Triage new issues

Skill britt/agent-skills/skills/triage-new-issues

Use when processing new or untriaged GitHub issues - assesses urgency from keyword and label signals, assigns P0-P3 priority, suggests labels and assignees, and flags issues needing escalation or clarificationFrom its SKILL.md

Install

npx -y skills add britt/agent-skills --skill triage-new-issues

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.3 KB, as published. Nobody here has run it

Triage New Issues Skill

Review new or untriaged GitHub issues, assess priority based on urgency signals, suggest labels, and recommend owners.

When to Use

Activate when:

Processing new incoming issues
Reviewing untriaged backlog
Assessing issue priority
Assigning issues to owners

Fetching and Applying Triage

Use the gh CLI (must be installed and authenticated):

# Find untriaged issues
gh issue list --search 'no:label' --json number,title,body,labels

# Apply labels after triage
gh issue edit <n> --add-label <label>

Priority Signals

Critical (P0)

Keywords: "down", "outage", "security", "vulnerability", "production", "urgent", "ASAP", "breach" Labels: critical, security, production Action: Immediate attention required

High (P1)

Keywords: "blocking", "regression", "broken", "can't use", "data loss", "crash" Labels: blocker, regression, priority/high Action: Address this sprint

Medium (P2)

Keywords: "bug", "incorrect", "should", "expected", "wrong" Labels: bug, priority/medium Action: Schedule for upcoming sprint

Low (P3)

Keywords: "nice to have", "minor", "cosmetic", "enhancement", "workaround exists" Labels: enhancement, low-priority Action: Add to backlog

Triage Guidelines

Assessment Process

Read title and full description
Scan for urgency keywords and labels
Check for existing labels that signal priority
Assess impact (how many users affected)
Look for workarounds mentioned
Check if duplicate of existing issue
Determine ownership: check CODEOWNERS, recent git log on affected paths, or past assignees of similar issues — omit the assignee suggestion if none found

When to Escalate

Security vulnerabilities → Flag immediately
Production outages → Notify on-call
Data integrity issues → High priority regardless of other signals

When to Ask Questions

Unclear reproduction steps
Missing environment details
Ambiguous severity ("it's broken" but unclear impact)
No indication of urgency or timeline

Red Flags

Issues with no response from author (>7 days)
Duplicate of closed/wontfix issue
Feature request disguised as bug
Missing required information from template

Output Structure (per issue)

## Triage: #[number] — [title]

### Priority Assessment

**Urgency**: [Critical | High | Medium | Low]
**Impact**: [Wide | Moderate | Limited]
**Recommended Priority**: P[0-3]

| Signal | Indicator |
|--------|-----------|
| [Keyword/label found] | [What it suggests] |

### Classification

**Type**: [Bug | Feature | Question | Task]
**Area**: [Component or area affected]
**Suggested Labels**: `priority/high`, `bug`, `area/auth`
**Suggested Assignee**: @username — based on CODEOWNERS, git history, or similar past issues (omit if no owner found)

### Assessment

[Summary of the issue and reasoning for priority assignment]

### Clarifying Questions (if needed)

- [ ] [Question to understand severity]

### Recommendation

[Immediate action | Next sprint | Backlog | Needs info | Duplicate of #X]