quay/ai-helpers/assess
- community
Checking that the SKILL.md file is still in the repository.
Understand a Quay bug report from JIRA or GitHub. Fetches ticket details, checks for existing work, classifies as UI vs backend, and proposes an investigation plan. No code changes.
Install
npx vskill@latest install quay/ai-helpers/assessSKILL.md
Assess Bug Report
Understand the bug before taking any action. This phase produces an assessment report — no code execution, no project code modifications (writing assessment artifacts and cloning repositories is allowed).
Your Role
Read the bug report, present your understanding back to the user, identify gaps, and propose a plan. Let the user correct you before you invest effort in the wrong direction.
Critical Rules
- Do not start reproducing, diagnosing, or fixing. Analysis and planning only.
- Do not run the project's code or tests. You may read code, but do not
execute it yet.
- Be honest about uncertainty. If the report is vague, say so.
Process
Step 1: Gather the Bug Report
Accept either a JIRA ticket key, a GitHub issue URL, or a free-text description from the user.
For JIRA tickets:
Extract: summary, description, type, component, priority, labels, comments, reporter, attachments.
For GitHub issues:
For free-text descriptions: Use the conversation context directly.
Step 2: Ensure the Repository Is Available
If the project repo is present (e.g., /workspace/repos/quay/), note its path. If not, clone it:
Read referenced files or code paths to inform the assessment. This is read-only exploration.
Step 3: Check for Existing Work
Search for PRs or related issues that may already address this bug:
If an open PR appears to directly address this bug, stop and use `AskUserQuestion` before continuing. Present options:
- "PR #N appears to address this bug — review it instead of starting fresh"
- "PR #N is related but doesn't fully cover it — continue with assessment"
- "Not sure if PR #N is relevant — continue with assessment"
Do not continue until the user responds.
Step 4: Check Backport Requirement
If Target Version is set, note that backporting will be required after merge.
Step 5: Classify the Bug
Determine whether this is a UI bug or Backend bug:
UI indicators: component is ui or web; keywords like rendering, display, button, form, modal, PatternFly, React; screenshot attachments.
Backend indicators: component is api, data, auth, workers, storage, buildman; keywords like endpoint, database, migration, worker, ORM; log file or stack trace attachments.
Step 6: Summarize Understanding
Present to the user:
- What the bug is: One or two sentences describing the problem
- Where it occurs: Which Quay subsystem is affected (use the subsystem
map from CLAUDE.md)
- Severity/impact: Based on JIRA priority and your assessment
- Available information: What the report provides
- Gaps: What's missing or unclear
- Assumptions: Any assumptions you're making
Step 7: Propose Investigation Plan
Based on your understanding, outline:
- What environment or setup is needed for reproduction
- What specific steps you would follow
- What you would look for to confirm the bug exists
- Which Quay subsystems to investigate during diagnosis
Step 8: Write Assessment Artifact
Save to artifacts/quay-bugfix/reports/assessment.md:
Confidence Assessment
Include this section at the end of your assessment artifact:
Confidence signals for this phase:
- High: Clear bug report with reproduction steps, single component identified, good logs/traces available
- Medium: Bug report has some details but missing reproduction steps or unclear component
- Low: Vague report, multiple possible components, missing critical details, no reproduction steps
Output
- Assessment presented directly to the user (inline)
- Assessment saved to
artifacts/quay-bugfix/reports/assessment.md - No project code is modified (only assessment artifacts are written)
When This Phase Is Done
Report your assessment: understanding, gaps, plan, and backport status.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingworkflows/quay-bugfix/.claude/skills/assess/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/quay/ai-helpers/assess)