New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Wandering Sample

by open-edge-platform in open-edge-platform/edge-ai-suites

Review-first workflow for changes in components/wandering and tutorial packages.

Apache-2.0Auto-check passed

Install Wandering Sample

skills CLI
$ npx skills add open-edge-platform/edge-ai-suites --skill wandering-sample -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install open-edge-platform/edge-ai-suites wandering-sample --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/open-edge-platform/edge-ai-suites.git skills-src && mkdir -p .claude/skills && cp -r skills-src/robotics-ai-suite/.github/skills/wandering-sample .claude/skills/wandering-sample && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
wandering-sample
GitHub stars
140
Token cost
~1.6k tokens
SKILL.md length
601 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
Apache-2.0

At a glance

Review-first workflow for changes in components/wandering and tutorial packages.

  • Works in 7 steps: Review the repository before editing. → Propose a plan and show the intended… → Wait for explicit user approval before… → …
  • Editing Wandering launch files
  • SKILL.md covers When to Use, Required Behavior, What The Sample Uses and Canonical Review-First Workflow, plus 5 more sections
  • Calls make

What it does

Wandering Sample is an agent skill from open-edge-platform/edge-ai-suites. Review-first workflow for changes in components/wandering and tutorial packages. Use when editing Wandering launch files, docs, tests, Nav2 wiring, RTAB-Map, RealSense, or robot bring-up paths.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: A curated collection of sample applications intended for reference in developing optimized AI solutions and testing hardware performance across various industry use cases. The licence is Apache-2.0.

When your agent uses it

  • Editing Wandering launch files
  • Robot bring-up paths

Example prompts

  • “/wandering-sample”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Review the repository before editing.
  2. Propose a plan and show the intended diff before making changes.
  3. Wait for explicit user approval before applying edits.
  4. Keep changes scoped to the Wandering Sample unless the user asks otherwise.
  5. Prefer Intel-packaged and Intel-aligned paths already used by the sample.
  6. Explain tradeoffs if a non-Intel path is suggested, and do not switch to it when an Intel path already exists.
  7. Produce a clear ASCII pipeline diagram when asked to explain the app.

What it can do on your machine

Read from SKILL.md and the folder at commit 6e2ba00. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • make

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Wandering Sample loads about 1.6k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 601 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from open-edge-platform/edge-ai-suites at commit 6e2ba00, republished under its Apache-2.0 licence (© open-edge-platform). 601 words, ~1,557 tokens.

Download SKILL.mdSave it as .claude/skills/wandering-sample/SKILL.md (or your agent's skills folder).
name
wandering-sample
description
Review-first workflow for changes in components/wandering and tutorial packages. Use when editing Wandering launch files, docs, tests, Nav2 wiring, RTAB-Map, RealSense, or robot bring-up paths.
license
Apache-2.0

Wandering Sample Agent Skill

This skill defines the review-first workflow for the Wandering Sample.

When to Use

Use this skill only for the Wandering Sample under components/wandering and its tutorial packages:

  • wandering
  • wandering_gazebo_tutorial
  • wandering_aaeon_tutorial
  • wandering_irobot_tutorial
  • wandering_jackal_tutorial
  • wandering_tutorials
  • wandering_agentic_tutorial

Required Behavior

Any coding companion using this skill must:

  1. Review the repository before editing.
  2. Propose a plan and show the intended diff before making changes.
  3. Wait for explicit user approval before applying edits.
  4. Keep changes scoped to the Wandering Sample unless the user asks otherwise.
  5. Prefer Intel-packaged and Intel-aligned paths already used by the sample.
  6. Explain tradeoffs if a non-Intel path is suggested, and do not switch to it when an Intel path already exists.
  7. Produce a clear ASCII pipeline diagram when asked to explain the app.

What The Sample Uses

The Wandering Sample is not an OpenVINO inference demo. Its Intel-specific runtime path is the sensor and robotics stack already present in the repo:

  • Intel RealSense camera support via realsense2_camera and realsense2_description
  • RTAB-Map SLAM via rtabmap_ros
  • Nav2 navigation via the tutorial packages and Nav2 plugins already wired in the sample
  • depthimage_to_laserscan and imu_filter_madgwick in the Jackal integration path
  • tf2_ros for the camera and robot frame wiring

Use those names when explaining the pipeline. Do not claim OpenVINO acceleration unless the user explicitly asks for a different sample.

Canonical Review-First Workflow

When a user asks for a change, the assistant should do the following:

  1. Read the nearest launch file, README, package metadata, and the tests that cover the touched behavior.
  2. State a falsifiable local hypothesis about how the Wandering Sample currently works or why it fails.
  3. State one cheap check that could disconfirm that hypothesis.
  4. Propose a minimal edit plan and show the expected diff summary.
  5. Wait for review approval before editing.
  6. After approval, apply the change, run the narrowest relevant validation, and fix only what the validation disconfirms.

Canonical Example Prompt

Paste this prompt into your coding assistant after opening the Wandering Sample folder in VS Code:

text
You are working only in the Wandering Sample under components/wandering.

First, inspect the nearest launch files, README, and tests. Do not edit anything yet.
Then respond with:
1) a short plan,
2) the exact files you expect to change,
3) a brief diff summary,
4) one ASCII pipeline diagram of the current app,
5) a plain-English explanation of which Intel-aligned libraries or packages the sample uses and what each part of the pipeline does.

Do not make edits until I approve the plan and diff.

If I approve, make the smallest safe change needed for the requested feature.
Keep the change scoped to Wandering Sample code, docs, or tests.
Do not introduce non-Intel alternatives when an Intel-aligned path already exists.

When you are ready to propose the change, include both simulation and real-robot considerations:
- simulation mode with the Gazebo tutorial,
- real-robot mode with the AAEON, Jackal, or iRobot tutorial when supported.

If you propose a modification, also provide the exact validation command or commands I should run after the change.
Show full SKILL.md (262 more words)Show less

Use the following steps in your coding companion UI:

  1. Enable Chat or Plan mode in your coding assistant window.
  2. Paste the canonical prompt from this file.
  3. Review the assistant's plan, ASCII diagram, and proposed diff before allowing edits.
  4. Once reviewed, enable Agent mode and let the assistant apply the change.
  5. Verify the result in simulation first, then in real-robot mode if the feature supports it.

Supported examples include Copilot, Continue, and Gemini Assist.

Current Pipeline Diagram

text
Simulation path:

  [Gazebo / simulated robot]
             |
             v
  [Nav2 + wandering_app]
             |
             v
  [robot motion / map updates]

Real-robot path:

  [Intel RealSense camera] -----> [realsense2_camera]
             |                           |
             |                           v
             |                    [rtabmap_ros]
             |                           |
  [IMU / base_link / tf2_ros] --> [Nav2 + wandering_app]
                                         |
                                         v
                                [depthimage_to_laserscan]
                                         |
                                         v
                                [robot cmd_vel / navigation]

Validation Expectations

When the assistant makes changes, it should validate with the narrowest command that covers the touched behavior. Typical checks include:

  • make test
  • make lint
  • the tutorial launch command for the selected platform
  • the real-robot launch script when the change touches hardware bring-up

If the change affects simulation, it must be runnable in the Gazebo tutorial before it is considered complete. If the change affects a supported robot, it must also work with the documented real-robot workflow.

Troubleshooting

  • If the assistant starts editing before showing a plan and diff, stop it and rerun the prompt.
  • If the assistant suggests a non-Intel camera or SLAM path, keep the Intel-aligned stack already used by the sample unless you explicitly want a redesign.
  • If the build fails, check that the correct ROS distro has been sourced and that the tutorial package is built before launch.
  • If the real-robot workflow fails, verify the robot namespace, camera topic names, and calibration assumptions in the tutorial script.
  • If the assistant output does not include an ASCII diagram, ask it again before approving edits.

© open-edge-platform, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in robotics-ai-suite/.github/skills/wandering-sample of open-edge-platform/edge-ai-suites.

Open the folder on GitHubat commit 6e2ba00

Compare with similar skills

Wandering Sample next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Wandering Sample compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Wandering Sample this skillopen-edge-platform/edge-ai-suites140—~1.6kAutomated safety check: PassApache-2.0
Add Packageremix-run/remix33k—~2kAutomated safety check: PassMIT
TutorialQ00/ouroboros6.2k—~1.6kAutomated safety check: PassMIT
Tutorial Engineersickn33/agentic-awesome-skills47k2 repos~4.1kAutomated safety check: PassMIT
Add New Packageremotion-dev/remotion62k—~777Automated safety check: NotesCustom licence
Technical Tutorialssickn33/agentic-awesome-skills47k1 repos~770Automated safety check: PassMIT

Similar skills

  • Add Package

    remix-run/remix

    Create or align a package in the Remix monorepo to match existing package conventions.

    33k GitHub stars~2k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Tutorial

    Q00/ouroboros

    Interactive tutorial teaching Ouroboros hands-on. An agent skill from Q00/ouroboros.

    6.2k GitHub stars~1.6k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Tutorial Engineer

    sickn33/agentic-awesome-skills

    Creates step-by-step tutorials and educational content from code.

    47k GitHub starsUsed in 2 repos~4.1k tokens
    EducationAuto-check passed

  • Add New Package

    remotion-dev/remotion

    Official

    Add a new package to the Remotion monorepo, including package scaffolding, monorepo registration, documentation, build scripts, and release checklist updates.

    62k GitHub stars~777 tokensUpdated today
    Media & CreativeAuto-check: notes

  • Technical Tutorials

    sickn33/agentic-awesome-skills

    When the user wants to create step-by-step technical tutorials, quickstarts, or code walkthroughs.

    47k GitHub starsUsed in 1 repo~770 tokens
    Writing & ContentAuto-check passed

  • Python Packaging

    wshobson/agents

    Package and publish Python libraries and CLI tools: project layout, pyproject.toml, build backends, wheels and source distributions, versioning and PyPI releases.

    40k GitHub starsUsed in 11 repos~911 tokens
    DevelopmentAuto-check passed

More from open-edge-platform/edge-ai-suites

All 15 skills in this repo

  • Onboarding Validation

    open-edge-platform/edge-ai-suites

    Validate the get-started experience of Open Edge Platform (OEP) software components from the perspective of a first-time user.

    140 GitHub stars~3.3k tokensUpdated yesterday
    Auto-check passed

  • Sc QA

    open-edge-platform/edge-ai-suites

    Ask a natural-language question against indexed content via the Content Search RAG Q&A endpoint.

    140 GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed

  • Sc Upload

    open-edge-platform/edge-ai-suites

    Upload a file to the Content Search backend and poll the ingestion task until the file is fully indexed (status COMPLETED).

    140 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed

  • Uav Vision Analytics

    open-edge-platform/edge-ai-suites

    Build an end-to-end UAV object detection and telemetry overlay application on Intel hardware using DL Streamer Pipeline Server with MAVLink telemetry.

    140 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check: notes

  • Knowledgebase

    open-edge-platform/edge-ai-suites

    Generic RAG query skill - Retrieve any information from the local knowledge base and generate structured reports, summaries, or Q&A responses.

    140 GitHub stars~900 tokensUpdated yesterday
    Auto-check passed

  • Lvc Run App

    open-edge-platform/edge-ai-suites

    Run, start, or smoke-test the Live Video Captioning app (Docker Compose stack with dashboard on :4173).

    140 GitHub stars~796 tokensUpdated yesterday
    Auto-check passed

Questions about Wandering Sample

What does Wandering Sample do?

Review-first workflow for changes in components/wandering and tutorial packages. Wandering Sample is an agent skill from open-edge-platform/edge-ai-suites. Review-first workflow for changes in components/wandering and tutorial packages.

When should I use Wandering Sample?

Wandering Sample fits situations like: editing Wandering launch files; robot bring-up paths.

How do I install Wandering Sample in Claude Code?

Run `npx skills add open-edge-platform/edge-ai-suites --skill wandering-sample -a claude-code`. Or copy the skill folder (robotics-ai-suite/.github/skills/wandering-sample in open-edge-platform/edge-ai-suites) into .claude/skills/wandering-sample in your project. Claude Code loads it when a task matches its description.

How do I install Wandering Sample in Codex?

Run `npx skills add open-edge-platform/edge-ai-suites --skill wandering-sample -a codex`. Or copy the skill folder (robotics-ai-suite/.github/skills/wandering-sample in open-edge-platform/edge-ai-suites) into .agents/skills/wandering-sample in your project. Codex loads it when a task matches its description.

Can I use Wandering Sample in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add open-edge-platform/edge-ai-suites --skill wandering-sample -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wandering-sample, .gemini/skills/wandering-sample, .github/skills/wandering-sample and .opencode/skills/wandering-sample in your project.

What does Wandering Sample need to run?

Going by SKILL.md and its folder, Wandering Sample needs the command-line tools its instructions call (make).

Does Wandering Sample access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Wandering Sample safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Wandering Sample use?

Wandering Sample is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Wandering Sample use?

About 1.6k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Wandering Sample?

Skills that share tags, products or a category with Wandering Sample: Add Package (remix-run/remix, 33k stars), Tutorial (Q00/ouroboros, 6.2k stars), Tutorial Engineer (sickn33/agentic-awesome-skills, 47k stars) and Add New Package (remotion-dev/remotion, 62k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Wandering Sample?

open-edge-platform (a GitHub organization) maintains it in open-edge-platform/edge-ai-suites, which has 140 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 6, 2026.

Source: open-edge-platform/edge-ai-suites on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.