Skip to main content
Manus에서 모든 스킬 실행
원클릭으로
EATSTEAK
GitHub 제작자 프로필

EATSTEAK

4개 GitHub 저장소에서 수집된 37개 skills를 저장소 단위로 보여줍니다.

수집된 skills
37
저장소
4
업데이트
2026-07-23
저장소 탐색

저장소와 대표 skills

autodesign-skillopt
기타 컴퓨터 관련 직업

Private Stage 11 SkillOpt subskill. Generates deterministic hardening reports and review-only patch proposals after eval E2E PASS.

2026-06-07
autodesign-start
기타 컴퓨터 관련 직업

Start Autodesign setup from the eatsteak/autodesign skill package. Use when the user asks to initialize, start, install-check, bootstrap, validate state, inspect the artifact graph, check subskill readiness, record gates, compute dirty artifacts, generate canonical artifacts, run visual reference gates, run Pencil/DS/prototype/QA metadata records, generate frontend handoff docs, generate reconcile reports, or generate SkillOpt hardening reports.

2026-06-07
autodesign-handoff
웹·디지털 인터페이스 디자이너

Private Stage 09 handoff subskill. Generates frontend handoff documentation as JSON and Markdown only, after Stage 08 prototype and QA gates pass.

2026-06-07
autodesign-reconcile
웹·디지털 인터페이스 디자이너

Private Stage 09 reconcile subskill. Generates advisory dirty-propagation reports from artifact graph preserve/may-change policies after handoff docs exist.

2026-06-07
autodesign-ds
소프트웨어 개발자

Private Stage 08 design-system subskill. Generates DS tokens and component contracts from primitives, selected references, and Pencil wireframes.

2026-06-07
autodesign-primitives
소프트웨어 개발자

Private Stage 08 primitives subskill. Generates deterministic primitive inventory from selected visual references and canonical brand direction.

2026-06-07
autodesign-prototype
소프트웨어 개발자

Private Stage 08 prototype subskill. Persists prototype metadata and real canvas export path records without generating frontend handoff.

2026-06-07
autodesign-qa
소프트웨어 품질 보증 분석가·테스터

Private Stage 08 semantic visual QA subskill. Persists QA and max-two-refinement gate records.

2026-06-07
이 저장소에서 수집된 skills 19개 중 상위 8개를 표시합니다.
pr
소프트웨어 개발자

Prepare and create a GitHub pull request from the current branch. Use when the user asks to open a PR, create a pull request, or requests `/pr`, including an optional base branch argument.

2026-07-23
orchestrator
기타 컴퓨터 관련 직업

Orchestrate staged repository work through delegated preflight, single-writer implementation, independent validation, and a final closure gate. Use for multi-stage refactors, migrations, phased rollouts, or other work with clean stage boundaries. The parent coordinates; subagents perform all repository observation and mutation.

2026-07-23
xy
소프트웨어 개발자

Resolve XY problems — surface questions that mask a deeper goal. Use when the user invokes /xy, when a request is vague or mismatched to its context, or when a narrow how-to looks like it's hiding the real objective.

2026-07-01
use-pnpm
소프트웨어 개발자

Always use pnpm/pnpx for Node.js work unless the project packageManager field specifies another package manager. Use when Node.js, JavaScript, TypeScript, npm scripts, package installation, or Node CLI tools are involved.

2026-05-08
youtube-summarizer
기술 작가

YouTube 영상 URL에서 자막을 추출하고 한국어로 상세 요약을 작성합니다. Use this skill whenever the user provides a YouTube URL and asks to summarize, recap, extract a transcript, analyze video contents, or create Korean notes from a video, including Korean prompts such as "유튜브 요약", "영상 정리", "자막 추출", or "한국어로 요약".

2026-05-07
superlearn
개인 교습 강사

Use when the user wants to rapidly learn, memorize, quiz, review, or prepare for exams from Markdown course notes or weekly lecture files. Runs an adaptive active-recall loop with questions, grading, error patches, summaries, and next-action selection until the user stops.

2026-04-29
setup-rust
소프트웨어 개발자

Set up Claude Code hooks for Rust projects when a Cargo.toml file exists. Use when the user wants Rust quality checks wired into settings.json/settings.local.json, asks to enable cargo check/fmt/clippy hooks, or wants automatic Rust validation for a repository.

2026-04-20
use-uv
소프트웨어 개발자

Always use uv for Python work. Use when Python code, dependencies, virtual environments, scripts, or Python CLI tools are involved.

2026-04-19
이 저장소에서 수집된 skills 9개 중 상위 8개를 표시합니다.
commit
소프트웨어 개발자

Analyze staged git changes and create one or more well-scoped commits. Use when the user asks to commit, split staged changes into logical commits, or requests `/commit`-style smart committing, including single-commit mode.

2026-04-25
pdftomd
데스크톱 출판 전문가

Convert PDF files to Markdown while preserving content accuracy and document structure. Use when the user asks for `/pdftomd`, PDF to Markdown conversion, or wants a PDF transformed into one or more Markdown files.

2026-04-25
pr
소프트웨어 개발자

Prepare and create a GitHub pull request from the current branch. Use when the user asks to open a PR, create a pull request, or requests `/pr`, including an optional base branch argument.

2026-04-25
rearrange
소프트웨어 개발자

Analyze and reorganize current branch commits for easier review. Use when the user asks to rearrange, reorder, split, squash, or clean up commits, or requests `/rearrange` with an optional base branch.

2026-04-25
review
소프트웨어 품질 보증 분석가·테스터

Perform a code review for a branch diff, staged diff, or specific file. Use when the user asks for review, code review, `/review`, staged review, branch review, or review of a named file.

2026-04-25
summary
소프트웨어 개발자

Summarize current branch changes against a base branch. Use when the user asks for a branch summary, change summary, release-style summary, or `/summary` with an optional base branch.

2026-04-25
find-skills
소프트웨어 개발자

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

2026-02-16
evaluate-instructions
소프트웨어 개발자

이 스킬은 사용자가 에이전트 설정 파일을 '평가', '분석', '개선', '점검'하고 싶을 때 사용합니다. AGENTS.md, CLAUDE.md, .cursorrules, .cursor/rules/*.mdc, .github/copilot-instructions.md 등 에이전트 instructions 파일의 품질을 20편의 ArXiv 논문 기반 기준으로 평가합니다. 'evaluate agents', 'agent instructions 평가', 'AGENTS.md 리뷰', 'instructions 품질 체크' 등의 요청에 활성화됩니다.

2026-02-13
저장소 4개 중 4개 표시
모든 저장소를 표시했습니다