mcpbeat Sign in

Studio Feedback Skill for Claude

Prepare a user-reviewed Architecture 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.

1k tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
302
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/AlpacaLabsLLC/skills-for-architects --skill studio-feedback

What comes with it

491 bytes besides the instruction
README.md

What it tells the agent to use

found in the instruction text
Bash runs shell commands — read the instruction before connecting

The instruction itself

6 sections, as written by the author

/as:studio-feedback — Prepare a GitHub report

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

Read the installed version from ${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json. Gather the operating-system name and version with local commands only. 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. Architecture Studio will not submit the issue.

Use a single confirmation gate with these outcomes:

  • Open the prefilled GitHub issue.
  • Edit the fields first.
  • 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. Percent-encode every value with jq @uri; use Python 3 urllib.parse.quote only when jq is unavailable. Never interpolate unencoded report text into a shell command.

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.

After the confirmed URL is built:

  • On macOS, safely pass it as one quoted argument to open.
  • On other systems, print the URL rather than assuming a browser command.

Then 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.

Other skills for the same job

different authors, same section of the catalogue
Hook Development
by anthropics
vendor ×2

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

16k tokens scripts
Hook Development
by anthropics
vendor ×2

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

16k tokens scripts
Copilot SDK
by christophacham
×2

Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent.

6k tokens
Cass
by Dicklesworthstone
×2

Coding Agent Session Search - unified CLI/TUI to index and search local coding agent history from Claude Code, Codex, Gemini, Cursor, Aider, ChatGPT, Pi-Agent, Factory, and more. Purpose-built for AI agent consumption with robot mode.

6k tokens
Dcg
by Dicklesworthstone
×2

Destructive Command Guard - High-performance Rust hook for Claude Code that blocks dangerous commands before execution. SIMD-accelerated, modular pack system, whitelist-first architecture. Essential safety layer for agent workflows.

4k tokens
Makepad Skills
by ComeOnOliver
×2

Makepad UI development skills for Rust apps: setup, patterns, shaders, packaging, and troubleshooting.

2k tokens
Varlock Claude Skill
by ComeOnOliver
×2

Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits

3k tokens
Create Agentsmd
by github
vendor ×1

Prompt for generating an AGENTS.md file for a repository

2k tokens

How to use it

Copy the folder

Take alpacalabsllc/studio-feedback from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.