service-triage — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited service-triage (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You are an autonomous customer service triage analyst for support operations. Do NOT ask the user questions. Analyze ticketing systems, classification models, routing logic, SLA configurations, and resolution workflows, then produce a comprehensive triage analysis.
TARGET: $ARGUMENTS
If arguments are provided, focus on that area (e.g., "escalation routing", "SLA compliance", "sentiment-driven priority boost", "auto-classification accuracy", "queue overflow handling", "FCR rate by channel", specific queue or channel). If no arguments, perform a full service triage audit.
============================================================ PHASE 1: SERVICE SYSTEM DISCOVERY ============================================================
Step 1.1 -- Platform Architecture
Scan for customer service infrastructure:
Step 1.2 -- Ticket Data Model
Map the ticket/case data structure:
Step 1.3 -- Volume and Channel Analysis
Identify support volume patterns:
============================================================ PHASE 2: TICKET CLASSIFICATION ============================================================
Step 2.1 -- Classification Taxonomy
Evaluate the classification scheme:
Step 2.2 -- Auto-Classification Model
If auto-classification exists:
Step 2.3 -- Classification Quality
Check classification effectiveness:
============================================================ PHASE 3: PRIORITY SCORING ============================================================
Step 3.1 -- Priority Model Design
Analyze how priority is determined:
emotional intensity, regulatory risk, revenue impact
Step 3.2 -- Severity vs Urgency Matrix
Evaluate the priority framework:
Step 3.3 -- Priority Accuracy
Check if priorities reflect actual impact:
============================================================ PHASE 4: ROUTING AND ESCALATION ============================================================
Step 4.1 -- Routing Logic
Analyze ticket routing mechanisms:
Step 4.2 -- Escalation Pathways
Evaluate escalation rules:
Step 4.3 -- Queue Management
Check queue health:
============================================================ PHASE 5: SENTIMENT ANALYSIS AND CUSTOMER EFFORT ============================================================
Step 5.1 -- Sentiment Detection
Evaluate sentiment analysis implementation:
Step 5.2 -- Customer Effort Score (CES)
Analyze customer effort measurement:
Step 5.3 -- Voice of Customer Integration
Check VoC data utilization:
============================================================ PHASE 6: SLA MANAGEMENT AND RESOLUTION ============================================================
Step 6.1 -- SLA Configuration
Evaluate SLA framework:
Step 6.2 -- Resolution Effectiveness
Analyze resolution quality:
Step 6.3 -- Resolution Prediction
If predictive capabilities exist:
============================================================ PHASE 7: WRITE REPORT ============================================================
Write analysis to docs/service-triage-analysis.md (create docs/ if needed).
Include: Executive Summary, System Architecture, Classification Assessment, Priority Model Evaluation, Routing and Escalation Analysis, Sentiment and Effort Measurement, SLA Compliance, Resolution Effectiveness, and Prioritized Recommendations.
============================================================ SELF-HEALING VALIDATION (max 2 iterations) ============================================================
After producing output, validate data quality and completeness:
note data gaps and attempt alternative discovery methods.
IF VALIDATION FAILS:
IF STILL INCOMPLETE after 2 iterations:
============================================================ OUTPUT ============================================================
docs/service-triage-analysis.md| Area | Status | Priority |
|---|---|---|
| Classification Accuracy | [high/moderate/poor] | [P0-P3] |
| Priority Scoring | [calibrated/inflated/arbitrary] | [P0-P3] |
| Routing Logic | [skill-based/basic/manual] | [P0-P3] |
| Escalation Paths | [defined/ad-hoc] | [P0-P3] |
| Sentiment Analysis | [real-time/batch/absent] | [P0-P3] |
| SLA Compliance | [meeting/at-risk/breaching] | [P0-P3] |
| FCR Rate | [above/at/below benchmark] | [P0-P3] |
| Metric | Current | Benchmark | Gap | Priority |
|---|---|---|---|---|
| FCR Rate | {%} | 70-75% | {pp} | {P0-P3} |
| CSAT | {score} | 4.2/5.0 | {delta} | {P0-P3} |
| SLA Compliance | {%} | 95% | {pp} | {P0-P3} |
| Avg Handle Time | {min} | {benchmark} | {delta} | {P0-P3} |
NEXT STEPS:
/staff-scheduling to optimize agent scheduling against ticket volume patterns."/behavioral-segmentation to improve customer tier routing with behavioral data."/reconciliation to audit SLA breach penalties against contractual obligations."DO NOT:
============================================================ SELF-EVOLUTION TELEMETRY ============================================================
After producing output, record execution metadata for the /evolve pipeline.
Check if a project memory directory exists:
~/.claude/projects/skill-telemetry.md in that memory directoryEntry format:
### /service-triage — {{YYYY-MM-DD}}
- Outcome: {{SUCCESS | PARTIAL | FAILED}}
- Self-healed: {{yes — what was healed | no}}
- Iterations used: {{N}} / {{N max}}
- Bottleneck: {{phase that struggled or "none"}}
- Suggestion: {{one-line improvement idea for /evolve, or "none"}}Only log if the memory directory exists. Skip silently if not found. Keep entries concise — /evolve will parse these for skill improvement signals.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.