App Feedback Admin logo

App Feedback Admin

CommunityPopular
Jamailar
app-feedback-admin

Read platform-admin feedback issues through the trusted HTTP admin API, summarize user reports, and turn them into RedBox/RedConvert repair and iteration plans. Use when the user asks to read app feedback, triage feedback tickets, inspect remote feedback context, or prepare fix/iteration plans from feedback. This skill must keep FEEDBACK_ADMIN_API_KEY server-side/local only and must not place it in app UI, frontend code, desktop client code, logs, commits, or shared artifacts.

Overview

PublisherJamailar
RepositoryBeav
Skill nameapp-feedback-admin
Stars
1.9K
Forks
240
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Jamailar on GitHub. Read the source before you install it.

Installation

Install the App Feedback Admin AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Jamailar/Beav/tree/main/desktop/skills/app-feedback-admin
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Jamailar/Beav.git /tmp/Beav
mkdir -p .claude/skills
cp -r /tmp/Beav/desktop/skills/app-feedback-admin .claude/skills/app-feedback-admin
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable App Feedback Admin in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads App Feedback Admin on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so App Feedback Admin is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

app-feedback-admin

Use this skill to read remote feedback tickets and convert them into concrete RedBox/RedConvert repair and iteration work.

Activate this skill when the user asks to read app feedback, process feedback tickets, inspect remote feedback context, or turn feedback into a repair or iteration plan.

Hard Boundaries

  • Never put FEEDBACK_ADMIN_API_KEY into desktop app code, renderer UI, frontend bundles, committed docs, screenshots, transcripts, or generated plans.
  • Treat the feedback API as an operator-only channel. It is suitable for local scripts, CI/ops jobs, or trusted server automation only.
  • Default to read-only triage. Do not update ticket status, add comments, or review/reward feedback unless the user explicitly asks for a write action in the current turn.
  • Do not infer product root cause only from the ticket text. For bugs, cross-check RedBox code and local runtime evidence where relevant, especially ~/Library/Application Support/RedBox/session-transcripts/, session-bundles/, and state DB/files.

Local Environment

Use the ignored env file at repo root:

text
.redbox-dev/feedback-admin.env

Expected variables:

bash
API_BASE="https://..."
FEEDBACK_ADMIN_API_KEY="..."
FEEDBACK_APP_SLUG="xitun"

If the env file is missing or incomplete, stop and ask the user for the missing local configuration. Do not invent an API base or app slug.

Read Workflow

  1. Load the local env file without printing secrets.
  2. Fetch the newest feedback list:
bash
python3 desktop/skills/app-feedback-admin/scripts/fetch_feedback.py list --page-size 20
  1. For tickets that look actionable, fetch details:
bash
python3 desktop/skills/app-feedback-admin/scripts/fetch_feedback.py detail <feedback_id>
  1. Classify each ticket into one of:
    • bug: reproducible product failure, crash, wrong result, data loss, broken workflow.
    • ux: confusing UI, missing affordance, excessive friction.
    • feature: new capability or workflow expansion.
    • ops: account, billing, deployment, API, notification, or backend process issue.
    • invalid: duplicate, unclear, spam, unsupported, or not enough evidence.
  2. Map actionable items to RedBox modules:
    • desktop UI: desktop/src/pages/*, desktop/src/components/*, desktop/src/bridge/ipcRenderer.ts
    • Tauri host: desktop/src-tauri/src/commands/*, runtime/*, persistence/*, events/*
    • AI runtime: desktop/src-tauri/src/agent/*, skills/*, tools/*, mcp/*, subagents/*
    • media/video: desktop/src-tauri/src/media*, editor/runtime files
    • plugin intake: Plugin/*
    • website/release: RedBoxweb/*, private/scripts/hybrid-release/*
  3. Produce a concrete plan, not loose advice. Include ticket ids, severity, evidence, suspected module, implementation target files, verification steps, and whether it is a fix or product iteration.

Output Shape

Use this shape unless the user asks for a different one:

markdown
**Feedback Triage**
- <id>: <status/priority> <classification> - <one-line user problem>

**Repair Plan**
- <module>: <specific fix>, files: <paths>, verification: <checks>

**Iteration Plan**
- <module>: <specific product improvement>, files/docs: <paths>, risk: <risk>

**Needs User Decision**
- <question or tradeoff, only when blocked>

Keep user-facing wording concise. Prefer evidence and next actions over explanatory text.

Optional Write Actions

Only after explicit user approval, use the admin API to:

  • add internal comments for investigation notes,
  • add user-visible replies,
  • update status/priority/category,
  • review as useless, thanks, or useful.

Write actions must include a short audit note and must not expose secrets.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the App Feedback Admin AI skill do?

Read platform-admin feedback issues through the trusted HTTP admin API, summarize user reports, and turn them into RedBox/RedConvert repair and iteration plans. Use when the user asks to read app feedback, triage feedback tickets, inspect remote feedback context, or prepare fix/iteration plans from feedback. This skill must keep FEEDBACK_ADMIN_API_KEY server-side/local only and must not place it in app UI, frontend code, desktop client code, logs, commits, or shared artifacts.

Why use App Feedback Admin on TypingMind?

Because you install it once and use it with any model. App Feedback Admin is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install App Feedback Admin in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Jamailar/Beav/tree/main/desktop/skills/app-feedback-admin. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use App Feedback Admin?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with App Feedback Admin?

As many as you like. As long as a model supports skills, you can use App Feedback Admin with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the App Feedback Admin AI skill free?

It is published on GitHub by Jamailar. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇