본문으로 건너뛰기
cccskills
무료GitHub에 공개

longgraph

Use only when the user explicitly invokes /longgraph or names this skill. Routes and authors a durable longgraph run. Do not use unless named. Do not execute or resume generated runtime node files.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(64)

  • SKILL.md1.7 KB
  • .claude-plugin/marketplace.json481 B
  • .claude-plugin/plugin.json899 B
  • .github/ISSUE_TEMPLATE/bug_report.md555 B
  • .github/ISSUE_TEMPLATE/feature_request.md636 B
  • .github/PULL_REQUEST_TEMPLATE.md567 B
  • .github/workflows/grok-bot-issue-relay.yml1.2 KB
  • .github/workflows/grok-bot-pr-relay.yml1.1 KB
  • .gitignore165 B
  • AGENTS.md6.3 KB
  • assets/graph.png611.6 KB
  • CLAUDE.md199 B
  • CONTRIBUTING.md4.8 KB
  • docs/public-private-boundary.md5.8 KB
  • install.sh2.8 KB
  • lib/methodology.md21.1 KB
  • LICENSE1.0 KB
  • llms.txt2.8 KB
  • README.md15.1 KB
  • README.zh-CN.md14.5 KB
  • skills/loop-converge/preset.md8.3 KB
  • skills/loop-converge/README.md1.6 KB
  • skills/loop-converge/README.zh-CN.md1.6 KB
  • skills/loop-converge/SKILL.md1.8 KB
  • skills/loop-deliver/preset.md4.8 KB
  • skills/loop-deliver/README.md1.4 KB
  • skills/loop-deliver/README.zh-CN.md1.2 KB
  • skills/loop-deliver/SKILL.md1.9 KB
  • skills/loop-graph/docs/model.md7.8 KB
  • skills/loop-graph/docs/preset-contract.md2.8 KB
  • skills/loop-graph/examples/add-tests-to-cli/executor.md3.2 KB
  • skills/loop-graph/examples/add-tests-to-cli/ledger.md2.9 KB
  • skills/loop-graph/examples/add-tests-to-cli/README.md2.0 KB
  • skills/loop-graph/examples/migrate-blob-storage/archive/directives.md1.3 KB
  • skills/loop-graph/examples/migrate-blob-storage/archive/rounds.md602 B
  • skills/loop-graph/examples/migrate-blob-storage/directives.md360 B
  • skills/loop-graph/examples/migrate-blob-storage/executor.md6.1 KB
  • skills/loop-graph/examples/migrate-blob-storage/ledger.md3.6 KB
  • skills/loop-graph/examples/migrate-blob-storage/README.md5.0 KB
  • skills/loop-graph/examples/redacted-multiday-control-plane/README.md6.7 KB
  • skills/loop-graph/examples/redacted-multiday-control-plane/README.zh-CN.md5.8 KB
  • skills/loop-graph/examples/scout-library-choice/README.md4.4 KB
  • skills/loop-graph/examples/self-iteration-longgraph-skill/README.md6.5 KB
  • skills/loop-graph/examples/self-iteration-longgraph-skill/README.zh-CN.md6.0 KB
  • skills/loop-graph/README.md16.0 KB
  • skills/loop-graph/README.zh-CN.md15.4 KB
  • skills/loop-graph/references/claude-code.md4.2 KB
  • skills/loop-graph/references/codex.md5.4 KB
  • skills/loop-graph/references/cursor.md1.9 KB
  • skills/loop-graph/references/grok.md3.9 KB
  • skills/loop-graph/references/shell-cron.md1.8 KB
  • skills/loop-graph/SKILL.md22.7 KB
  • skills/loop-graph/templates/directives.md2.6 KB
  • skills/loop-graph/templates/executor.md11.2 KB
  • skills/loop-graph/templates/findings.md1.7 KB
  • skills/loop-graph/templates/handoff.md1.0 KB
  • skills/loop-graph/templates/ledger.md7.8 KB
  • skills/loop-graph/templates/ops-and-environment.md5.0 KB
  • skills/loop-graph/templates/scout.md4.8 KB
  • skills/loop-graph/templates/supervisor.md7.4 KB
  • skills/loop-research/preset.md6.6 KB
  • skills/loop-research/README.md1.4 KB
  • skills/loop-research/README.zh-CN.md1.3 KB
  • skills/loop-research/SKILL.md2.0 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

longgraph — route to the right durable run

longgraph has one shared compiler, loop-graph, and focused entries that bind only goal-specific rules. All compile the same executor, supervisor, ledger, directives, and ops artifacts. Do not execute the generated runtime nodes from this authoring skill.

Fit and route

  • Use loop-converge for multi-round unused code, duplication, consolidation, reuse, or slimming.
  • Use loop-deliver for a product or engineering requirement that needs incremental implementation and acceptance proof.
  • Use loop-research to compare feasible approaches with open-source implementations, primary research, and controlled experiments before committing to one.
  • Use loop-graph directly only when none of the focused packs fits but the work still needs durable state, gates, owner boundaries, host switching, or independent verification.
  • If the request is one self-contained task that fits a normal host goal/task, explain that longgraph adds no value and recommend sending the task directly. Do not wrap it in another objective or invent a lighter longgraph mode.

Shared reference: lib/methodology.md explains why the graph's discipline exists. The baseline and pack boundary is in skills/loop-graph/docs/preset-contract.md.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Use only when the user explicitly invokes /loop-converge or names this skill. Authors a loop-converge run. Do not use unless named. Do not execute or resume generated runtime node files.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

levi-qiao/longgraph-skill782026년 9월 23일 업데이트

Use only when the user explicitly invokes /loop-deliver or names this skill. Authors a loop-deliver run. Do not use unless named. Do not execute or resume generated runtime node files.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

levi-qiao/longgraph-skill782026년 9월 23일 업데이트

Use only when the user explicitly invokes /loop-graph or names this skill. Compiles a custom loop-graph run. Do not use unless named. Existing runtime nodes are self-contained.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

levi-qiao/longgraph-skill782026년 9월 23일 업데이트

Use only when the user explicitly invokes /loop-research or names this skill. Authors a loop-research run. Do not use unless named. Do not execute or resume generated runtime node files.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

levi-qiao/longgraph-skill782026년 9월 23일 업데이트

levi-qiao의 스킬 모두 보기

이 스킬의 문제 신고