
paseo-help
Answer questions about the Paseo product and app, including setup, configuration, connectivity, providers, workspaces, updates, logs, and troubleshooting. Use when a user inside Paseo asks how Paseo works, how to configure it, or why something is broken; use the paseo skill instead to operate agents and workspaces through MCP or the CLI.
- Installs
- 1.5K
- Last 24h
- +21
- Trending rank
- #5727
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/getpaseo/paseo --skill paseo-help- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads paseo-help automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Paseo Help
You are helping a user understand, configure, or troubleshoot Paseo itself. Answer their question directly, verify the answer against the current public documentation, and include the relevant documentation link. Do not send the user away to read the docs in place of helping them.
User's question: $ARGUMENTS
Use current documentation
Fetch https://paseo.sh/llms.txt first. It is the current index of Paseo documentation, with a description and Markdown URL for each page.
Use that index to select the page that owns the user's question, then fetch the linked .md page before answering. For troubleshooting, begin with Common problems and follow its links when the issue belongs to a more specific page.
Prefer the deployed docs over memory. Answer the user directly, then link the relevant .md page as supporting documentation.
Establish the topology first
Identify the daemon involved before diagnosing versions, paths, providers, logs, updates, or connectivity. Do not infer the daemon from the client: Paseo Desktop can manage its bundled local daemon and connect to other remote daemons at the same time.
Establish two facts:
- Where and how the daemon runs
- Desktop-managed: Paseo Desktop bundles, starts, and updates a daemon on that computer. No separate daemon install is required.
- Standalone: the daemon was installed separately, commonly through the npm CLI, and runs independently of the desktop app.
- Docker: the daemon, its home, provider CLIs, credentials, and code mounts live in the container runtime.
- How the affected client reaches it
- same-machine local connection
- relay connection
- direct LAN, VPN, or Tailscale connection
- daemon-served web UI
Use Settings → About to compare the app version with each connected host. For the affected host, open Settings → your host → Overview → Full status. On the daemon machine, paseo daemon status --json reports facts such as server ID, hostname, version, home, listen address, process owner, log path, and whether the daemon is desktop-managed.
Record which host the user is viewing and which machine or container runs it. A local paseo daemon status describes the daemon for that CLI's local PASEO_HOME; it may not be the remote host visible in the app.
Apply later checks to the daemon runtime, not automatically to the client device:
- Provider binaries, credentials,
PATH, workspaces, config, and daemon logs live on the daemon machine or inside its container. - App version and app logs live on the client device.
- A desktop-managed daemon follows the Desktop app lifecycle and update path.
- A standalone daemon follows its own CLI/npm lifecycle and may use a different
PASEO_HOMEor listen address. - A Docker daemon uses container paths, volumes, user permissions, image versions, and container lifecycle commands.
Diagnose before changing state
After identifying the affected host, compare that daemon's version with the client app version. Ask the user to update both through the correct topology-specific update path. Old versions and app/daemon version skew cause many apparent bugs, and fixes ship frequently. Use the Updates page and the installation-specific docs for current instructions.
Use the smallest relevant read-only checks:
paseo --version
paseo daemon status --json
paseo provider diagnostic <provider> --json
Use the status-reported home, listen address, and log path for further checks. Probe http://127.0.0.1:6767/api/health or read ~/.paseo/daemon.log only when those values match the affected daemon. Do not restart the daemon, edit config, update software, or expose a network listener without the user's explicit permission. A daemon restart can interrupt the agent doing the diagnosis.
For a missing provider or command not found, run paseo provider diagnostic <provider> against the affected host, or open Settings → your host → Providers → provider → Diagnostic. Compare its resolved binary, daemon PATH, and provider version with a brand-new login shell. Shell aliases and functions are not executable paths.
Logs and local files
Use these defaults on the machine where the daemon or Desktop app actually runs. Do not look for a remote daemon's files on the client device.
- Daemon config:
~/.paseo/config.json - Daemon log:
~/.paseo/daemon.log - Agent state directory:
~/.paseo/agents/ - Default managed worktree root:
~/.paseo/worktrees/ - macOS desktop log:
~/Library/Logs/Paseo/main.log - Linux desktop log:
~/.config/Paseo/logs/main.log - Windows desktop log:
%APPDATA%\Paseo\logs\main.log
Substitute the status-reported PASEO_HOME for ~/.paseo. In the official Docker image, the default is /home/paseo/.paseo; its host path depends on the volume mount, and container stdout is available through Docker. Desktop app logs describe the Desktop process; daemon logs describe the selected daemon. Read the narrowest useful slice and redact credentials, pairing offers, tokens, passwords, and user code before sharing logs.
If diagnosing the bundled daemon on a computer with Paseo Desktop installed, but paseo is not on PATH, the bundled CLI is at:
- macOS:
/Applications/Paseo.app/Contents/Resources/bin/paseo - Linux:
<install-dir>/resources/bin/paseo - Windows:
C:\Program Files\Paseo\resources\bin\paseo.cmd
Offer to fix the PATH or symlink; do not change shell configuration silently.
Escalate with evidence
If the current docs and diagnostics do not resolve the problem, collect the app and daemon versions, OS, install method, connection method, exact error, minimal reproduction, and a small redacted log excerpt.
- Bugs: GitHub Issues
- Questions and quick help: Paseo Discord
- Product workflow discussions: GitHub Discussions or
#productin Discord
FAQ
What does the paseo-help skill do?
Answer questions about the Paseo product and app, including setup, configuration, connectivity, providers, workspaces, updates, logs, and troubleshooting. Use when a user inside Paseo asks how Paseo works, how to configure it, or why something is broken; use the paseo skill instead to operate agents and workspaces through MCP or the CLI.
How do I install paseo-help?
Run npx skills add https://github.com/getpaseo/paseo --skill paseo-help in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/paseo-help/ (personal) or .claude/skills/paseo-help/ (project).
Which AI agents can use paseo-help?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is paseo-help safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains paseo-help?
It is published by getpaseo in getpaseo/paseo. It has 1,472 recorded installs.
More from getpaseo/paseo
paseo
getpaseo/paseo
Paseo reference for managing hosts, projects, workspaces, workspace scripts, agents, schedules, and heartbeats.
paseo-handoff
getpaseo/paseo
Hand off the current task to another agent with full context. Use when the user says "handoff", "hand off", "hand this to", or wants to pass work to another agent.
paseo-committee
getpaseo/paseo
Form a committee of two high-reasoning agents to step back, do root cause analysis, and produce a plan. Use when stuck, looping, tunnel-visioning, or facing a hard planning problem.
paseo-advisor
getpaseo/paseo
Spin up a single agent as an advisor — second opinion on the current task. Use when the user says "advisor", "second opinion", "what does X think", or wants an outside take without delegating the work itself.
paseo-loop
getpaseo/paseo
Run an agent loop until an exit condition is met. Use when the user says "loop", "babysit", "keep trying until", "check every X", "watch", or wants iterative autonomous execution.
release-stable
getpaseo/paseo
Cut a stable release of Paseo (fresh patch or minor, or promote from beta). Use when the user says "release stable", "ship stable", "promote", "release:patch", "release:minor", "release:promote", or "/release-stable".
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available