skills.rest
openharmonyinsight
openharmonyinsightOFFICIAL
Explore all skills by this author →
GitHub

ai-feedback-collector-zh

Normalize user-described AI usage problems into structured, taggable feedback reports.

31|6|Updated Jan 29, 2026
Search Tags:#triage#label taxonomy#severity classification#ai feedback#issue reporting#webhook integration
One-click install
npx skills add https://github.com/openharmonyinsight/openharmony-skills --skill ai-feedback-collector-zh
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-feedback-collector-zh
Source: https://github.com/openharmonyinsight/openharmony-skills/tree/main/skills/ai-feedback-collector-zh
Command: npx skills add https://github.com/openharmonyinsight/openharmony-skills --skill ai-feedback-collector-zh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps when users need to report, collect,整理,归类, and template problems they encountered while using AI tools or AI-assisted workflows, converting vague natural-language descriptions into structured, objective feedback that is easy to copy, search, and dispatch.

Core Features & Use Cases

  • Structured feedback normalization: Transforms user-provided issue narratives into a consistent report with title, summary,原始描述, usage scenario, classification, tags, severity, impact, and suggested next steps.
  • Fact vs. inference guardrails: Encourages separating observable facts from speculation, using unknown when information is missing to avoid overreach.
  • Label-taxonomy alignment: Produces machine-readable lowercase kebab-case tags and uses the repository’s label taxonomy to standardize tool/category/scenario/task/issue/capability/severity/frequency.
  • Automated issue dispatch support: Persists the generated title/body into scripts/issue_output.json and triggers webhook-based issue creation via OS-specific scripts.

Quick Start

Use this skill by asking an AI assistant to convert the following user description of an AI usage problem into a structured feedback report: “When I used the AI coding assistant to generate a patch for a build failure, it produced an unsafe destructive change and the build still failed; I want you to collect and classify this as actionable feedback.”

Frequently Asked Questions about ai-feedback-collector-zh

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert free-form AI usage problems into structured feedback reports?▼

To convert free-form AI usage problems into structured feedback reports, this Skill normalizes natural language narratives into a consistent format with title, summary, classification, tags, severity, and impact. It enforces fact vs. inference separation to ensure objective, actionable issue reporting.

How does fact vs. inference separation work when classifying AI issues?▼

Fact vs. inference separation works by extracting observable facts from user narratives and classifying root-cause categories with confidence, while using unknown defaults for missing information. This guardrail prevents overreach, ensuring the generated structured feedback remains objective and accurately reflects the reported AI issue.

What is the best way to standardize triage tags for AI issue reporting?▼

The best way to standardize triage tags for AI issue reporting is by aligning outputs with the repository's label taxonomy. This Skill produces machine-readable lowercase kebab-case tags that standardize tool, category, scenario, task, issue, capability, severity, and frequency dimensions.

Can I use webhook integration to automate issue creation from normalized AI feedback?▼

Yes, you can use webhook integration to automate issue creation. The Skill persists the generated report title and body into scripts/issue_output.json and triggers webhook-based issue creation via OS-specific scripts, dispatching the structured AI feedback downstream automatically.

Does this structured feedback normalization work for coding agents and office workflows?▼

Yes, structured feedback normalization works for coding agents, chat assistants, office workflows, search, writing, and internal AI systems. It is applicable whenever you need to collect, triage, and template problems encountered while using AI tools or AI-assisted workflows.

Why should I enforce unknown defaults when collecting AI issue reports?▼

You should enforce unknown defaults when collecting AI issue reports to avoid speculation when information is missing. This approach maintains strict fact vs. inference separation, ensuring the structured feedback remains objective, preventing overreach, and keeping the triage data accurate for downstream statistics.

Related Skills

Explore More Product & Management Skills→
l3ochol3ocho

label-taxonomy

Fetch Gitea organization and repository label taxonomies for issue classification.

Community
Basic
whichguywhichguy

webhook-subscriptions

Subscribe to webhook events and trigger automated Hermes agent runs.

Community
Intermediate
xqinagxqinag

analyze-results

Analyze ML experiment results to compute statistics and generate comparison tables.

Community
Advanced
NITISH-gitbitNITISH-gitbit

outlines

Generate structured JSON, regex, and Pydantic outputs from text using local LLMs.

Community
Advanced