
Claw Advisor
Route OpenClaw or Claw-style support questions to the right documentation slug prefixes before the agent guesses from generic chat knowledge.
Install
npx skills add https://github.com/gupsammy/claudest --skill claw-advisorWhat is this skill?
- Domain map routes user problems to doc slug prefixes (channels, gateway, install, automation, CLI, concepts, tools, plat
- Entry-point slugs per domain (e.g. channels/troubleshooting, gateway/sandboxing, automation/cron-jobs)
- Designed for broad questions that need multi-area doc research
- Reduces wrong-doc deep dives when configuring Telegram, Discord, sandboxes, or model providers
Adoption & trust: 1 installs on skills.sh; 253 GitHub stars; 1/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
Recommended Skills
Journey fit
Agent-tooling is the canonical shelf because the skill's core job is navigating a large agent product doc tree during build and integration work. Claw-advisor is invoked whenever domain identification is unclear—channels, gateway, automation, CLI—so tooling setup stays the primary browse anchor.
Common Questions / FAQ
Is Claw Advisor safe to install?
skills.sh reports 1 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.
SKILL.md
READMESKILL.md - Claw Advisor
# Topic Routing Map user problem domains to the most relevant doc slug prefixes. Load when the question domain needs identification or when broad questions require multi-area research. ## Domain Map | Domain | Slug Prefix | Entry Points | |--------|-------------|--------------| | Channels (Telegram, Discord, Slack, WhatsApp, etc.) | `channels/` | `channels/index`, `channels/<name>`, `channels/troubleshooting`, `channels/pairing` | | Gateway & networking | `gateway/` | `gateway/configuration`, `gateway/security`, `gateway/sandboxing`, `gateway/troubleshooting`, `gateway/remote` | | Installation & setup | `install/`, `start/` | `start/getting-started`, `install/index`, `start/wizard`, `start/onboarding` | | Automation (cron, hooks, webhooks) | `automation/` | `automation/cron-jobs`, `automation/webhook`, `automation/hooks`, `automation/troubleshooting` | | CLI commands | `cli/` | `cli/index`, `cli/<command>` | | Concepts & architecture | `concepts/` | `concepts/architecture`, `concepts/agent`, `concepts/models`, `concepts/sessions`, `concepts/memory` | | Tools & skills | `tools/` | `tools/skills`, `tools/subagents`, `tools/index`, `tools/exec`, `tools/browser` | | Platforms | `platforms/` | `platforms/macos`, `platforms/linux`, `platforms/windows`, `platforms/ios`, `platforms/android` | | Model providers | `providers/` | `providers/index`, `providers/anthropic`, `providers/openai`, `providers/openrouter` | | Security | `security/`, `gateway/security` | `gateway/sandboxing`, `gateway/security`, `security/formal-verification` | | Troubleshooting | `help/` | `help/troubleshooting`, `help/faq`, `help/debugging`, `help/environment` | | Nodes (audio, camera, voice) | `nodes/` | `nodes/index`, `nodes/audio`, `nodes/talk`, `nodes/voicewake` | | Web UI | `web/` | `web/dashboard`, `web/webchat`, `web/tui` | | Agent system | `concepts/agent*`, `cli/agent*` | `concepts/agent`, `concepts/agent-loop`, `concepts/agent-workspace`, `cli/agent`, `cli/agents` | | Templates & reference | `reference/` | `reference/templates/*`, `reference/token-use`, `reference/rpc` | ## Cross-Cutting Patterns Some questions span multiple domains. Common combinations: - **Remote access**: `gateway/remote` + `gateway/tailscale` + `gateway/security` - **Channel + automation**: `channels/<name>` + `automation/webhook` or `automation/cron-jobs` - **Multi-agent**: `concepts/multi-agent` + `tools/subagents` + `gateway/sandboxing` - **Model selection**: `concepts/models` + `providers/<name>` + `concepts/model-failover` - **Getting started**: `start/getting-started` + `start/wizard` + `install/index` - **macOS app**: `platforms/macos` + `platforms/mac/*` (10+ sub-pages) ## Discovery When the topic doesn't map cleanly to a domain: ```bash clawdocs search "<user's keywords>" --slugs-only ``` Then fetch the top 1-3 results. --- name: claw-advisor description: > This skill should be used when the user asks about OpenClaw configuration, troubleshooting, setup, architecture, or any OpenClaw question. Triggers on "how do I configure OpenClaw", "set up telegram in OpenClaw", "gateway configuration", "OpenClaw troubleshooting", "claw advisor", "what's the best way to set up OpenClaw", "OpenClaw docs", "help me with OpenClaw", "openclaw channel setup", "debug OpenClaw", or needs guidance on OpenClaw features, channels, gateway, automation, models, or design decisions. allowed-tools: - Read - Grep - Glob - Bash(clawdocs:*) - Bash(openclaw:*) - Task - AskUserQuestion - WebSearch argument-hint: "[OpenClaw question or topic]" --- # Claw Advisor Answer OpenClaw questions, suggest optimal configuration, diagnose issues, and guide design decisions. Two backends: `clawdocs` CLI for documentation, `openclaw` CLI for live state inspection. ## Backends ### clawdocs (documentation — always available) | Command | Use When | |---------|----------| | `clawdocs fetch "<topic>" --no-header -q` | Topic known, need full page content | | `clawdocs search "<