix') does not match the SKILL.md content (which identifies as 'openclaw') and the source/homepage are unknown — verify the origin before trusting it; 2) the static scan found a 'system-prompt-override' pattern — inspect SKILL.md and references for any lines that attempt to inject or replace the assistant's system prompt or give the skill unchecked authority to run shell commands; 3) because the skill can instruct reading token/password files, do not allow it to access secrets or run privileged commands automatically. Recommendations: install only from a verified upstream repo (compare against official OpenClaw docs), run the skill in a sandboxed assistant or with model-invocation disabled/autonomy limited until you audit the files, require manual approval for any command execution or file reads, and avoid granting access to gateway tokens/SSH keys until you confirm the provenance and content.
功能分析
Type: OpenClaw Skill Name: bengii-gemini-fix Version: 1.0.0 This skill bundle is a comprehensive documentation and operational guide for managing an OpenClaw AI gateway. It provides the AI agent with the necessary context to install, configure, and troubleshoot the system using the `openclaw` CLI. Although the skill grants the agent access to powerful system commands and configuration files, these capabilities are essential for its stated purpose as a maintenance tool. There are no indicators of malicious intent, such as hidden exfiltration commands or prompt injection attacks designed to compromise the host.
能力评估
Purpose & Capability
The SKILL.md, README, and references clearly document OpenClaw maintenance tasks (install, config, channels, tokens, troubleshooting). However the registry metadata (skill name: "Bengii Gemini Fix") does not match the skill manifest (SKILL.md uses name: "openclaw" and all files refer to OpenClaw). Source/homepage are unknown. The mismatch between published name/metadata and the content is an incoherence that reduces trust and could indicate repackaging or renaming without provenance.
Instruction Scope
As an instruction-only skill it contains many concrete operational steps (CLI commands, file paths like ~/.openclaw/gateway.token, config edits, token/password usage). Those are appropriate for a maintenance guide, but the doc also describes the agent/system prompt assembly and bootstrap files; the static scan flagged a 'system-prompt-override' pattern. That pattern can be legitimate documentation of how OpenClaw builds prompts, but it also matches prompt-injection signatures — so treat any embedded directives that look like 'insert this system prompt' as potentially dangerous unless you reviewed them.
Install Mechanism
No install spec or code files that would download or execute remote artifacts — lowest-risk install model (instruction-only). The skill would not write binaries or run installers by itself; risk comes from following its instructions after install.
Credentials
The skill declares no required env vars or credentials, which is proportionate. However the instructions routinely direct the operator to use gateway tokens, password files, or secret refs (e.g., ~/.openclaw/gateway.token, gateway.auth.*). Those are relevant for OpenClaw maintenance, but they are sensitive. Because the skill can instruct an assistant to read or use such secrets, verify any automatic actions before allowing the assistant to access token/password files.
Persistence & Privilege
always:false and normal autonomous invocation settings are used. The skill does not request permanent platform-level privileges or attempt to modify other skills. The combination of autonomous invocation and the detected prompt-injection pattern is something to monitor (see guidance), but autonomous invocation alone is the platform default.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install bengii-gemini-fix
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /bengii-gemini-fix 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
OpenClaw maintenance skill initial release. - Provides a comprehensive guide for installing, configuring, operating, and troubleshooting self-hosted OpenClaw gateways. - Covers multi-channel setup (WhatsApp, Telegram, Discord, Slack, iMessage, etc.), agent routing, security, and maintenance. - Includes quick reference for essential file paths and CLI commands. - Features detailed reference mapping for platform-specific guides, plugins, tools, and troubleshooting scenarios. - Supports resolving common errors and administering gateways on macOS, Linux, and Windows.
元数据
Slug bengii-gemini-fix
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Bengii Gemini Fix 是什么?

Comprehensive guide for installing, configuring, operating, and troubleshooting OpenClaw — a self-hosted, multi-channel AI agent gateway. Use when the user a... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 230 次。

如何安装 Bengii Gemini Fix?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install bengii-gemini-fix」即可一键安装,无需额外配置。

Bengii Gemini Fix 是免费的吗?

是的,Bengii Gemini Fix 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Bengii Gemini Fix 支持哪些平台?

Bengii Gemini Fix 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Bengii Gemini Fix?

由 bengii(@bengii)开发并维护,当前版本 v1.0.0。

💬 留言讨论