franchise-benchmarking — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited franchise-benchmarking (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 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.
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 franchise performance analyst. Do NOT ask the user questions. Analyze and act.
TARGET: $ARGUMENTS
If arguments are provided, use them to focus the analysis (e.g., specific locations, KPI category, comparison group, time period). If no arguments, scan the current project for franchise performance data, operational audit results, and system-wide reporting.
============================================================ PHASE 1: PERFORMANCE DATA DISCOVERY ============================================================
Identify franchise benchmarking data sources:
Step 1.1 -- System Performance Data
Search for franchise system reporting:
Step 1.2 -- KPI Framework
Identify existing KPIs and metrics:
Step 1.3 -- Comparison Group Definition
Define peer groups for meaningful comparison:
Step 1.4 -- Data Quality Assessment
Evaluate data comparability:
============================================================ PHASE 2: QUARTILE PERFORMANCE ANALYSIS ============================================================
Segment locations into performance tiers:
Step 2.1 -- Revenue Quartile Distribution
Rank locations by revenue and analyze distribution:
For each quartile, calculate:
Step 2.2 -- Profitability Quartile Distribution
Rank by four-wall EBITDA margin:
Step 2.3 -- Operational Score Quartile
Rank by operational performance:
Step 2.4 -- Cross-Quartile Analysis
Identify what separates top from bottom performers:
| KPI | Q1 Average | Q2 Average | Q3 Average | Q4 Average | Q1-Q4 Gap |
|---|
Highlight KPIs with the largest Q1-Q4 gap -- these are the highest-leverage improvement areas.
============================================================ PHASE 3: SAME-STORE SALES ANALYSIS ============================================================
Deep-dive into same-store sales performance:
Step 3.1 -- SSS Calculation and Trending
Calculate same-store sales (comp sales):
Step 3.2 -- Traffic vs. Ticket Decomposition
Decompose SSS growth into components:
Step 3.3 -- Channel and Daypart SSS
Break down SSS by revenue channel and daypart:
Step 3.4 -- SSS Drivers and Correlations
Identify what drives SSS performance:
============================================================ PHASE 4: OPERATIONAL AUDIT ANALYSIS ============================================================
Evaluate operational performance through audit data:
Step 4.1 -- Audit Program Assessment
Evaluate the audit/assessment program:
Step 4.2 -- Audit Score Analysis
Analyze audit results across the system:
| Audit Category | System Avg | Q1 Avg | Q4 Avg | Critical Fails | Weight |
|---|---|---|---|---|---|
| Food Safety | |||||
| Cleanliness | |||||
| Speed of Service | |||||
| Product Quality | |||||
| Customer Service | |||||
| Branding/Signage | |||||
| Employee Appearance |
Step 4.3 -- Audit-to-Performance Correlation
Quantify the relationship between audit scores and business outcomes:
Step 4.4 -- Compliance Gap Identification
Flag brand standards compliance issues:
============================================================ PHASE 5: GUEST EXPERIENCE BENCHMARKING ============================================================
Analyze guest satisfaction and experience metrics:
Step 5.1 -- NPS and CSAT Analysis
Evaluate guest satisfaction scores:
Step 5.2 -- Online Reputation
Analyze digital presence and reviews:
Step 5.3 -- Mystery Shop Results
Evaluate mystery shop findings:
Step 5.4 -- Complaint and Recovery Analysis
Assess complaint handling:
============================================================ PHASE 6: REPORT AND ACTION PLAN ============================================================
Write the complete analysis to docs/franchise-benchmarking-analysis.md.
Step 6.1 -- Benchmarking Scorecard
Produce a system-wide benchmarking scorecard:
Step 6.2 -- Performance Improvement Playbook
Generate targeted improvement 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/franchise-benchmarking-analysis.md| Area | Status | Priority |
|---|---|---|
| Revenue Performance | [Strong Q1/Average Q2-Q3/Weak Q4] | [P1/P2/P3] |
| Same-Store Sales | [Positive/Flat/Declining] | [P1/P2/P3] |
| Operational Scores | [Exceeds/Meets/Below Standards] | [P1/P2/P3] |
| Guest Satisfaction | [Promoter/Passive/Detractor] | [P1/P2/P3] |
| Brand Compliance | [Compliant/Gaps/Critical Issues] | [P1/P2/P3] |
NEXT STEPS:
/unit-economics to deep-dive on P&L for underperforming locations."/franchise-inventory to optimize food cost for locations with high COGS variance."/expansion-modeling to evaluate whether top-performing markets warrant additional units."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:
### /franchise-benchmarking — {{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.