Expo Skill Feedback
FreeProvide actionable feedback to improve Expo skills.
Free · Opens the source repo
What Expo Skill Feedback does
The Expo Skill Feedback tool allows users to submit specific feedback about their experiences with Expo skills or the Expo platform itself. This tool is particularly useful for developers and designers who want to contribute to the improvement of Expo by reporting what worked well or where they encountered issues. Users can submit feedback via a command-line interface using the npx command, which makes it straightforward to provide insights directly from their development environment.
When submitting feedback, users have the option to include additional context by specifying a category and subject. Categories include options like skills, docs, and mcp, while subjects can pinpoint exact tools or commands involved in the feedback. This structured approach helps the Expo team understand the context of the feedback better and prioritize improvements effectively. The feedback process is independent of usage telemetry, meaning users can report their experiences without enabling tracking.
In addition to general feedback, the tool also allows users to report instances where an AI agent failed to complete a task related to Expo. This is valuable for identifying areas where the AI may need improvement and ensuring that future iterations of the agent can handle tasks more effectively. Users can submit these reports in a specific format that outlines the task, expected outcomes, and actual results, providing clear evidence for the Expo team to work with.
The Expo Skill Feedback tool is ideal for developers and designers who actively use Expo and want to influence its evolution. By sharing their experiences, they can help shape the platform into a more robust and user-friendly environment for everyone involved in Expo development.
When to use it
Use this tool when you encounter issues with Expo skills or want to provide suggestions for improvement.
When not to use it
This is not suitable for casual users who do not have specific feedback or technical issues to report.
What you can build with it
Reporting a Skill Issue
If you find that an Expo skill is confusing or broken, use this tool to submit detailed feedback directly.
Suggesting Improvements
When you have ideas on how an Expo feature could be enhanced, submit your actionable feedback to help guide development.
Documenting AI Agent Failures
If an AI agent struggles with an Expo task, report it as an eval candidate to help improve its performance.
How to install Expo Skill Feedback
View source1. Install with the skills CLI
npx skills add expo/skills/expo-skill-feedback --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by expoExpo Skill Feedback
Help Expo improve by sharing specific feedback about what worked well or what fell short. Feedback submission is independent of usage telemetry and does not require enabling it.
Submit feedback
npx --yes submit-expo-feedback@latest "<ACTIONABLE_FEEDBACK>"
Add either optional flag independently when it provides useful context:
npx --yes submit-expo-feedback@latest --category "<CATEGORY>" --subject "<SUBJECT>" "<ACTIONABLE_FEEDBACK>"
--category defaults to unknown, and --subject may be omitted when there is no specific target.
When including them, choose the values that most precisely identify what the feedback is about:
| Category | Subject |
|---|---|
skills | Exact skill name from its frontmatter, such as expo-router |
docs | Full Expo documentation URL |
mcp | Exact MCP tool name used |
expo-cli | Full Expo CLI command, such as npx expo install |
eas-cli | Full EAS CLI command, such as eas build |
evals | Expo package or command the failed task involves, else a capability phrase, such as expo-router or eas build |
unknown | Concise Expo product, package, feature, or other topic |
In the final argument, say what helped and why, or provide the relevant context, expected behavior, and what happened instead. Do not include secrets, source code, personal data, long prompts, or stack traces.
Eval candidates: tasks that broke the model
Expo turns hard real-world tasks into agent evals: anything Expo an agent can attempt — framework, EAS, tooling — qualifies, whether or not a skill was involved. The signal worth sending is a task an AI agent could not complete cleanly despite real effort: several failed attempts, a build or screen that never worked, or the user stepping in to fix it manually. Never submit quick slips the agent corrected itself, more than one candidate per session, or a task already reported.
When such a failure happens — or the user says a model failed at an Expo task — show the user the exact
submission you intend to send and get approval; the Task field must describe the Expo-technical
shape of the task, never the user's product or business context. Without a user to approve it
(headless or CI runs), do not submit. Then run from the failing app's directory (the CLI attaches
the SDK and package versions, agent harness, and platform automatically) with --category evals,
--subject naming the Expo package or command involved (a capability phrase only when no single
package fits), and this structure in the final argument:
Task: <what was asked, self-contained>.
Expected: <observable success criteria>.
Actual: <what the agent did instead>.
Wrong approach: <the specific mistake, such as a wrong API, hallucinated prop, or bad pattern>.
Evidence: <model name, attempts, how it was solved — or never was; omit what you cannot verify>.
A good candidate is solvable (eventually done or clearly doable), verifiable (success is
observable), and specific. Mention only environment details the CLI cannot see, such as other key
packages or a freshly created app. Describe code; do not paste it. If the command fails with an
error naming evals as an invalid category, resend once with --category unknown and the same
subject prefixed eval-candidate: ; on any other error, do not resend.
Usage telemetry
Automatic skill usage telemetry is separate from feedback and off by default. Never enable it
without an explicit user request. Use the following script with --on, --off, or --status:
node "${CLAUDE_PLUGIN_ROOT}/skills/expo-skill-feedback/scripts/telemetry.cjs" --status
Environment equivalents are EXPO_SKILLS_TELEMETRY=1 to enable and
EXPO_SKILLS_TELEMETRY=0 or DO_NOT_TRACK=1 to disable. CI never sends telemetry.
Submitting Feedback
If you encounter errors, misleading or outdated information in this skill, report it so Expo can improve:
npx --yes submit-expo-feedback@latest --category skills --subject "expo-skill-feedback" "<actionable feedback>"
Only submit when you have something specific and actionable to report. Include as much relevant context as possible. If an AI agent repeatedly failed or the user had to take over an Expo task, load the expo-skill-feedback skill and follow its eval-candidate flow instead of reusing the command above.
Frequently asked questions about Expo Skill Feedback
Similar skills
Spring Boot Testing
Master testing techniques for Spring Boot 4 applications.
GitHub Issues
Manage GitHub issues efficiently with MCP tools.
Geofeed Tuner
Optimize your IP geolocation feeds in CSV format.
Batch Files
Master Windows batch scripting for automation and task management.
Adobe Illustrator Scripting
Automate your Illustrator workflows with ExtendScript.
Plugin Structure
Create and organize Claude Code plugins effectively.