mikeparcewski/maturity-model
skills/agentic/maturity-model/SKILL.md
Five-level maturity assessment model for agentic systems from prototype to optimized production. Use when: "agent maturity", "production readiness", "how mature is my agent", "agent assessment"
$ install --global
skillsauthnpx skillsauth add mikeparcewski/wicked-garden maturity-modelInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 5:58 AM7.4s4 files scanned
SKILL.md
- name:
- maturity-model
- description:
- |
- Use when:
- agent maturity", "production readiness", "how mature is my agent", "agent assessment
- portability:
- portable
Agentic System Maturity Model
Framework for assessing and advancing the maturity of agentic systems across five levels.
The Five Levels
Level 0: Prototype
Definition: Proof of concept, demonstrates core functionality.
Characteristics:
- Single agent or simple multi-agent setup
- Hardcoded prompts and logic
- No error handling
- No observability
- No safety guardrails
- Works in happy path only
Appropriate for: Experiments, demos, early exploration
Level 1: Functional
Definition: Works reliably for basic scenarios, handles common errors.
Characteristics:
- Multiple specialized agents
- Basic error handling (try/catch)
- Simple logging
- Timeout mechanisms
- Manual testing only
- Configuration externalized
Appropriate for: Internal tools, limited user testing
Level 2: Reliable
Definition: Production-ready for limited scale, monitored and tested.
Characteristics:
- Comprehensive error handling
- Structured logging and basic tracing
- Automated testing (unit + integration)
- Human-in-the-loop for high-stakes actions
- Basic safety guardrails
- Incident response process
Appropriate for: Production with limited users, internal production use
Level 3: Production
Definition: Scaled production system, handles load and failures gracefully.
Characteristics:
- Scales horizontally
- Advanced observability (logs, metrics, traces)
- Comprehensive safety system
- Automated testing and deployment
- SLOs and SLA tracking
- Cost monitoring and optimization
Appropriate for: Large-scale production, external users
Level 4: Optimized
Definition: Continuously improving, data-driven optimization.
Characteristics:
- A/B testing of prompts and strategies
- Automated performance optimization
- Self-healing capabilities
- Advanced cost optimization
- Real-time quality monitoring
- Feedback loops for improvement
Appropriate for: Mature, business-critical systems
Maturity Dimensions
Assess maturity across these dimensions:
1. Reliability
- L0: Works sometimes
- L1: Works for common cases
- L2: Handles errors gracefully
- L3: Self-recovers from failures
- L4: Predicts and prevents failures
2. Observability
- L0: No logging
- L1: Print statements
- L2: Structured logs + basic metrics
- L3: Distributed tracing + dashboards
- L4: Real-time analytics + predictive monitoring
3. Safety
- L0: No guardrails
- L1: Basic input validation
- L2: Human-in-the-loop for risky actions
- L3: Comprehensive safety system
- L4: ML-powered anomaly detection
4. Testing
- L0: Manual only
- L1: Some unit tests
- L2: Automated test suite (70%+ coverage)
- L3: Integration + e2e + load testing
- L4: Continuous testing + mutation testing
5. Scalability
- L0: Single instance
- L1: Handles 10s of requests
- L2: Handles 100s of requests
- L3: Handles 1000s of requests
- L4: Auto-scales based on load
6. Cost
- L0: No tracking
- L1: Manual tracking
- L2: Automated tracking
- L3: Per-request cost monitoring
- L4: Automated optimization
Quick Self-Assessment
Rate your system (0-4) on each dimension:
Reliability: [ ]
Observability: [ ]
Safety: [ ]
Testing: [ ]
Scalability: [ ]
Cost: [ ]
Average Score: [ ]
Overall Maturity Level:
- Average 0-0.5: Level 0 (Prototype)
- Average 0.5-1.5: Level 1 (Functional)
- Average 1.5-2.5: Level 2 (Reliable)
- Average 2.5-3.5: Level 3 (Production)
- Average 3.5-4.0: Level 4 (Optimized)
Anti-Patterns by Level
L0-L1 Mistakes:
- Deploying prototype to production
- No error handling
- Hardcoded secrets
L1-L2 Mistakes:
- No testing before production
- Print statements in production
- No monitoring
L2-L3 Mistakes:
- Single instance in production
- No cost tracking
- Manual deployments at scale
L3-L4 Mistakes:
- Not investing in automation
- Ignoring user feedback
- No continuous improvement culture
References
refs/assessment-rubric-dimensions.md- Scoring rubric for dimensions 1-4 (Reliability, Observability, Safety, Testing) with scoring template and prioritizationrefs/assessment-rubric-dimensions5-8.md- Scoring rubric for dimensions 5-8 (Scalability, Cost, Development Velocity, Documentation) with example assessmentrefs/assessment-checklists-progression.md- Must-have checklists, exit criteria, and progression guidance by level
Related Skills
mikeparcewski/wicked-garden-engineering-conformance-reviewer
development
VerifiedTrustedCommunity
Pattern-conformance agent-half: evaluates a produced artifact or diff against a set of architectural/design pattern rules from the conformance-rule store (wicked_governance schema). Returns structured findings with rule ID, severity, and rationale — the deterministic half (mechanical rule recall) is done by the guard pipeline; this is the semantic evaluation step. Triggered by: the guard_pipeline `outgov_pattern` check (session-close), or explicitly by an engineering review when WICKED_OUTGOV_RULES_DIR is populated. NOT a replacement for the full `engineering` review skill — focuses only on conformance to stored Pattern rules; architecture and code-quality checks live in the `engineering` skill. Semantic evaluation reuses `wicked-garden-qe-semantic-reviewer` as the designated agent-half evaluator (per garden#983 spec). This skill is the orchestrating wrapper that loads applicable Pattern rules and delegates the per-rule semantic judgment to qe-semantic-reviewer.
8SKILL.mdUpdated Jul 22, 2026
mikeparcewski/wicked-garden-domain
tools
VerifiedTrustedCommunity
The FOUNDATIONAL domain-model capability: extract a codebase's domain — testable business rules (with confidence + provenance), entities, requirements — as a schema-conformant model on the estate graph. The workers annotate the store; wicked-core reads it and builds the requirements graph, coverage-gating fail-closed. Steers three fork workers. A shared substrate, not a modernization tool. The `modernize` archetype DERIVES from it; build / migrate / review / specify / explore consume the SAME domain model — none OWN it. Understanding a codebase's domain is upstream of almost everything else garden does. Use when: "extract the business rules / domain model from this codebase", "build a requirements graph from the code", "what does this system actually require", "reverse-engineer the domain before we build/port/migrate". Works on ANY codebase (modern or legacy) — the value is the domain model, not the porting. NOT the code transform itself (that is the archetype consuming this model). This skill produces the DOMAIN MODEL, not new code.
8SKILL.mdUpdated Jul 15, 2026
mikeparcewski/wicked-garden-domain-modeler
development
VerifiedTrustedCommunity
Domain-graph fork worker for the modernize archetype. Groups the estate's Louvain communities into business domains, attaches each requirement to its cluster (advisory cluster_id provenance), and invokes wicked-core's domain-graph build (which reads the annotated estate store, recomputes coverage fail-closed, and builds the requirements graph) — then validates core's output against the vendored schema. Use when: dispatched by wicked-garden-domain after rule extraction to turn a flat rule set into cluster-keyed domains; "group these into domains", "build the requirements graph", "translate clusters into a domain model". NOT for mining the rules themselves (that is domain-extractor) or threat-modeling (that is domain-coverage).
8SKILL.mdUpdated Jul 15, 2026
mikeparcewski/wicked-garden-domain-extractor
tools
VerifiedTrustedCommunity
Rule-extraction fork worker for the FOUNDATIONAL domain-model capability. Mines testable business rules from a codebase — each with a numeric confidence and a provenance{source, ref, source_kinds} — and annotates them into the estate store so wicked-core can build the domain-model requirements graph (coverage-gated). This is a substrate, not a modernization tool: the `modernize` archetype DERIVES from it, and build / migrate / review / specify / explore can consume the same domain model — none OWN it. Use when: dispatched by wicked-garden-domain to mine the business_rules of a codebase (or a module); "extract the domain rules", "what does this system require", building the requirements half of a domain model. NOT for grouping into domains (that is domain-modeler) or judging coverage (that is domain-coverage — a seat-distinct evaluator).
8SKILL.mdUpdated Jul 15, 2026