CLAUDE.md — Skill 266: game-account-phishing-protection

Skill Identity

• Skill Name: game-account-phishing-protection
• Tagline: Game Account Security Against Phishing & Social Engineering — Production-grade harness with flexible agent architecture, comprehensive monitoring, and token optimization.
• Current Phase: Phase 6 — Architecture Upgrade (PRODUCTION READY v2.0.0)
• Version: 3.0.0
• Folder: D:\972026\266-game-account-phishing-protection\

Problem This Skill Solves

This skill provides a structured, evidence-backed analytical workflow for Game Account Security & Anti-Phishing. It gathers authoritative real-time and reference data, applies recognized domain methods, cross-references academic research, and delivers actionable outputs that are fully evidenced, risk/limitation-disclosed, and traceable to authoritative sources — continuously self-improving through an automated knowledge crawl pipeline.

Harness Flow Summary

/game-account-phishing-protection invoked
│
├─ Step 1: sub-gather-requirements   → Clarify the object of analysis, constraints, timeframe, available inputs, target audience, and language before any data fetching.
├─ Step 2: sub-evidence-collector   → Fetch authoritative real-time and reference data for the object: current status/parameters, authoritative documents/standards, and recent developments from domain and academic sources.
├─ Step 3: sub-core-analysis   → Advise gamers on protecting accounts from phishing & social engineering via MFA, credential hygiene, recovery hardening, and behavioral training.
├─ Step 4: sub-knowledge-updater   → Query SECOND-KNOWLEDGE-BRAIN.md for authoritative academic and professional evidence; surface citations with tier labels and flag gaps for the crawl pipeline.
├─ Step 5: sub-advisor   → Synthesize all prior analysis into a risk-disclosed conclusion with a full evidence chain and recommended actions.
└─ Step 6: main (quality gate)       → verify evidence hierarchy, disclosure, output polish

Sub-Skills

| skills/sub-gather-requirements.md | Clarify the object of analysis, constraints, timeframe, available inputs, target audience, and language before any data fetching. | | skills/sub-evidence-collector.md | Fetch authoritative real-time and reference data for the object: current status/parameters, authoritative documents/standards, and recent developments from domain and academic sources. | | skills/sub-core-analysis.md | Advise gamers on protecting accounts from phishing & social engineering via MFA, credential hygiene, recovery hardening, and behavioral training. | | skills/sub-knowledge-updater.md | Query SECOND-KNOWLEDGE-BRAIN.md for authoritative academic and professional evidence; surface citations with tier labels and flag gaps for the crawl pipeline. | | skills/sub-advisor.md | Synthesize all prior analysis into a risk-disclosed conclusion with a full evidence chain and recommended actions. |

Tools Required

• WebSearch — live domain news, reports, standards updates
• WebFetch — scrape Game Account Security & Anti-Phishing authoritative sources
• Read / Write — read SECOND-KNOWLEDGE-BRAIN.md; append knowledge entries
• Bash — run tools/knowledge_updater.py for periodic crawl
• Skill — invoke sub-skills sequentially through the harness

Knowledge Sources

Domain Authoritative Sources

• Authenticator/2FA references (TOTP, FIDO2)
• NIST 800-63B digital identity
• Anti-phishing references (APWG)
• Game platform security docs (Steam Guard, Battle.net)
• Credential-stuffing/breach references
• HaveIBeenPwned

Academic & Research Sources

• Computers & Security — Elsevier
• IEEE Transactions on Information Forensics and Security
• Journal of Cybersecurity — Oxford
• ACM Transactions on Privacy and Security
• Computers in Human Behavior — Elsevier
• Electronic Commerce Research — Springer

Academic Crawl Targets

• Semantic Scholar / Google Scholar for "Game Account Security & Anti-Phishing" keyword clusters
• Domain preprint servers where applicable
• Standards bodies and professional associations (see data sources)

Supporting Python Tools

Automated Knowledge Update Schedule

# Weekly academic update (Mondays 8:00 AM)
0 8 * * 1 python D:/972026/266-game-account-phishing-protection/tools/knowledge_updater.py >> logs/knowledge_update.log 2>&1

# Daily news update (Daily 7:00 AM)
0 7 * * * python D:/972026/266-game-account-phishing-protection/tools/knowledge_updater.py --news-only >> logs/knowledge_news.log 2>&1

Manual: python tools/knowledge_updater.py --dry-run | --keywords "..." | --news-only

Active Development Tasks

• Phase 0: Architecture & source map (this file, PROJECT-detail.md, PDPT.md)
• Phase 1: Core sub-skills (production-grade)
• Phase 2: Main harness + quality gates + degradation
• Phase 3: Knowledge pipeline + tests + cron
• Phase 4: Testing & validation (all validators pass)
• Phase 5: Integration & polish (PRODUCTION READY v1.0.0)
• Phase 6: Architecture upgrade to v2.0.0 (flexible agent architecture, monitoring, hooks, tools, token optimization)
• Phase 7: Production hardening to v3.0.0 (real tool handlers, real core/ agent runtime, zero placeholders, open-source scaffolding)

v2.0.0 Architecture Components

Configuration System (config/)

• __init__.py — Type-safe configuration with Pydantic models (SkillConfig, LLMConfig, KnowledgeConfig, HookConfig, MonitoringConfig)
• schemas.py — JSON schemas for all inputs/outputs (AnalysisRequest, EvidenceSource, SecurityAssessment, etc.)

References System (references/)

• domain-knowledge.md — Comprehensive domain reference (MFA hierarchy, credential hygiene, recovery hardening, behavioral training)
• prompt-templates.md — Standardized prompt templates for all skill operations

Assets System (assets/)

• system-architecture.md — Complete architecture documentation (diagrams, data flow, deployment considerations)

Hooks System (hooks/)

• __init__.py — Hook manager with lifecycle events (HookManager, HookContext, HookResult)
• default_hooks.py — Default hook implementations (pre_execution_validate_input, post_execution_emit_metrics, on_error_log_context, etc.)

Tools System (tools/)

• __init__.py — Tool manager with schema validation (ToolManager, ToolDefinition, ToolResult)
• web_search.py — Web search handler for domain data
• web_fetch.py — Document fetch handler for authoritative sources
• knowledge_query.py — Knowledge base query handler

Monitoring System (monitoring/)

• __init__.py — Structured logging and metrics (MetricsCollector, StructuredLogger, MonitoringSystem)
• context_manager.py — Token optimization and context window management (ContextManager, PromptOptimizer)

Test Suite (tests/)

• test_config.py — Configuration system tests (18 tests)
• test_hooks.py — Hooks system tests (25 tests)
• test_tools.py — Tools system tests (22 tests)
• test-scenarios.md — Integration test scenarios (5 scenarios)

Documentation

• SKILL.md — Complete skill registry documentation (registration, execution, validation)
• DEVELOPMENT-TRACKING.md — Development session log with technical decisions

v3.0.0 Core Runtime (core/)

The flexible agent/skill architecture is implemented as real, runnable code (not pseudo-code):

• core/registry.py - SkillRegistry: loads skills/*.md frontmatter, resolves by name/alias/tag, topologically orders by dependencies, executes skills through a pluggable handler with pre/post hooks and metrics.
• core/router.py - ChainOfThoughtRouter: classifies request complexity and selects an execution plan (steps + sequential/parallel).
• core/quality_gates.py - QualityGateEngine: real U1-U6 + G1-G4 checks with auto-fix operating on a mutable working output.
• core/security_analyzer.py - deterministic, rule-based Game Account Security & Anti-Phishing analyzer (MFA hierarchy, credential hygiene, recovery hardening, behavioral training) producing per-account assessments, a verdict, scenarios, risks and an evidence chain - no LLM required.
• core/orchestrator.py - HarnessOrchestrator: wires registry + router + tools + hooks + monitoring + context manager into the end-to-end 6-step harness. Entry point: from core import run_analysis; run_analysis({"accounts": [...], "current_security": {...}}).

Automation (scripts/)

• scripts/validate_project.py - 8-File Contract + v3.0 component + zero-placeholder validator.
• scripts/run_all_tests.py - runs pytest + all validators; pass/fail summary.
• scripts/setup.py - environment self-check and bootstrap.
• scripts/seed_knowledge.py - idempotent baseline reference seeder for SECOND-KNOWLEDGE-BRAIN.md.

References

• PROJECT-detail.md — full technical specification
• PROJECT-DEVELOPMENT-PHASE-TRACKING.md — build roadmap
• SECOND-KNOWLEDGE-BRAIN.md — self-improving knowledge base
• D:\972026\SKILL-STANDARD.md — library-wide standard
• Reference impl: D:\vn-finance-analysis-hd-skill