From corezoid
Collects and submits bug reports, improvement requests, and quality signals about the Corezoid plugin to the Corezoid team.
How this skill is triggered — by the user, by Claude, or both
Slash command
/corezoid:corezoid-feedbackThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You help users report bugs, suggest improvements, and flag unexpected behavior
You help users report bugs, suggest improvements, and flag unexpected behavior in the Corezoid plugin to the Corezoid team.
Case 1 — bug or broken behavior. The user reports something that stopped working, produced wrong output, or broke their process. Offer once, adapting to the context:
"Хотите сообщить о баге команде Corezoid?"
Case 2 — improvement request. The user hints that something could work better ("хотелось бы", "было бы здорово", "можно улучшить"):
"Хотите отправить пожелание команде Corezoid?"
Case 3 — platform-level mistake by the plugin. The message reveals that the plugin chose the wrong node type, wrong API, wrong structure, or wrong MCP tool. Add one line to the normal response without interrupting it:
"Хотите сообщить об этом команде Corezoid?"
In all cases: offer once per problem context, do not repeat if the user declines. Do not offer when the user is iterating on business logic.
If the user agrees, derive as much as possible from context and ask only for what is missing:
| Field | Meaning |
|---|---|
problem (required) | What went wrong, in the user's words |
expected | What the user expected to happen |
proposed_solution | How the user thinks it should work |
tool | Which tool or skill was involved (derive from context) |
transcript_excerpt | Short relevant excerpt of the dialog |
contact | Optional email or handle for follow-up |
Before calling send-feedback, always show the user exactly what will be sent:
Планирую отправить следующее:
• Проблема: <problem text>
• Ожидалось: <expected text>
• Предложение: <proposed_solution text>
• Инструмент: <tool>
• Выдержка из диалога: <transcript_excerpt>
• Контакт: <contact or "не указан">
Explicitly note that any tokens, API keys, and secrets have been masked. Ask the user to confirm, edit, or cancel before proceeding.
Never call send-feedback without an explicit "yes" / "да" / "отправляй" from the user.
After confirmation, call the MCP tool:
send-feedback(
problem: "<user's description>",
expected: "<optional>",
proposed_solution: "<optional>",
tool: "<optional>",
transcript_excerpt: "<optional, keep short>",
contact: "<optional>"
)
The tool performs its own secret redaction automatically. Pass the raw user text — do not pre-redact in your message to the tool.
On success the tool returns a ticket id, for example:
Feedback submitted. Ticket id: 6a3b8b6ab677ac777074794f
Tell the user:
"Спасибо! Заявка отправлена, номер:
6a3b8b6ab677ac777074794f. По нему можно ссылаться при дальнейшем обсуждении с командой Corezoid."
On error, respond gently:
"Не удалось отправить фидбек прямо сейчас. Попробуйте позже или напишите на [email protected]."
Do not show the technical endpoint URL or error details to the user.
npx claudepluginhub corezoid/corezoid-ai-plugin --plugin corezoidExtracts actionable learnings from a finished Corezoid session and routes them to CLAUDE.md, team feedback, allowlists, or personal memory — no changes without confirmation.
Files a feedback issue against the SDD plugin repo when a skill causes significant friction like contradictory instructions, tool failures, or ambiguous docs. Shows the proposed body for user approval.
Deprecated alias for bug reports — redirects to `/woz-feedback` for bug submission with structured details.