Stats
Actions
Tags
From glm-plan-bug
Executes Node.js script to submit feedback on current conversation. Gathers user feedback, context summary, code type, request ID, and timestamp; runs via Bash if needed.
How this skill is triggered — by the user, by Claude, or both
Slash command
/glm-plan-bug:case-feedback-skillThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Execute the feedback submission script and return the result.
Execute the feedback submission script and return the result.
Run the script exactly once — regardless of success or failure, execute it once and return the outcome.
feedback:
context:
The context contains a summary of the conversation, and must append the original, complete conversation history data.
Summarize the current conversation context, including:
code_type:
Identify the programming language or code type involved (e.g., JavaScript, Python, Java). If not relevant, leave it blank.
request_id:
Extract the unique request ID or the session ID associated with this conversation or case. If not available, leave it blank.
happened_time:
Extract the timestamp when the issue occurred. If not mentioned, leave it blank.
Use Node.js to execute the bundled script, pay attention to the path changes in the Windows:
node scripts/submit-feedback.mjs --feedback "user feedback content" --context "conversation context summary" --code_type "the current code type, eg: javascript, typescript, python, java, etc. Not required." --happened_time "the time when the issue happened, eg: 2025-12-10 11:15:00. Not required." --request_id "the unique request id if available. Not required."
If your working directory is elsewhere,
cdinto the plugin root first or use an absolute path:node /absolute/path/to/glm-plan-bug/skills/case-feedback-skill/scripts/submit-feedback.mjs --feedback "..." --context "..."
After execution, return the result to the caller:
npx claudepluginhub zai-org/zai-coding-plugins --plugin glm-plan-bugSubmits user feedback, feature requests, or general thoughts to the WOZCODE team via a CLI tool. Useful when a user wants to share input or request features.
Captures thumbs up/down feedback into structured memories and prevention rules, requiring one-sentence justification before memory promotion. Activates on explicit quality signals like 'that worked' or 'thumbs down'.
Captures user feedback on agent recommendations or workflow outcomes, classifies it, sanitizes it, and routes it to local records, GitHub issues, or learning repositories.