triage-display
Internal process for the triage-summarizer agent. Defines the step-by-step procedure for formatting triage results as terminal markdown and parsing review commands. Not user-invocable — loaded by the agent via its `skills: ["triage-display"]` frontmatter property.
Allowed Tools
No tools specified
Provided by Plugin
x-bug-triage-plugin
Closed-loop bug triage: X complaints → clusters → repo evidence → owner routing → terminal review → filed issues
Installation
This skill is included in the x-bug-triage-plugin plugin:
/plugin install x-bug-triage-plugin@claude-code-plugins-plus
Click to copy
Instructions
Triage Display Process
Step-by-step procedure for formatting triage results as terminal-ready markdown and handling interactive review command parsing.
Instructions
Step 1: Render Summary
Produce the initial triage summary as terminal markdown:
X Bug Triage — Run {date} {time} UTC
Account: @{account} · Window: last {window} · {count} posts ({unique} unique, {dedup_groups} duplicate groups)
⚠ Data quality: {warning} ← show ONLY when date_confidence is low or medium
--- Sources --- ← show ALWAYS between header and clusters
{source_name} {status} {count} posts (rate limit: {remaining}/{limit})
...
--- {n} clusters ({new} new, {existing} existing) ---
{icon} {#} · {bug_signature}
{report_count} reports · {severity} severity · {status_note}
Owner: {team}
Evidence: {t1} Tier 1, {t2} Tier 2, {t3} Tier 3, {t4} Tier 4 · Top: {description}
--- Commands ---
details <#> · file <#> · dismiss <#> · merge <#> <issue>
escalate <#> · monitor <#> · snooze <#> <duration>
split <#> · reroute <#> · full-report
Step 2: Render Detail View (for details command)
When showing a single cluster in detail:
- Family, surface, feature area
- Report count, confidence percentage
- Severity + rationale (always show rationale for high/critical)
- Status and time range (firstseen to lastseen)
- Evidence summary line:
"Evidence: {t1} Tier 1, {t2} Tier 2, {t3} Tier 3, {t4} Tier 4"(omit tiers with 0 count) - Evidence listed by tier (all tiers, highest first)
- 3 representative posts (highest quality, most distinct, most recent) — truncate at 100 chars
- Routing with ranked assignees and confidence percentages
Step 3: Parse Review Commands
When receiving a command string, call mcptriageparsereviewcommand:
- Returns structured ParsedCommand with command, clusterNumber, args, valid, error
- If invalid: display the error message to the user
- If valid: return the parsed command to the orchestrator for execution
Step 4: Render Action Confirmation
After each successfully executed review command, display a confirmation line using formatActionConfirmation() from mcp/triage-server/lib.ts. Examples:
dismiss 1 noise→"Cluster #1 dismissed (noise). Suppression rule created."file 2→"Draft issue created for cluster #2. Use "confirm file 2" to submit."escalate 3→"Cluster #3 escalated. Severity raised."
Formatting Rules
- Severity icons: redcircle = critical/high, yellowcircle = medium, green_circle = low
- Cluster cap: Show top 5 by severity. If >5, append "{N} more — type
full-report" - Line budget: Max 20 lines for <=5 clusters in summary view
- Post truncation: Representative posts capped at 100 chars with "..." suffix
- Large clusters: >50 reports — show count + top 3 posts only
- Evidence display: Summary shows per-tier counts + top evidence description. Detail shows per-tier counts + full evidence list, ranked. Omit tiers with 0 count from the summary line.
- Routing display: Summary shows team name only. Detail shows ranked assignees with source and confidence.
References
Load override and memory policy for review command processing:
!cat skills/x-bug-triage/references/review-memory-policy.md