원클릭으로 Manus에서 모든 스킬 실행

openclaw-docs-lookup

스타0

포크0

업데이트2026년 2월 12일 15:09

Look up OpenClaw documentation via web_fetch — config reference, agent runtime, skills, cron, providers, sessions. Use when: You need to verify a config key, understand an OpenClaw feature, or look up documentation before making changes. Always use before changing config keys you're unsure about or when encountering unknown features. Don't use when: The answer is already in your workspace files (AGENTS.md, TOOLS.md, MEMORY.md, or skill files). Don't use for Kubernetes docs (use kubectl --help or official k8s docs). Don't use for general web searches (use web_search instead). Outputs: Documentation content fetched via web_fetch. No persistent artifacts — the information is used in-context.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

rajsinghtech

rajsinghtech/openclaw-workspace

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

OpenClaw Docs Lookup

Routing

Use This Skill When

Changing config keys and need to verify they exist
Adding new providers or models and need the format
Setting up cron jobs, hooks, or automation
Debugging startup failures that might be config-related
Encountering an OpenClaw feature you haven't seen before
Someone asks about OpenClaw capabilities or configuration

Don't Use This Skill When

The answer is in AGENTS.md, TOOLS.md, or MEMORY.md → check workspace files first
You need Kubernetes/kubectl documentation → use kubectl <cmd> --help
You need general information → use web_search
You already know the config key and format → just make the change
You're debugging pod/Flux/CI issues → use the appropriate troubleshooting skill

You have access to the full OpenClaw documentation at docs.openclaw.ai. Use web_fetch to look up answers before guessing.

How to Look Things Up

1. Master Index

Fetch https://docs.openclaw.ai/llms.txt to get the full doc index with every page URL. Use this when you're not sure which page has the answer.

2. Direct Page Access

If you know the topic, go straight to the page:

Topic	URL
Config reference	`https://docs.openclaw.ai/gateway/configuration`
Agent runtime	`https://docs.openclaw.ai/concepts/agent-runtime`
Multi-agent routing	`https://docs.openclaw.ai/concepts/multi-agent`
Memory system	`https://docs.openclaw.ai/concepts/memory`
Sessions	`https://docs.openclaw.ai/concepts/sessions`
Model failover	`https://docs.openclaw.ai/concepts/model-failover`
Skills	`https://docs.openclaw.ai/tools/skills`
Sub-agents	`https://docs.openclaw.ai/tools/agents`
Exec / shell tools	`https://docs.openclaw.ai/tools/exec`
Web tools	`https://docs.openclaw.ai/tools/web`
Cron jobs	`https://docs.openclaw.ai/automation/cron`
Hooks	`https://docs.openclaw.ai/automation/hooks`
Heartbeat	`https://docs.openclaw.ai/gateway/heartbeat`
Health checks	`https://docs.openclaw.ai/gateway/health`
Sandboxing	`https://docs.openclaw.ai/gateway/sandbox`
Discord channel	`https://docs.openclaw.ai/channels/discord`
Environment vars	`https://docs.openclaw.ai/help/env`
Troubleshooting	`https://docs.openclaw.ai/help/debugging`
FAQ	`https://docs.openclaw.ai/help/faq`
Docker install	`https://docs.openclaw.ai/installation/docker`
Model providers	`https://docs.openclaw.ai/providers/overview`
Custom providers	`https://docs.openclaw.ai/providers/custom`
CLI reference	`https://docs.openclaw.ai/cli/overview`
ClawHub (skills marketplace)	`https://docs.openclaw.ai/tools/clawhub`

3. Config Schema Quick Reference

OpenClaw config (clawdbot.json) top-level keys:

gateway        — port, auth, controlUi
models         — providers, mode
agents         — defaults, list
session        — scope, idleMinutes
tools          — profile, web, exec
skills         — entries, load
channels       — discord, telegram, whatsapp, etc.
logging        — level, consoleStyle
commands       — parsing settings
messages       — prefixes, reactions

Agent-level keys (under agents.defaults or per-agent in agents.list):

model          — primary, thinking, failover
workspace      — path to workspace dir
identity       — name, emoji
heartbeat      — every, model, target, activeHours
subagents      — allowAgents, model, maxConcurrent
compaction     — memoryFlush settings
memorySearch   — enabled, sources, experimental
timeoutSeconds — max turn duration
maxConcurrent  — concurrent session limit

Common mistake: putting agent-level keys at root level. They MUST go under agents.defaults or a specific agent in agents.list.

4. ClawHub — Community Skills

Search and install community skills:

clawhub search "kubernetes"
clawhub install <skill-slug>
clawhub update --all

Notable ops skills: kubernetes, docker-essentials, git-essentials, gitflow

이 저장소의 다른 Skills

같은 저장소

code-review

rajsinghtech/openclaw-workspace

Structured PR review — security scan, correctness, consistency, style. Covers diff analysis, comment posting via gh, and priority-based finding reports. Use when: A PR needs review, someone asks for code feedback, or changes need security/correctness validation before merge. Also use for pre-commit review of your own changes. Don't use when: The issue is a runtime pod failure (use pod-troubleshooting), a Flux reconciliation error (use flux-debugging), or a CI build failure (use ci-diagnosis). Don't use for architecture-level design discussions (use architecture-design instead). Outputs: Review comment posted on the PR via `gh pr review`, or a structured findings report grouped by severity (Critical/High/Medium/Low).

2026-02-200

openspec-workflow

rajsinghtech/openclaw-workspace

Spec-driven development workflow — proposals, requirements, design docs, task breakdowns, and implementation using the OpenSpec framework. Use when: Starting a new feature or change that needs planning, someone says "I want to build X", creating proposals or specs, breaking down requirements into tasks, or transitioning from planning to implementation. Don't use when: Debugging or troubleshooting (use appropriate troubleshooting skill). Don't use for Kubernetes manifest changes (use pr-workflow). Don't use for reviewing existing code (use code-review). Outputs: OpenSpec change folder with proposal.md, specs/, design.md, and tasks.md. Implementation follows directly from tasks.md.

2026-02-200

session-review

rajsinghtech/openclaw-workspace

Analyze agent sessions for tool failures, retry patterns, knowledge gaps, context limits, and config drift. Use when: Running periodic session reviews (cron), investigating agent reliability issues, looking for recurring failure patterns, or identifying workspace improvements from real usage. This is the primary skill for Robert's review cron job. Don't use when: You're making changes to fix issues (use workspace-improvement for that). Don't use for live debugging of a current issue (use the appropriate troubleshooting skill). Don't use for code review of PRs (use code-review). Outputs: Session analysis report with categorized findings (tool failures, retries, knowledge gaps, config drift), severity ratings, and proposed fixes. Written to /tmp/outputs/session-review.md for handoff.

2026-02-200

cluster-context

rajsinghtech/openclaw-workspace

OpenClaw pod architecture, volumes, networking, secrets, and provider configuration reference. Use when: Debugging container, mount, networking, or credential issues. Also use when you need to understand pod structure, check which providers are configured, verify volume mounts, or inspect secrets configuration. Don't use when: Debugging pod crashes (use pod-troubleshooting). Don't use for Flux issues (use flux-debugging). Don't use for deploying changes (use gitops-deploy). This is a reference skill, not a diagnostic workflow. Outputs: Architecture reference information. No artifacts — this skill provides context for other skills to use.

2026-02-200

gitops-deploy

rajsinghtech/openclaw-workspace

End-to-end deployment workflow — commit, CI, Flux reconcile, pod restart, verify. Includes ConfigMap changes, Flux postBuild escaping, and SOPS secret management. Use when: You need to deploy changes to the OpenClaw pod — config updates, workspace changes, image rebuilds, or secret rotations. Also use when someone asks "how do I deploy this?" or "push this change live." Don't use when: You're debugging why a deployment failed (use flux-debugging or pod-troubleshooting). Don't use for changes to kubernetes-manifests repo (Dyson's pr-workflow handles that). Don't use for registry/image inspection (use zot-registry). Outputs: Deployed changes verified in the running pod. Confirmation includes CI status, Flux reconciliation state, pod status, and startup logs.

2026-02-200

openclaw-docs-lookup-morty

rajsinghtech/openclaw-workspace

Look up OpenClaw documentation via web_fetch for config validation and verification. Use when: You need to verify a config key, understand OpenClaw configuration options, or check documentation for Kubernetes-specific settings before making changes. Don't use when: The answer is already in CONFIG.md, AGENTS.md, TOOLS.md in your workspace.

2026-02-200

name	OpenClaw Docs Lookup
description	Look up OpenClaw documentation via web_fetch — config reference, agent runtime, skills, cron, providers, sessions. Use when: You need to verify a config key, understand an OpenClaw feature, or look up documentation before making changes. Always use before changing config keys you're unsure about or when encountering unknown features. Don't use when: The answer is already in your workspace files (AGENTS.md, TOOLS.md, MEMORY.md, or skill files). Don't use for Kubernetes docs (use kubectl --help or official k8s docs). Don't use for general web searches (use web_search instead). Outputs: Documentation content fetched via web_fetch. No persistent artifacts — the information is used in-context.
requires	[]

OpenClaw Docs Lookup

Routing

Use This Skill When

Changing config keys and need to verify they exist
Adding new providers or models and need the format
Setting up cron jobs, hooks, or automation
Debugging startup failures that might be config-related
Encountering an OpenClaw feature you haven't seen before
Someone asks about OpenClaw capabilities or configuration

Don't Use This Skill When

The answer is in AGENTS.md, TOOLS.md, or MEMORY.md → check workspace files first
You need Kubernetes/kubectl documentation → use kubectl <cmd> --help
You need general information → use web_search
You already know the config key and format → just make the change
You're debugging pod/Flux/CI issues → use the appropriate troubleshooting skill

You have access to the full OpenClaw documentation at docs.openclaw.ai. Use web_fetch to look up answers before guessing.

How to Look Things Up

1. Master Index

Fetch https://docs.openclaw.ai/llms.txt to get the full doc index with every page URL. Use this when you're not sure which page has the answer.

2. Direct Page Access

If you know the topic, go straight to the page:

Topic	URL
Config reference	`https://docs.openclaw.ai/gateway/configuration`
Agent runtime	`https://docs.openclaw.ai/concepts/agent-runtime`
Multi-agent routing	`https://docs.openclaw.ai/concepts/multi-agent`
Memory system	`https://docs.openclaw.ai/concepts/memory`
Sessions	`https://docs.openclaw.ai/concepts/sessions`
Model failover	`https://docs.openclaw.ai/concepts/model-failover`
Skills	`https://docs.openclaw.ai/tools/skills`
Sub-agents	`https://docs.openclaw.ai/tools/agents`
Exec / shell tools	`https://docs.openclaw.ai/tools/exec`
Web tools	`https://docs.openclaw.ai/tools/web`
Cron jobs	`https://docs.openclaw.ai/automation/cron`
Hooks	`https://docs.openclaw.ai/automation/hooks`
Heartbeat	`https://docs.openclaw.ai/gateway/heartbeat`
Health checks	`https://docs.openclaw.ai/gateway/health`
Sandboxing	`https://docs.openclaw.ai/gateway/sandbox`
Discord channel	`https://docs.openclaw.ai/channels/discord`
Environment vars	`https://docs.openclaw.ai/help/env`
Troubleshooting	`https://docs.openclaw.ai/help/debugging`
FAQ	`https://docs.openclaw.ai/help/faq`
Docker install	`https://docs.openclaw.ai/installation/docker`
Model providers	`https://docs.openclaw.ai/providers/overview`
Custom providers	`https://docs.openclaw.ai/providers/custom`
CLI reference	`https://docs.openclaw.ai/cli/overview`
ClawHub (skills marketplace)	`https://docs.openclaw.ai/tools/clawhub`

3. Config Schema Quick Reference

OpenClaw config (clawdbot.json) top-level keys:

gateway        — port, auth, controlUi
models         — providers, mode
agents         — defaults, list
session        — scope, idleMinutes
tools          — profile, web, exec
skills         — entries, load
channels       — discord, telegram, whatsapp, etc.
logging        — level, consoleStyle
commands       — parsing settings
messages       — prefixes, reactions

Agent-level keys (under agents.defaults or per-agent in agents.list):

model          — primary, thinking, failover
workspace      — path to workspace dir
identity       — name, emoji
heartbeat      — every, model, target, activeHours
subagents      — allowAgents, model, maxConcurrent
compaction     — memoryFlush settings
memorySearch   — enabled, sources, experimental
timeoutSeconds — max turn duration
maxConcurrent  — concurrent session limit

Common mistake: putting agent-level keys at root level. They MUST go under agents.defaults or a specific agent in agents.list.

4. ClawHub — Community Skills

Search and install community skills:

clawhub search "kubernetes"
clawhub install <skill-slug>
clawhub update --all

Notable ops skills: kubernetes, docker-essentials, git-essentials, gitflow