Studio Feedback logo

Studio Feedback

Organization
AlpacaLabsLLC
studio-feedback

Prepare a user-reviewed Arch Studio bug report or feature request for GitHub. Use when the user runs /as:studio-feedback, says "report a bug", "this skill broke", "send feedback", or requests a feature. Do not use for Claude Code's native /feedback command.

Overview

PublisherAlpacaLabsLLC
Repositoryskills-for-architects
Skill namestudio-feedback
Stars
386
Forks
81
Bundled files
1
LicenseMIT
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Studio Feedback 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/AlpacaLabsLLC/skills-for-architects/tree/main/skills/studio-feedback
  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/AlpacaLabsLLC/skills-for-architects.git /tmp/skills-for-architects
mkdir -p .claude/skills
cp -r /tmp/skills-for-architects/skills/studio-feedback .claude/skills/studio-feedback
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Studio Feedback 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 Studio Feedback 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 Studio Feedback 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.

/as:studio-feedback — Prepare a GitHub report

Before acting, read the host contract and this component's declaration (skill:studio-feedback). Load only its referenced mode profiles from the shared catalog. Compose modes required by the actual task; declarations are requirements, not proof of access or permission.

Host adapter: read delivery-specific guidance for invocation, metadata access, questions and browser opening.

This native report-preparation procedure has no registered operation IDs. Its steps below are the complete owner; no Arch Studio runner, installer, executable download or reconstructed helper is required. An ordinary native encoding or metadata tool may be used where available. Follow the completion contract and distinguish a prepared draft, an opened URL and a submitted issue.

Prepare a report locally, show exactly what would leave the machine, and open GitHub only after one informed confirmation. Never submit the issue, post a comment, call the GitHub API, or transmit diagnostics in the background.

1. Choose the report type

Infer bug or feature when the request is clear. Otherwise use one AskUserQuestion gate to choose the type; do not first ask the same question in prose.

Use these issue forms and labels:

  • Bug: bug-report.yml, label bug; fields version, os, skill, what-happened, expected.
  • Feature: feature-request.yml, label enhancement; fields version, skill, problem, proposal.

2. Prepare minimal fields locally

For MCP, use the actual delivered release version and digest when present; a connection does not imply a local plugin path. For an installed plugin, read its actual .codex-plugin/plugin.json on Codex or .claude-plugin/plugin.json on Claude Code through the host's known package location. Gather only the operating-system name/version through available native host metadata or a bounded local command. Process access is optional and depends on that method. If metadata is unavailable, say unknown rather than searching unrelated files, installing tools or inventing it. Infer the affected skill from the conversation when reliable; otherwise leave it blank or ask during editing.

Draft the report from the user's words, but do not automatically include raw conversation history, files, stack traces, environment variables, or command output. Before showing the draft, remove or visibly flag:

  • client and project names;
  • street and project addresses;
  • home-directory paths and usernames;
  • email addresses and phone numbers;
  • likely secrets, tokens, keys, cookies, and credentials; and
  • proprietary document contents.

When uncertain, omit the value and mark where the user can add a safe description. Never invent reproduction details.

3. Show the exact outbound values

Present every proposed query field verbatim in one fenced text block. Explain immediately before the gate:

Opening GitHub sends the displayed fields immediately as URL query parameters, and the URL may remain in browser history. GitHub receives them before issue submission; closing the tab does not undo that transmission. Arch Studio will not submit the issue.

Use a single confirmation gate with these outcomes:

  1. Open the prefilled GitHub issue.
  2. Edit the fields first.
  3. Cancel without opening GitHub.

Do not ask for confirmation in prose and then repeat it with AskUserQuestion. Editing returns to the same preview and gate. Cancel ends with no browser action or network request.

4. Encode and open only after confirmation

Build the URL from https://github.com/AlpacaLabsLLC/skills-for-architects/issues/new, the selected template, title, label, and the form field IDs above. Encode each query value independently as UTF-8 percent encoding: retain only ASCII letters/digits and -._~, encode every other byte as %HH, then join key/value pairs with &. A native URL API or ordinary task-specific code may do this. Decode each encoded value locally and compare it with the exact approved text before opening; do not double-encode or interpolate report text into shell code. No particular encoding executable is required.

Keep the final URL at or below 6,000 characters. Reduce only the narrative fields, state visibly that they were shortened for the URL, and retain the complete draft locally in the conversation for optional manual pasting. Never shorten version, operating system, or affected skill.

If shortening or any other edit changes a displayed value after confirmation, return the exact revised outbound values to the same preview and informed gate before opening. Earlier approval does not cover a changed payload. Prefer doing encoding and length checks locally before the gate so the user reviews the final values once.

After the confirmed URL is built:

  • Use an actually available native browser-opening capability for the exact approved URL; safely pass it as data. On macOS an available open command is one possible method.
  • If no browser-opening capability is available, print the exact URL and label it not opened; do not install a browser helper or claim transmission occurred.

Only after observing the browser action, say: "GitHub is open with the displayed fields. Review and edit the issue before choosing Submit on GitHub."

Hard boundaries

  • Never submit the issue or use gh issue create.
  • Never open GitHub before the exact-value preview and informed gate.
  • Never claim that closing an opened tab means nothing was transmitted.
  • Never treat feedback as telemetry or send it to ALPA infrastructure.
  • Never add project files, conversation transcripts, or attachments automatically.

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 Studio Feedback AI skill do?

Prepare a user-reviewed Arch Studio bug report or feature request for GitHub. Use when the user runs /as:studio-feedback, says "report a bug", "this skill broke", "send feedback", or requests a feature. Do not use for Claude Code's native /feedback command.

Why use Studio Feedback on TypingMind?

Because you install it once and use it with any model. Studio Feedback 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 Studio Feedback in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/studio-feedback. 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 Studio Feedback?

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 Studio Feedback?

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

Is the Studio Feedback AI skill free?

Yes. It is published on GitHub by AlpacaLabsLLC under the MIT license. 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 👇