Skill category
Use this category when the work spans Telegram, WhatsApp, Discord, browser automation, or internal operator loops.
Profiles for keeping multi-channel assistants stable across gateway and message workflows.
Use the hub when you need a wider choice set, review methodology, or a different workflow path. Return to the skills overview
Use this profile when the main outcome is getting OpenClaw running with sane defaults, channel bindings, and a clear operator handoff.
curl -fsSL https://openclaw.ai/install.sh | bash2 source signals • Last reviewed 2026-03-11
Do not expose management or gateway surfaces directly to the public internet.
Use this profile when OpenClaw has to coordinate across messaging channels, browser actions, and everyday operator interventions.
npm install -g openclaw@latest2 source signals • Last reviewed 2026-03-11
Keep channel-specific failure handling visible to humans.
Use this profile when OpenClaw is already installed and the next job is connecting model auth, Telegram, WhatsApp, Slack, Discord, or other channel credentials cleanly.
openclaw onboard1 source signals • Last reviewed 2026-03-11
Do not reuse one credential across every channel when scoped tokens are available.
Use this profile when OpenClaw is already running and the next job is editing `openclaw.json`, adjusting gateway behavior, or installing a skill into the workspace.
openclaw skills install <skill-name>1 source signals • Last reviewed 2026-03-11
Review any third-party skill before running `openclaw skills install` against a trusted workspace.
Use this profile when you are comparing Claude Code skill collections and need a clear mental model for what a package is, how SKILL.md-based bundles work, and how to evaluate them before installation.
3 source signals • Last reviewed 2026-04-01
Do not blindly install unreviewed skills from SkillsMP or any other public directory.
Use this profile when Claude Code keeps missing project conventions, architecture context, or operating rules and you need to structure CLAUDE.md files deliberately instead of relying on repeated prompts.
3 source signals • Last reviewed 2026-04-01
Do not put API keys, passwords, or other secrets in any CLAUDE.md file.
Use this profile when one Claude Code session is becoming a bottleneck and the work can be split into parallel, scoped subtasks with cleaner context boundaries.
3 source signals • Last reviewed 2026-04-01
Each subagent has its own tool permissions, so define scope and allowed actions explicitly before delegation.
Use this profile when Claude Code needs live access to databases, APIs, file systems, or operator tools through MCP and you want the connection model to stay legible.
3 source signals • Last reviewed 2026-04-01
MCP servers can have full system access, so confirm the source and permissions model before connecting one to Claude Code.
Use this profile when Claude Code is part of a real Git workflow and you need the collaboration pattern around branching, reviewing, and landing work to stay disciplined.
3 source signals • Last reviewed 2026-04-01
Avoid letting Claude Code automatically push to main or perform force pushes without an explicit human checkpoint.
Use this profile when the repo is TypeScript-first and you want the agent to respect tsconfig boundaries, type inference, strictness, and the build scripts that already define correctness.
3 source signals • Last reviewed 2026-04-01
Do not weaken strict compiler settings just to make an AI-generated patch pass quickly.
Use this profile when the repository is built on Next.js App Router and you want Claude Code to follow the framework's routing, data-fetching, and server-client boundaries correctly.
3 source signals • Last reviewed 2026-04-01
Do not blur server-only and client-only code paths when moving logic across App Router boundaries.
Use this profile when the quality bottleneck is not installation but instruction design: project rules, system framing, few-shot examples, and stable prompt patterns that Claude Code can reuse.
3 source signals • Last reviewed 2026-04-01
Do not encode secrets, private credentials, or sensitive customer data into reusable system prompts or CLAUDE.md files.
Use this profile when you need a general Claude Code operating pattern rather than one narrow sub-workflow. It is useful for teams wiring Claude Code into daily development and repo maintenance.
1 source signals • Last reviewed 2026-04-02
Treat Claude Code hooks and connected tools as execution surfaces that can affect the local machine, not just the chat transcript.
Use this profile when you need Claude Code to trigger structured actions around development events such as setup, validation, or workflow handoff. It is most useful when hook behavior needs to stay predictable and reviewable.
1 source signals • Last reviewed 2026-04-02
Hooks often end up running shell commands, so review every command path and environment assumption before enabling them broadly.
Use this profile when Claude Code already runs in a repo but the project-level config is weak, inconsistent, or drifting. It is helpful for teams refining hooks, instructions, and repo defaults after the first install.
1 source signals • Last reviewed 2026-04-02
Project config can indirectly authorize file edits, command execution, and hook behavior, so treat it as an operational control plane.
Use this profile when you need Claude Code to operate with a more opinionated execution stack for QA, review, or shipping workflows. It is a good fit for teams that want repeatable command flows instead of improvising every task from scratch.
1 source signals • Last reviewed 2026-04-02
A stacked workflow can hide a lot of shell and browser automation, so review what commands and tools it is actually allowed to run.
Use this profile when the main question is which MCP servers to add and how they fit into a Claude Code workflow. It helps when a team is moving from simple chat usage toward tool-connected automation.
1 source signals • Last reviewed 2026-04-02
Every MCP server is part of the trust boundary, so confirm what data, commands, and auth surfaces it exposes before enabling it.
Use this profile when you are building an app experience that depends on MCP rather than only adding one server. It fits teams shaping product flows where Claude Code or another agent coordinates multiple MCP-backed capabilities.
1 source signals • Last reviewed 2026-04-02
When an app combines multiple MCP tools, keep capability boundaries explicit so one prompt path does not gain accidental access to everything.
Use this profile when Claude Code or another agent needs to participate in a Power Automate oriented toolchain through MCP. It is useful for teams bridging agent workflows with enterprise automation systems.
1 source signals • Last reviewed 2026-04-02
Power Automate style integrations often touch business systems, so audit the downstream actions an MCP trigger can invoke.
Use this profile when the work is about authoring an MCP integration from scratch or shaping a new server around existing systems. It is useful for developers who need Claude-compatible tooling that does not exist yet.
1 source signals • Last reviewed 2026-04-02
Keep the server interface as small as possible so the agent only gets the actions and data it truly needs.
Use this profile when the main need is to inspect, run, or manage MCP behavior from a terminal-oriented workflow. It is useful for developers who prefer a direct CLI layer over app-specific setup surfaces.
1 source signals • Last reviewed 2026-04-02
A terminal workflow makes it easy to run broad or repetitive actions quickly, so verify target servers and credentials before executing commands.
Use this profile when an agent workflow needs payment-related capabilities through MCP rather than only local dev tools. It is useful for builders connecting commerce or transaction flows to Claude-compatible tooling.
1 source signals • Last reviewed 2026-04-02
Treat any payments-related MCP surface as high risk because even small mistakes can trigger real financial side effects.
Use this profile when an MCP integration needs to represent checkout steps inside a commerce workflow. It is useful for builders exposing purchase actions to agents in a more structured way.
1 source signals • Last reviewed 2026-04-02
Checkout-related MCP tools should be treated as transactional surfaces, not general-purpose convenience actions.
Use this profile when an agent needs to participate in checkout flows through a dedicated commerce MCP toolset. It helps when you want checkout steps to be agent-addressable without opening up the entire commerce system.
1 source signals • Last reviewed 2026-04-02
Treat checkout actions as high-sensitivity operations and require clear environment boundaries between test and production.
Use this profile when an agent needs MCP-mediated access in browser-heavy or web automation contexts. It fits teams connecting interactive web workflows to model-accessible tools.
1 source signals • Last reviewed 2026-04-02
Browser-facing bridges can cross several trust boundaries at once, so review what page data and what tool actions become reachable together.
Use this profile when MCP needs to support Canvas app configuration or similar low-code admin flows. It is helpful for teams bringing app-configuration work into an agent-friendly tool surface.
1 source signals • Last reviewed 2026-04-02
Administrative app configuration surfaces can alter shared environments quickly, so scope tools to the minimal set of safe operations.
Use this profile when Claude-oriented workflows need shared memory or persistent context beyond the current session. It is useful for teams experimenting with memory-backed agent tooling and prompt persistence.
1 source signals • Last reviewed 2026-04-02
Persistent memory layers can quietly accumulate sensitive data, so define what is allowed into memory before connecting the service broadly.
Use this profile when an OpenClaw or Claude-style workflow benefits from clearly separating context gathering from mutation steps. It is useful for operators who want safer execution in workspaces where reading and writing should not blur together.
1 source signals • Last reviewed 2026-04-02
Keep the read phase broad enough to build context, but narrow the write phase to the exact files or actions that were actually approved.
Need broader discovery? Skills overview
Need OpenClaw context? OpenClaw workflow