report-issue

Classify researcher feedback and generate diagnostic issue reports.

Updated Apr 10, 2026
One-click install
npx skills add https://github.com/phdemotions/faculty-meeting --skill report-issue-phdemotions
Or copy as Structured Prompt for Agentโ–ผ
Please help me install this Agent Skill.
Skill: report-issue
Source: https://github.com/phdemotions/faculty-meeting/tree/main/skills/meta/report-issue
Command: npx skills add https://github.com/phdemotions/faculty-meeting --skill report-issue-phdemotions

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill captures a researcher's reaction when an advisor's response "felt off", clarifies the complaint in one brief exchange, classifies the failure mode, and produces a privacy-safe, diagnostic-quality issue report that maintainers can act on without exposing the researcher's work.

Core Features & Use Cases

  • Conversational Clarification: Warmly acknowledge the user's reaction and ask at most one follow-up question to clarify tone, substance, or accuracy problems.
  • Issue Classification: Internally classify failures into types such as voice, accuracy, blind-spots, caricature, disagreement, coverage, wrong-lens, or other and assign severity levels.
  • Diagnostic Report Builder: Construct a reproducible, privacy-preserving issue body with Persona, Issue Type, Mode, a generic Question Type, failure description, recommended fixes, and an anonymous researcher ID.
  • Submission & Fallbacks: Attempt direct submission to an HTTP feedback endpoint, fall back to the GitHub CLI if available, and save to a local pending queue as a last resort.
  • Use Case: A researcher says "that advice sounded generic" and the Skill confirms once, diagnoses which persona commitments failed, files a ticket for maintainers, and confirms completion to the user.

Quick Start

Say that an advisor's response "felt off" and briefly describe what was wrong so the assistant can file privacy-safe diagnostic feedback.

Frequently Asked Questions about report-issue

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

FAQPage Schema
How do I file diagnostic feedback about an advisor persona without exposing my research?โ–ผ

To file diagnostic feedback without exposing research, describe what felt off about the advisor's response. The Skill clarifies the issue in one exchange, classifies the failure mode, and generates a privacy-safe issue report with an anonymous researcher ID for submission.

What types of advisor persona failures can be classified in an issue report?โ–ผ

Advisor persona failures classified in an issue report include voice, accuracy, blind-spots, caricature, disagreement, coverage, and wrong-lens. The Skill assigns severity levels to these failure modes to help maintainers diagnose and address the specific persona commitments that failed.

How does anonymous issue triage work for faculty meeting panels?โ–ผ

Anonymous issue triage for faculty meeting panels works by applying failure classification to multi-advisor interactions. The Skill generates a privacy-preserving issue body containing the Persona, Issue Type, Mode, and a generic Question Type, linking the report to an anonymous researcher ID stored locally.

What happens if the HTTP feedback endpoint is unavailable when submitting an issue triage report?โ–ผ

If the HTTP feedback endpoint is unavailable when submitting an issue triage report, the Skill falls back to the GitHub CLI. If the GitHub CLI is also unavailable, it saves the diagnostic issue body to a local pending queue as a last resort fallback.

Do I need the GitHub CLI installed to submit diagnostic feedback?โ–ผ

You do not need the GitHub CLI installed to submit diagnostic feedback. The Skill first attempts direct submission via an HTTP feedback endpoint, only falling back to the GitHub CLI if the endpoint fails, and finally using a local pending queue if neither is available.

How to report a generic or inaccurate advisor response as a reproducible issue?โ–ผ

To report a generic or inaccurate advisor response, state that the advice felt off and briefly describe the problem. The Skill asks one clarifying question, diagnoses the persona failure, and builds a reproducible issue body with recommended fixes for maintainers to act on.