jjackkun
UserClaude Code 스킬·룰·훅 프리셋 설치 관리 + 대화에서 배우는 자가진화 러닝 루프(롤링 요약·드리밍·결정화) | Preset-based setup manager for Claude Code skills/rules/hooks + a self-evolving learning loop (rolling summary, dreaming, skill crystallization)
Categories
Indexed Skills (44)
impeccable
Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context. Call with 'craft' for shape-then-build, 'teach' for design context setup, or 'extract' to pull reusable components and tokens into the design system.
backend-patterns
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
coding-standards
Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns.
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.
dart-flutter-patterns
Production-ready Dart and Flutter patterns covering null safety, immutable state, async composition, widget architecture, popular state management frameworks (BLoC, Riverpod, Provider), GoRouter navigation, Dio networking, Freezed code generation, and clean architecture.
database-migrations
Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate).
flutter-dart-code-review
Library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
frontend-patterns
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
java-coding-standards
Java coding standards for Spring Boot services: naming, immutability, Optional usage, streams, exceptions, generics, and project layout.
jpa-patterns
JPA/Hibernate patterns for entity design, relationships, query optimization, transactions, auditing, indexing, pagination, and pooling in Spring Boot.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
postgres-patterns
PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.
python-patterns
Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.
search-first
Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Dispatches a general-purpose agent for parallel research.
springboot-patterns
Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.
springboot-security
Spring Security best practices for authn/authz, validation, CSRF, secrets, headers, rate limiting, and dependency security in Java Spring Boot services.
springboot-tdd
Test-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo. Use when adding features, fixing bugs, or refactoring.
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
verification-loop
A comprehensive verification system for Claude Code sessions.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
harness-eval
하네스 행동 회귀 평가 — 훅·가드·룰이 에이전트의 실제 행동을 막는지 `claude -p`(haiku) 로 재서 pass@k·pass^k·"발화 후 위반" 수치를 낸다. 사용자가 "훅이 진짜 막아?", "규칙 바꿨는데 행동이 퇴행했는지 재자", "행동 평가 돌려", "agent eval", "pass@k" 라고 하거나 룰·훅·스킬 문구를 바꾼 직후에 쓴다. 공장 도구(소우주 배포 아님), 로컬·수동·구독 CLI 만, CI·야간 금지.
run-to-the-end
오래 걸리는 명령을 돌리기 **직전에** 본다. 내가 "시험을 돌립니다" · "전체 검사를 돌리고" · "검증하겠습니다" · "실측하겠습니다" · "빌드하겠습니다" 라고 말하려는 자리, 또는 사용자가 "검사부터 돌려" · "시험 돌려" · "테스트 해봐" · "빌드해" · "마이그레이션 하자" · "커밋하고 푸시하자" 라고 한 자리에서 걸린다. `pytest` · `npm/pnpm test` · `gradle` · `mvn` · `cargo test` · `go test` · 타입 검사 · 린트 · 마이그레이션 · 배포 스크립트를 부르려 할 때도 걸린다. ⚠️ **정하는 것은 하나다 — 배경(run_in_background)으로 돌릴지 앞에서 기다릴지.** 배경으로 돌리고 턴을 끝내면 **기다리는 일이 사용자에게 넘어가고, 사용자가 "끝났어?" 를 물어야 일이 이어진다.** 대부분의 검사는 앞 한도(600초) 안에 들어오므로 배경으로 돌릴 이유가 없다 — 그것을 재는 도구가 여기 있다.
fastapi-patterns
FastAPI application patterns — routing, Pydantic v2, dependency injection, error handling, async DB sessions, middleware.
fastapi-testing
Testing FastAPI apps with pytest-asyncio and httpx.AsyncClient — fixtures, dependency overrides, DB isolation, auth.
harness-boundary-check
실행 모드(once/scheduled/realtime) 간 경계 위반과 LLM SDK 직접 호출을 감지한다. Use when writing or reviewing code that touches execution modules, LLM calls, or import statements across mode directories.
harness-promote-rule
반복되는 결함·리뷰 지적·경계 위반을 docs/design-docs/core-beliefs.md 의 R 룰로 승격하고, 대응하는 강제 장치(테스트·린터 규칙)를 스캐폴드한다. Use when the same defect/review comment/boundary violation appears 2+ times, when the user says "이거 룰로 박아"/"rule로 올려", or when weekly-doc-gardening issues a rule-candidate. Invoke before continuing implementation if the pattern is load-bearing.
hermes-loop
Goal-based autonomous loop for the CURRENT project. Trigger when the user types /hermes-loop (with or without a goal), or asks in natural language to run/start a Hermes loop (e.g. "헤르메스 루프 하자", "헤르메스 루프 돌려줘", "목표 루프 작업하자", "run a hermes loop"). On trigger, FIRST present the options form and ask the user to fill the required goal, letting them skip any optional field, THEN run. The target is always the current project where this skill is installed — never ask which project. Destructive actions go through the standard permission prompts.
hermes-status
Show the overall Hermes engineering status. Use when the user types /hermes-status. Reads the project's .hermes/state.db and prints skill/rule/session counts, pending crystallization patterns, and the latest/most-used crystallized skills, then offers to run crystallization if patterns are pending.
node-patterns
Node.js runtime patterns — ESM, package manager discipline, async/await, streams, error handling, environment config.
plan-verification-split
Use this skill whenever a plan or spec contains an acceptance-criteria checklist ("수용 기준", "acceptance criteria", "manual verification", "수동 검증", browser walk-through, feature sign-off) that the agent needs to confirm before marking the work done. Split every item into programmatically-verifiable (auto) and human-only (human) parts, run the auto parts immediately, record evidence in the audit doc, and ask the user only for the residual human items. Invoke even when the plan labels the step "수동 검증" or "manual test" — most such checklists have items an agent can prove without user eyes via a DB query, API call, grep, or log scan. The point is to stop dumping the entire checklist on the user when half of it is mechanically verifiable.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
structured-file-layout
Use when creating new files, planning features, or writing exec-plans — before any code is written, to ensure each file has a single responsibility and folders are organized by domain
svelte-patterns
Svelte 5 runes, SvelteKit routing/load/form patterns, store patterns, and SSR/CSR decisions.
typescript-patterns
TypeScript type system patterns — strict mode, generics, discriminated unions, branded types, inference, utility types.
hermes-agent
헤르메스 에이전트 명부·조직·소환·인계를 CLI 로 잇는다. `/hermes-agent` 라고만 치거나 "에이전트 만들자"·"한 명 입사시켜"·"직원 뽑자" 처럼 분야·직급·조직 없이 입사를 말하면 터미널 폼(선택지)을 먼저 띄워 조직 정의 → 입사까지 하고 SOUL 은 기계 초안으로 채운다(사람은 승인만). 사용자가 자연어로 "누구를 입사시켜"(예 "users 담당 입사시켜", "QA 한 명 뽑아"), "이 일을 누구한테 넘겨"(예 "이 로그인 버그 프론트 담당한테 넘겨", "이거 QA 한테 인계해"), "누가 이 일 맡지"(담당 찾기), "누구 은퇴/복직시켜", "명부 보여줘", "지금 나 누구야"(정체성 확인), "누구한테 이거 가르쳐"·"이건 기억해 둬"(가르침·기억) 중 하나를 말할 때 반드시 이 스킬을 쓴다. 담당 배정·인계·입사·조직 얘기가 나오면, "봉투"·"done_when"·"소환"이라는 단어를 쓰지 않더라도 발동한다. 파괴적 판단(은퇴·인계 실패 처리)은 사람 확인을 거친다.
ai-dev-setting-install
Use when modifying assets (rules, skills, agents, hooks) in ai-dev-setting and deciding whether changes need reinstallation across projects, or when running setup/update-all commands.
harness-reasoning-sandwich
비자명한 작업에 계획 → 구현 → 검증 흐름을 적용하고, 큰 변경일 때만 깊은 리뷰로 승격한다. Use when starting a new feature, multi-file change, or any non-trivial implementation task.
hermes-crystallize
Crystallize repeated conversation patterns into reusable skill files. Triggered automatically by the Hermes learning loop (Stop hook) when the same pattern is detected 3+ times (pattern_count count >= 3, crystallized = 0). Saves the new skill under [project]/.hermes/skills/, registers it in skill_index, and marks the pattern as crystallized.
hermes-dream
Run Hermes dreaming — consolidate accumulated rolling summaries into crystallized/evolved skills and propose junk-skill deletions. Use when the user types /hermes-dream [apply]. Without 'apply' it crystallizes/evolves automatically and only PROPOSES deletions (dry-run); with 'apply' it also EXECUTES the proposed deletions.
hermes-recall
Recall past conversation context from Hermes rolling summaries. Use when the user types /hermes-recall [keyword]. Reads the project's .hermes/state.db session_summary table and prints matching 5-slot summaries (decisions/open tasks). Without a keyword, shows the most recent session summary.
claude-harness-hermes-install
Use when modifying assets (rules, skills, agents, hooks) in claude-harness-hermes and deciding whether changes need reinstallation across projects, or when running setup/update-all commands.
hermes-dashboard
소우주(현재 프로젝트)의 에이전트·스킬·학습 루프·건강 현황을 정적 HTML 한 장으로 만들어 경로를 알린다. 사용자가 `/hermes-dashboard` 를 치거나 "대시보드 보여줘", "현황 페이지", "에이전트 상황 한눈에", "스킬 상태 보고서", "지금 소우주 어때" 처럼 전체 상황을 한 페이지로 보고 싶어 할 때 반드시 이 스킬을 쓴다. `--universe` 는 공장에서 설치된 소우주 전부를 한 표로 본다. 모델 호출 0, 외부 자원 0, 보기 전용.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.