wicked-garden-agentic-review-methodology
Skill9 starsChanged 7 months agoMITView on GitHub
Use when reviewing an agentic codebase for issues, risks, and maturity gaps — covers the four-phase review process (Detect → Analyze → Prioritize → Report) and the five-level maturity model (Prototype → Functional → Reliable → Production → Optimized) for assessing production readiness. NOT for architecture design (use agentic-patterns) or a live agentic review (the `wicked-garden-agentic` skill's `review` action).
In this repository142 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- plugin-json-schemaSkill
- readme-style-guideSkill
- releaseSkill
- scaffoldSkill
- wicked-garden-agentic-agentic-patternsSkill
- wicked-garden-agentic-architectSkill
- wicked-garden-agentic-context-engineeringSkill
- wicked-garden-agentic-frameworksSkill
- wicked-garden-agentic-performance-analystSkill
- wicked-garden-agentic-safety-reviewerSkill
- wicked-garden-agenticSkill
- wicked-garden-agentic-trust-and-safetySkill
- wicked-garden-appsSkill
- wicked-garden-archetypeSkill
- wicked-garden-build-guideSkill
- wicked-garden-classifySkill
- wicked-garden-coreSkill
- wicked-garden-data-engineerSkill
- wicked-garden-dataSkill
- wicked-garden-deliberateSkill
- wicked-garden-demoSkill
- wicked-garden-domain-coverageSkill
- wicked-garden-domain-extractorSkill
- wicked-garden-domain-modelerSkill
- wicked-garden-domainSkill
- wicked-garden-draftSkill
- wicked-garden-editor-scaffoldSkill
- wicked-garden-engineering-api-documentarianSkill
- wicked-garden-engineering-architectureSkill
- wicked-garden-engineering-backendSkill
- wicked-garden-engineering-debuggingSkill
- wicked-garden-engineering-docsSkill
- wicked-garden-engineering-frontendSkill
- wicked-garden-engineering-integrationSkill
- wicked-garden-engineering-large-scale-migrationSkill
- wicked-garden-engineering-migration-engineerSkill
- wicked-garden-engineering-patchSkill
- wicked-garden-engineeringSkill
- wicked-garden-engineering-solution-architectSkill
- wicked-garden-engineering-system-designSkill
- wicked-garden-engineering-unit-test-qualitySkill
- wicked-garden-governed-workerSkill
- wicked-garden-groundSkill
- wicked-garden-jam-brainstorm-facilitatorSkill
- wicked-garden-jam-councilSkill
- wicked-garden-jamSkill
- wicked-garden-learnSkill
- wicked-garden-mcp-scaffoldSkill
- wicked-garden-mcpSkill
- wicked-garden-mem-captureSkill
- wicked-garden-mem-ingestSkill
- wicked-garden-memSkill
- wicked-garden-personaSkill
- wicked-garden-platform-auditSkill
- wicked-garden-platform-compliance-officerSkill
- wicked-garden-platform-complianceSkill
- wicked-garden-platform-errorsSkill
- wicked-garden-platform-gate-benchmark-rebaselineSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 113
No input validation (SQL injection risk)
- Distinctive: line 115
No error handling (system crashes)
- Distinctive: line 120
No circuit breakers (cascading failures)
- Distinctive: line 122
No resource limits (runaway costs)
- Distinctive: line 124
No testing (high bug risk)
- Distinctive: line 129
No caching (higher costs)
- Distinctive: line 177
Be Systematic: Follow all four phases
- Distinctive: line 181
Be Prioritized: Don't overwhelm with low-priority issues
- Distinctive: line 182
Be Clear: Use simple language in reports
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Agentic Review Methodology
Systematic approach to reviewing agentic systems and codebases for issues, risks, and improvement opportunities.
Four-Phase Review Process
Phase 1: Detect (Discovery)
Goal: Identify all potential issues
Activities:
- Code analysis (static analysis, anti-patterns)
- Configuration review (prompts, secrets, limits)
- Runtime analysis (logs, traces, metrics)
- Documentation review
Tools:
- Static analyzers (pylint, mypy, eslint)
- Custom grep patterns for agentic anti-patterns
- Log aggregation tools
Deliverable: Raw issue inventory
Phase 2: Analyze (Assessment)
Goal: Understand each issue's impact and root cause
For Each Issue:
- Classify type (see
refs/issue-taxonomy-reliability-safety.mdandrefs/issue-taxonomy-quality-testing.md) - Determine severity (Critical/High/Medium/Low)
- Assess impact (Reliability/Security/Cost/Performance)
- Identify root cause
- Estimate fix effort
Analysis Framework:
- What is the issue?
- Why is it a problem?
- What are the consequences?
- What is the root cause?
- How should it be fixed?
Deliverable: Analyzed issue list with severity and impact
Phase 3: Score (Prioritization)
Goal: Prioritize issues for remediation
Severity Levels:
Critical (P0): Security vulnerabilities, data loss risks, system crashes, compliance violations. Fix immediately.
High (P1): Reliability issues, performance problems, cost inefficiencies, safety gaps. Fix within 1 week.
Medium (P2): Code quality issues, minor performance issues, missing observability. Fix within 1 month.
Low (P3): Style issues, optimization opportunities, nice-to-have features. Backlog.
Prioritization Matrix:
Impact vs Effort:
Low Effort High Effort
High Quick Wins Major Projects
Impact (Do First) (Plan)
Low Easy Wins Avoid
Impact (Do Later) (Skip)Deliverable: Prioritized roadmap
Phase 4: Report (Communication)
Goal: Communicate findings effectively to stakeholders
Report Components:
- Executive Summary (1 page) - Overall assessment and top recommendations
- Issue Inventory (Detailed) - All issues with severity and recommendations
- Remediation Roadmap - Phased approach with quick wins
- Metrics Dashboard - Issue counts and maturity score
Deliverable: Comprehensive review report
See refs/deliverable-templates.md for complete templates.
Issue Severity Classification
Determining Severity
- Can it cause data loss? → Critical
- Can it cause security breach? → Critical
- Does it crash the system? → Critical/High
- Does it violate compliance? → Critical
- Does it affect reliability? → High/Medium
- Does it waste money? → High/Medium
- Is it a code quality issue? → Medium/Low
Examples by Severity
Critical:
- No input validation (SQL injection risk)
- Credentials in code
- No error handling (system crashes)
- Production deletes without approval
- Missing audit logs for compliance
High:
- No circuit breakers (cascading failures)
- Missing observability (can't debug)
- No resource limits (runaway costs)
- Hardcoded prompts (can't iterate)
- No testing (high bug risk)
Medium:
- Inefficient token usage
- Missing documentation
- No caching (higher costs)
- Verbose logging
- Code duplication
Low:
- Style inconsistencies
- Missing type hints
- Suboptimal variable names
- Minor optimizations
See refs/issue-taxonomy-reliability-safety.md and refs/issue-taxonomy-quality-testing.md for complete classification guide.
Finding Documentation Template
For each issue, document:
## Issue: [Short Title]
**ID:** ISSUE-001
**Severity:** Critical | High | Medium | Low
**Category:** Reliability | Security | Safety | Cost | Performance | Quality
**Component:** [Which agent/module]
### Description
[What is the issue?]
### Evidence
[Code snippets, logs, metrics]
### Impact
[What are the consequences?]
### Root Cause
[Why does this exist?]
### Recommendation
[How to fix it?]
### Effort Estimate
[Hours/Days/Weeks]
### Priority
[P0/P1/P2/P3]Tips for Effective Reviews
- Be Systematic: Follow all four phases
- Be Objective: Focus on facts, not opinions
- Be Specific: Provide code examples and evidence
- Be Constructive: Suggest solutions, not just problems
- Be Prioritized: Don't overwhelm with low-priority issues
- Be Clear: Use simple language in reports
References
refs/issue-taxonomy-reliability-safety.mdandrefs/issue-taxonomy-quality-testing.md- Complete issue category reference and anti-pattern detectionrefs/deliverable-templates.md- Detailed report templates and review checklist
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

