expo-skill-feedback
An agent skill by expo, from expo/skills. Tags: analysis, documentation, evaluation, feedback, tracking.
What it does
Submit feedback on an Expo skill—or Expo itself—and control bundled anonymous usage telemetry (off by default / opt-in). Submit feedback with: npx --yes submit-expo-feedback@latest "ACTIONABLE_FEEDBACK". Optionally add either or both: --category "CATEGORY" and --subject "SUBJECT". Replace the uppercase placeholders before running. Use when a skill was useful, confusing, broken, missing context, or worth improving; when Expo, Expo CLI, EAS CLI, docs, or MCP worked well or fell short; when an AI agent repeatedly failed, got stuck, or needed the user to take over an Expo task (report it as an eval candidate); or when the user explicitly asks to enable or disable telemetry (tracking), check its status, or understand what it collects.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add expo/skills --skill expo-skill-feedback
Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/expo/skills
cp -r skills/plugins/expo/skills/expo-skill-feedback ~/.claude/skills/expo-skill-feedback
Safety box score
Grade C, moderate risk: 35 of 100 risk points, rated 2026-09-22. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill submits feedback to Expo using an `npx`-fetched package and can toggle anonymous usage telemetry. It also writes small persistent markers under `~/.expo-skills/` and sends data off-machine to Expo/PostHog. The main risk is the unpinned external package execution path plus the outbound network posts.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 3 (high) | The main command is `npx --yes submit-expo-feedback@latest ...`, which downloads and executes code from the registry; the bundled Node scripts also run locally. |
| Network access | 2 (moderate) | It sends feedback off-machine through `npx --yes submit-expo-feedback@latest` and telemetry posts to `https://us.i.posthog.com` via `sendToPosthog(...)`. |
| Filesystem reach | 1 (low) | The telemetry scripts create and remove persistent files only under the user's home directory, including `~/.expo-skills/opt-in` and `~/.expo-skills/installation-id`. |
| Secrets & credentials | 0 (none) | It does not read credential stores, browser sessions, `.env` files, or private API keys; the PostHog key in the repo is described as a public ingestion key. |
| Privilege & persistence | 0 (none) | There is no sudo, global install, service registration, shell-startup editing, or OS setting change. |
| Instruction hijack surface | 0 (none) | The files contain procedural guidance for submitting feedback and eval candidates, but nothing that tells the agent to ignore its rules, hide behavior, or follow remote instructions. |
| Irreversible actions | 2 (moderate) | It is designed to post feedback or eval-candidate reports on the user's behalf and to enable/disable telemetry, which are external side effects even though they are user-driven. |
| Transparency | 2 (moderate) | The core submission path depends on `submit-expo-feedback@latest`, so the actual code being run is outside this repo and not inspectable here. |
Before installing
- Check whether you are comfortable with `npx --yes submit-expo-feedback@latest` fetching and running code from npm.
- Confirm that creating `~/.expo-skills/` for telemetry opt-in and installation IDs is acceptable on this machine.
- If you only want to inspect telemetry state first, run `node scripts/telemetry.cjs --status`.
Rated 2026-09-22 by an automated review of 5 files from the skill's repository.
Source
- Repository
- expo/skills (all skills from this repository)
- Path
- plugins/expo/skills/expo-skill-feedback/SKILL.md
- Branch
- main
- Collection
- expo
- Updated
- 2026-09-22
Related skills
- learn — Manage project learnings.
- arena — Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
- attribution — When the user wants to figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model.
- audit-prep-assistant — Prepares codebases for security review using Trail of Bits' checklist.
- automate-me — Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill".
- code-maturity-assessor — Systematic code maturity assessment using Trail of Bits' 9-category framework.