菜单
JikiME-ADK's foundational principles - TRUST 5, SPEC-First DDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
AI-powered legacy site rebuilding workflow. Captures screenshots, analyzes source code, and generates modern frontend/backend code. Claude Code reads screenshots and writes actual code. Use when rebuilding legacy PHP, WordPress, or similar sites to Next.js, React, or other modern frameworks.
하네스를 구성합니다. 전문 에이전트를 정의하며, 해당 에이전트가 사용할 스킬을 생성하는 메타 스킬. (1) '하네스 구성해줘', '하네스 구축해줘' 요청 시, (2) '하네스 설계', '하네스 엔지니어링' 요청 시, (3) 새로운 도메인/프로젝트에 대한 하네스 기반 자동화 체계를 구축할 때, (4) 하네스 구성을 재구성하거나 확장할 때 사용.
Leader agent role guide for jikime team orchestration. Covers task distribution, plan approval, worker monitoring, and team shutdown. Use when spawned as the leader role in a jikime team.
Reviewer agent role guide for jikime team orchestration. Covers plan review, quality assessment, acceptance criteria validation, and feedback delivery via team inbox. Use when spawned as the reviewer role in a jikime team.
Use this skill when the user asks to "jikime team을 사용해줘", "팀 만들어줘", "에이전트 생성해줘", "멀티 에이전트로 작업해줘", "병렬로 에이전트 실행해줘", "여러 에이전트 조율해줘", "작업을 여러 에이전트에게 분배해줘", "team status 확인해줘", "task 만들어줘", "inbox 확인해줘", or mentions "jikime team", "multi-agent coordination", "spawn agents", "team tasks", "agent inbox", "task board", "team leader", "team worker". Also trigger when the scope of work is large enough to benefit from splitting into parallel subtasks — for example "전체 코드베이스 리팩토링", "여러 기능 동시에 구현", "대규모 분석", "full-stack app 만들어줘". Provides comprehensive guidance for using the jikime team CLI to orchestrate multi-agent teams with task management, messaging, and monitoring.
Claude Code skill for operating as part of a jikime multi-agent team (swarm). Provides command reference, coordination protocols, and role-specific workflows for leader, worker, and reviewer agents. Triggers when the task involves multi-agent coordination, spawning workers, assigning tasks, monitoring team progress, or when the scope exceeds what a single agent can efficiently handle (e.g., "build a full-stack app", "implement multiple features in parallel", "refactor the entire codebase"). Also triggers on keywords: "create a team", "spawn agents", "assign tasks", "team status", "board attach", "agent inbox", "multi-agent", "swarm", "jikime team".
| name | jikime-foundation-core |
| description | JikiME-ADK's foundational principles - TRUST 5, SPEC-First DDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows |
| version | 1.0.0 |
| tags | ["foundation","trust-5","spec","ddd","delegation","token-optimization","patterns"] |
| triggers | {"keywords":["TRUST","foundation","principle","architecture","delegation","token","원칙"],"phases":["plan","run","sync"],"agents":["manager-spec","manager-strategy","manager-quality"],"languages":[]} |
| progressive_disclosure | {"enabled":true,"level1_tokens":"~100","level2_tokens":"~3248"} |
| user-invocable | false |
| allowed-tools | ["Read","Grep","Glob","mcp__context7__resolve-library-id","mcp__context7__get-library-docs"] |
Foundational principles and architectural patterns that power JikiME-ADK's AI-driven development workflow.
Core Philosophy: Quality-first, test-driven, modular, and efficient AI development through proven patterns and automated workflows.
What is JikiME Foundation Core?
Six essential principles that ensure quality, efficiency, and scalability in AI-powered development:
Quick Access:
Use Cases:
Purpose: Automated quality gates ensuring code quality, security, and maintainability.
Five Pillars:
Test-first Pillar: Maintain test coverage at or above 85 percent. Execute pytest with coverage reporting. Block merge and generate missing tests on failure. High coverage ensures code reliability and reduces production defects. Catches bugs early and reduces debugging time by 60-70 percent.
Readable Pillar: Use clear and descriptive naming conventions. Execute ruff linter checks. Issue warning and suggest refactoring improvements on failure. Clear naming improves code comprehension and team collaboration. Reduces onboarding time by 40 percent and improves maintenance velocity.
Unified Pillar: Apply consistent formatting and import patterns. Execute black formatter and isort checks. Auto-format code or issue warning on failure. Consistency eliminates style debates and merge conflicts. Reduces code review time by 30 percent and improves readability.
Secured Pillar: Comply with OWASP security standards. Execute security-auditor agent analysis. Block merge and require security review on failure. Security vulnerabilities create critical business and legal risks. Prevents 95+ percent of common security vulnerabilities.
Trackable Pillar: Write clear and structured commit messages. Match Git commit message regex patterns. Suggest proper commit message format on failure. Clear history enables debugging, auditing, and collaboration. Reduces issue investigation time by 50 percent.
Integration Points: Pre-commit hooks for automated validation, CI/CD pipelines for quality gate enforcement, Agent workflows for manager-quality validation, Documentation for quality metrics.
Detailed Reference: modules/trust-5-framework.md
Purpose: Specification-driven development ensuring clear requirements before implementation.
Three-Phase Workflow:
Phase 1 SPEC (/jikime:1-plan): manager-spec generates EARS format. Output is .jikime/specs/SPEC-XXX/spec.md. Execute /clear to save 45-50K tokens.
Phase 2 DDD (/jikime:2-run): RED for failing tests, GREEN for passing code, REFACTOR for optimization. Validate with at least 85% coverage.
Phase 3 Docs (/jikime:3-sync): API documentation, architecture diagrams, project reports.
EARS Format: Ubiquitous for system-wide always active requirements. Event-driven for trigger-based when X do Y requirements. State-driven for conditional while X do Y requirements. Unwanted for prohibited shall not do X requirements. Optional for nice-to-have where possible do X requirements.
Token Budget: SPEC takes 30K, DDD takes 180K, Docs takes 40K, Total is 250K.
Key Practice: Execute /clear after Phase 1 to initialize context.
Detailed Reference: modules/spec-first-ddd.md
Purpose: Task delegation to specialized agents, avoiding direct execution.
Core Principle: The orchestrator must delegate all work through Task() to specialized agents. Direct execution bypasses specialization, quality gates, and token optimization. Proper delegation improves task success rate by 40 percent and enables parallel execution.
Delegation Syntax: Call Task with subagent_type parameter for specialized agent, prompt parameter for clear specific task, and context parameter with relevant data dictionary.
Three Patterns:
Sequential for dependencies: Call Task to backend for design, then Task to backend for implementation with design context.
Parallel for independent work: Call Promise.all with Task to backend and Task to frontend simultaneously.
Conditional for analysis-based: Call Task to debugger for analysis, then based on analysis.type, call Task to security-auditor or other appropriate agent.
Agent Selection: Simple tasks with 1 file use 1-2 agents sequential. Medium tasks with 3-5 files use 2-3 agents sequential. Complex tasks with 10+ files use 5+ agents mixed.
Detailed Reference: modules/delegation-patterns.md
Purpose: Efficient 200K token budget through strategic context management.
Budget Allocation:
SPEC Phase takes 30K tokens. Strategy is to load requirements only and execute /clear after completion. Specification phase requires minimal context for requirement analysis. Saves 45-50K tokens for implementation phase.
DDD Phase takes 180K tokens. Strategy is selective file loading, load only implementation-relevant files. Implementation requires deep context but not full codebase. Enables 70 percent larger implementations within budget.
Docs Phase takes 40K tokens. Strategy is result caching and template reuse. Documentation builds on completed work artifacts. Reduces redundant file reads by 60 percent.
Total Budget is 250K tokens across all phases. Phase separation with context reset between phases provides clean context boundaries and prevents token bloat. Enables 2-3x larger projects within same budget.
Token Saving Strategies:
Phase Separation: Execute /clear between phases, after /jikime:1-plan to save 45-50K, when context exceeds 150K, after 50+ messages.
Selective Loading: Load only necessary files.
Context Optimization: Target 20-30K tokens.
Model Selection: Sonnet for quality, Haiku for speed and cost with 70% cheaper rates for 60-70% total savings.
Detailed Reference: modules/token-optimization.md
Purpose: Three-tier knowledge delivery balancing value with depth.
Three Levels:
Quick Reference Level: 30 seconds time investment, core principles and essential concepts, approximately 1,000 tokens. Rapid value delivery for time-constrained users. Users gain 80 percent understanding in 5 percent of time.
Implementation Level: 5 minutes time investment, workflows, practical examples, integration patterns, approximately 3,000 tokens. Bridges concept to execution with actionable guidance. Enables immediate productive work without deep expertise.
Advanced Level: 10+ minutes time investment, deep technical dives, edge cases, optimization techniques, approximately 5,000 tokens. Provides mastery-level knowledge for complex scenarios. Reduces escalations by 70 percent through comprehensive coverage.
SKILL.md Structure (maximum 500 lines): Quick Reference section, Implementation Guide section, Advanced Patterns section, Works Well With section.
Module Architecture: SKILL.md as entry point with cross-references, modules directory for deep dives with unlimited size, examples.md for working samples, reference.md for external links.
File Splitting when exceeding 500 lines: SKILL.md contains Quick at 80-120 lines, Implementation at 180-250 lines, Advanced at 80-140 lines, References at 10-20 lines. Overflow content goes to modules/topic.md.
Detailed Reference: modules/progressive-disclosure.md
Purpose: Scalable file structure enabling unlimited content.
Standard Structure: Create .claude/skills/skill-name/ directory containing SKILL.md as core file under 500 lines, modules directory for extended content with unlimited size including patterns.md, examples.md for working samples, reference.md for external links, scripts directory for utilities (optional), templates directory (optional).
File Principles: SKILL.md stays under 500 lines with progressive disclosure and cross-references. modules directory is topic-focused with no limits and self-contained content. examples.md is copy-paste ready with comments. reference.md contains API docs and resources.
Cross-Reference Syntax: Reference modules as Details in modules/patterns.md, reference examples as Examples in examples.md#auth, reference external docs as External in reference.md#api.
Discovery Flow: SKILL.md to Topic to modules/topic.md to Deep dive.
Detailed Reference: modules/modular-system.md
Advanced patterns including cross-module integration, quality validation, and error handling are available in the detailed module references.
Key Advanced Topics:
Detailed Reference: examples.md for working code samples
Agents: agent-builder for creating agents with foundation principles, skill-builder for generating skills with modular architecture, manager-quality for automated TRUST 5 validation, manager-spec for EARS format specification, manager-ddd for ANALYZE-PRESERVE-IMPROVE execution, manager-docs for documentation with progressive disclosure.
Skills: jikime-foundation-claude for CLAUDE.md with foundation patterns, jikime-foundation-claude for config with TRUST 5, jikime-foundation-context for token optimization, jikime-workflow-jit-docs for MCP integration.
Tools: AskUserQuestion for direct user interaction and clarification needs.
Commands: /jikime:1-plan for SPEC-First Phase 1, /jikime:2-run for DDD Phase 2, /jikime:3-sync for Documentation Phase 3, /clear for token management.
Foundation Modules (Extended Documentation): modules/agents-reference.md for 26-agent catalog with 7-tier hierarchy, modules/commands-reference.md for 6 core commands workflow, modules/execution-rules.md for security, Git strategy, and compliance.
New Agent: Primary principle is TRUST 5 and Delegation. Supporting principles are Token Optimization and Modular.
New Skill: Primary principle is Progressive and Modular. Supporting principles are TRUST 5 and Token Optimization.
Workflow: Primary principle is Delegation Patterns. Supporting principles are SPEC-First and Token Optimization.
Quality: Primary principle is TRUST 5 Framework. Supporting principle is SPEC-First DDD.
Budget: Primary principle is Token Optimization. Supporting principles are Progressive and Modular.
Docs: Primary principle is Progressive and Modular. Supporting principle is Token Optimization.
Module Deep Dives: modules/trust-5-framework.md, modules/spec-first-ddd.md, modules/delegation-patterns.md, modules/token-optimization.md, modules/progressive-disclosure.md, modules/modular-system.md, modules/agents-reference.md, modules/commands-reference.md, modules/execution-rules.md.
Full Examples: examples.md External Resources: reference.md
