extraction-optimization — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited extraction-optimization (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 mining operations 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 process area, commodity, operational constraint, time period). If no arguments, scan the current project for mine production data, processing plant records, and operational management systems.
============================================================ PHASE 1: OPERATIONS DISCOVERY ============================================================
Identify the mining and processing data landscape:
Step 1.1 -- Production Data Systems
Search for operational data sources:
Step 1.2 -- Mining Operation Profile
Characterize the mining operation:
| Parameter | Value |
|---|---|
| Commodity | [gold, copper, iron ore, coal, nickel, zinc, lithium, etc.] |
| Mining method | [open pit, underground, combined] |
| Ore type | [oxide, sulphide, transitional, mixed] |
| Processing method | [CIL/CIP, flotation, heap leach, HPGR+ball mill, DMS, magnetic separation] |
| Nameplate capacity | [tonnes per annum / tonnes per day] |
| Current throughput | [actual vs. nameplate] |
| Head grade | [current vs. reserve average] |
| Recovery rate | [current vs. design] |
| Strip ratio | [waste:ore for open pit] |
Step 1.3 -- Value Chain Map
Map the mine-to-product value chain:
For each stage: record throughput, operating hours, utilization, and key performance parameters.
Step 1.4 -- Constraint Identification
Identify the current operational bottleneck:
============================================================ PHASE 2: ORE GRADE OPTIMIZATION ============================================================
Optimize grade management from resource to product:
Step 2.1 -- Grade Control Performance
Evaluate grade control effectiveness:
Step 2.2 -- Mine-to-Mill Reconciliation
Assess reconciliation across the value chain:
| Reconciliation Point | Model Grade | Mine Grade | Plant Feed Grade | Variance | Factor |
|---|
Step 2.3 -- Ore Blending Strategy
Evaluate ore blending effectiveness:
Step 2.4 -- Cut-Off Grade Optimization
Assess cut-off grade strategy:
============================================================ PHASE 3: PROCESSING THROUGHPUT OPTIMIZATION ============================================================
Optimize processing plant throughput:
Step 3.1 -- Throughput Analysis
Analyze plant throughput performance:
Step 3.2 -- Comminution Circuit Optimization
Evaluate crushing and grinding performance:
Step 3.3 -- Classification Efficiency
Assess size separation performance:
Step 3.4 -- Plant Availability and Utilization
Analyze processing plant reliability:
============================================================ PHASE 4: RECOVERY RATE OPTIMIZATION ============================================================
Optimize metallurgical recovery:
Step 4.1 -- Recovery Performance Analysis
Analyze recovery data:
Step 4.2 -- Process-Specific Optimization
For the applicable processing method:
Flotation:
Leaching (CIL/CIP/Heap Leach):
Gravity Separation:
Step 4.3 -- Metallurgical Accounting
Evaluate metal accounting integrity:
Step 4.4 -- Tailings and Waste Management
Assess process waste streams:
============================================================ PHASE 5: ENERGY AND WATER OPTIMIZATION ============================================================
Optimize energy and water consumption:
Step 5.1 -- Energy Consumption Analysis
Evaluate energy efficiency:
Step 5.2 -- Energy Optimization Opportunities
Identify energy reduction initiatives:
Step 5.3 -- Water Balance Analysis
Evaluate site water management:
Step 5.4 -- Water Optimization
Identify water reduction opportunities:
============================================================ PHASE 6: REPORT AND OPTIMIZATION ROADMAP ============================================================
Write the complete analysis to docs/extraction-optimization-analysis.md.
Step 6.1 -- Optimization Dashboard
Produce a comprehensive production optimization dashboard:
Step 6.2 -- Improvement Roadmap
Prioritize by production impact and implementation effort:
============================================================ 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/extraction-optimization-analysis.md| Area | Status | Priority |
|---|---|---|
| Ore Grade Management | [Optimized/Improvable/Critical Loss] | [P1/P2/P3] |
| Plant Throughput | [At Capacity/Below Design/Bottlenecked] | [P1/P2/P3] |
| Recovery Rate | [At Design/Below Design/Significant Loss] | [P1/P2/P3] |
| Energy Efficiency | [Benchmark/Above Average/Excessive] | [P1/P2/P3] |
| Water Management | [Efficient/Adequate/Excessive Use] | [P1/P2/P3] |
| Reconciliation | [Aligned/Variance/Systematic Bias] | [P1/P2/P3] |
NEXT STEPS:
/mining-maintenance to correlate equipment availability with throughput performance."/resource-estimation to update resource models with reconciliation feedback."/mining-safety to assess safety implications of proposed process changes."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:
### /extraction-optimization — {{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.