← Back to Skills Marketplace
566
Downloads
1
Stars
0
Active Installs
14
Versions
Install in OpenClaw
/install wayve
Description
The operating system for solopreneurs who use AI agents. Wayve helps you discover what to automate next, gives your agent permanent memory, and protects the...
Usage Guidance
This skill is internally coherent: it expects the Wayve CLI and an API key and will save user planning data to the Wayve backend. Before installing or using it: 1) Confirm you trust the npm package publisher (consider pinning a specific version rather than @latest and review the CLI's source code if available). 2) Understand that giving WAYVE_API_KEY and any push-channel tokens means those values will be sent to and stored by Wayve (the docs state they encrypt delivery credentials). 3) If you don't want to hand over bot/webhook tokens, use the 'pull' channel option (no external credentials). 4) Watch for automations the agent proposes — SKILL.md requires explicit consent for background jobs; only approve jobs you want scheduled. 5) If you need higher assurance, run the CLI in a sandboxed environment and audit network traffic or inspect the published package before use.
Capability Analysis
Type: OpenClaw Skill
Name: wayve
Version: 1.0.13
The 'wayve' skill bundle functions as a complex management system for solopreneurs, relying heavily on a third-party CLI tool (@gowayve/wayve-cli). It is classified as suspicious because the instructions (SKILL.md, onboarding.md, and automations.md) explicitly direct the AI agent to proactively collect and store highly sensitive information, including business revenue, financial goals, and third-party credentials such as Telegram bot tokens and Slack/Discord webhooks. While these capabilities are aligned with the stated goal of providing business coaching and notifications, the systematic collection of third-party secrets and financial data via an AI agent represents a high-risk pattern that could be easily repurposed for data exfiltration or credential harvesting.
Capability Assessment
Purpose & Capability
The skill is a CLI-driven integration with the Wayve service. It requires the 'wayve' binary and a single primary env var (WAYVE_API_KEY) which aligns with saving/retrieving user data, automations, and knowledge. Required binaries, env var, and declared install (npm package @gowayve/wayve-cli) are proportionate to the stated purpose.
Instruction Scope
SKILL.md consistently instructs the agent to run wayve CLI commands, read the provided reference files, and persist data via the CLI. It explicitly requires user confirmation before collecting third-party delivery credentials (telegram bot token, webhook URLs, etc.). The instructions do not ask the agent to read unrelated system files or unrelated environment variables, nor to exfiltrate data to unexpected endpoints; the flows focus on Wayve API/CLI usage.
Install Mechanism
Install is via an npm package (@gowayve/wayve-cli@latest) that creates the 'wayve' binary. Using a public npm package is expected for a CLI, but registry packages carry supply-chain risk (e.g., malicious or compromised packages). No downloads from arbitrary URLs or extract steps are present.
Credentials
The skill declares a single required environment variable (WAYVE_API_KEY) which is appropriate. The skill also instructs the agent to collect delivery-channel credentials (bot tokens, webhook URLs) from the user when setting up push automations — this is explained and guarded by an explicit consent step in the docs, but it does mean sensitive third-party credentials will be transmitted to and stored by Wayve if the user provides them.
Persistence & Privilege
always is false. The skill can create automations (agent routines / scheduled push notifications) via the Wayve CLI, but SKILL.md repeatedly requires explicit user confirmation before scheduling background jobs or collecting credentials. Autonomous invocation is allowed (platform default) but there is no 'always: true' or other elevated privilege requested by the skill.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install wayve - After installation, invoke the skill by name or use
/wayve - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.13
**Wayve 1.0.13 — The Solopreneur OS Update**
- Refined core identity: now positioned as an "operating system for solopreneurs who use AI agents" with a focus on automation, agent routines, and protecting all 7 life pillars.
- Updated language and values throughout: emphasizes automation discovery, agent routines, business and life balance, and strategic use of AI memory.
- Clarified pillar and automation terminology, including the role of "Mission" vs "Wealth" pillars and the meaning of agent routines.
- Instruction, tone, and flow updated for solopreneur/AI agent audiences; business and life planning aspects are unified.
- No changes to file structure or CLI command requirements.
v1.0.12
Version 1.0.12
- Migrated from Wayve MCP server/tooling to the new Wayve CLI (`wayve` command) for all workflow actions.
- Updated all tool call instructions and references to use CLI commands with `--json` for output, instead of API tool calls.
- Changed all technical language to match CLI parameters (e.g., `--pillar` instead of `bucket_id`).
- Updated setup and integration instructions to reference CLI setup documentation.
- Revised command execution rules to require immediate CLI execution and correct parsing of JSON responses.
v1.0.11
**Life planning terminology and coverage improved; new advanced references added.**
- Introduced standardized "pillar" terminology throughout the skill (replacing "bucket"), aligned to the 7 life areas.
- Added new commands and reference flows: business strategy reflection (/wayve strategy), nightly analysis framework, and solopreneur coaching.
- Updated all descriptions and internal flows to use "pillar" in conversation for greater clarity and alignment with app terminology.
- Enhanced session start: new intelligence and contextual checks for coaching and nudge opportunities.
- Expanded command table, including new reference files for coaching, analysis, and entrepreneurship.
- Interface and flow instructions now support richer proactive suggestions, report generation, and coaching interactions.
v1.0.10
Version 1.0.10
- Updated automation section to support server-side push notifications for proactive check-ins.
- Added details about using wayve_manage_automations to create, list, update, and delete automations.
- Clarified delivery channels for automations: Telegram, Discord, Slack, email, or pull model.
- Replaced references to "cron jobs" with updated automation management process.
v1.0.9
No user-facing changes in this release.
- No file changes detected between versions.
- No updates or modifications to commands, behavior, or documentation.
v1.0.8
- Updated package installation and requirements metadata for better compatibility and clarity.
- Centralized environment variable and binary requirements under a single metadata block.
- Now explicitly lists primary environment variable and install instructions in a structured format.
- No user-facing changes to core features or interaction flow.
v1.0.7
- Added npm dependency install step for @gowayve/wayve@^1.2.5 to the skill manifest.
- changes in references to remove suspicious labeled instructions.
v1.0.6
- Added a setup guide at `references/setup-guide.md` for installation and setup instructions.
- Updated SKILL.md to link to the new setup guide.
- Declared required bin (`npx`) and required environment variable (`WAYVE_API_KEY`) in the skill manifest.
v1.0.5
Version 1.0.5
- Added explicit instruction to require and actively use Wayve MCP tools for all flows (e.g., must call tools to persist data).
- Clarified that if a wayve tool call fails, the flow cannot continue—user must be notified and prompted to retry.
- Strengthened requirement to immediately call tools as instructed (not just plan to do so or defer).
- Detailed the need to persist all noted data via tool invocations—do not assume anything will be saved otherwise.
- Minor language and formatting improvements to emphasize correct tool usage and enhance clarity.
v1.0.4
- Added explicit instruction to always read the matching reference file for each command, and to follow its flow step by step without improvisation.
- Introduced a new `/wayve help` command to list all available commands.
- Updated the commands table to include the new help command and clarify command behavior.
- Reinforced best practices for referencing command-specific files and handling commands.
- No code or implementation changes detected; documentation and process clarifications only.
v1.0.3
Skill now supports slash commands for all major flows.
- Added explicit `/wayve` slash command syntax for setup, daily brief, weekly planning (Fresh Start), wrap up, time audit, and life audit.
- Clarified that natural language triggers the same flows as the matching command.
- Updated phase detection table to a more concise command keyword mapping.
- User-invokable property and metadata structure improved.
- No behavioral changes to existing rituals or automations; documentation and invocation process are now clearer.
v1.0.2
Time-audit onboarding added
v1.0.1
Wayve 1.0.1 is a refinement update with clarifications and minor adjustments to experience and documentation:
- Added explicit setup instructions link for installation and configuration.
- Improved guidance on automations: always ask for explicit permission, clearly explain automations before user confirms.
- Clarified knowledge-saving process: removed "don't announce" verbiage, now just save naturally.
- Minor tone and structure tweaks for clarity and brevity.
- Metadata reformatted; emoji placement updated.
v1.0.0
Wayve 1.0.0 – Initial Release
- Launches a personal life planning assistant focused on balancing health, relationships, growth, finance, and adventure among others. You decide
- Detects user’s planning phase (onboarding, wrap up, fresh start, daily brief, time audit, life audit, or general) and responds accordingly.
- Proactively suggests smart suggestions and routine check-ins, always with user consent.
- Delivers personalized advice grounded in actual user data and previously stored insights.
- Integrates app action links and concise markdown formatting for clear, actionable guidance.
Metadata
Frequently Asked Questions
What is Wavye?
The operating system for solopreneurs who use AI agents. Wayve helps you discover what to automate next, gives your agent permanent memory, and protects the... It is an AI Agent Skill for Claude Code / OpenClaw, with 566 downloads so far.
How do I install Wavye?
Run "/install wayve" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Wavye free?
Yes, Wavye is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Wavye support?
Wavye is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Wavye?
It is built and maintained by Skoppert (@skoppert); the current version is v1.0.13.
More Skills