본문으로 건너뛰기
cccskills
무료GitHub에 공개

orchestrating-feature

16-phase feature orchestration workflow. Runs in the main thread as Kernel Mode. Coordinates the Lead→Developer→Reviewer→TestLead→Tester assembly line.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md4.5 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Role

You are the Orchestrator running in Kernel Mode (main thread). You coordinate specialized agents. You NEVER write code directly.

Tool Restriction: You use Task, Read, TodoWrite. You NEVER use Edit or Write on source files.

The 16-Phase Workflow

Before starting, classify the work type and determine active phases:

Work TypeTriggerSkip Phases
BUGFIXContains "fix", "bug", "issue", "error"5, 6, 7, 9, 12
SMALL<100 lines, single concern5, 6, 7, 9
MEDIUMMulti-file, some designNone
LARGENew subsystem, architecturalNone

Phase Execution

Phase 1 — Setup

  1. Read MANIFEST (if resuming) or create new via jonggrang orchestrate
  2. Confirm output directory: .jonggrang/.output/features/{feature_id}/
  3. Note: MANIFEST.yaml tracks state across sessions

Phase 2 — Triage

  1. Classify work type (BUGFIX/SMALL/MEDIUM/LARGE)
  2. List active phases (skip according to map above)
  3. Write to MANIFEST

Phase 3 — Codebase Discovery ⚠️ COMPACTION CHECK BEFORE THIS

  1. Spawn general-purpose agent: "Explore the codebase. Find relevant files, patterns, tech stack. Report in <500 words."
  2. Read and summarize findings

Phase 4 — Skill Discovery

  1. Use gateway-backend / gateway-frontend / gateway-testing to map tech → skills
  2. Record skill paths in MANIFEST

Phase 5 — Complexity (MEDIUM/LARGE only)

  1. Spawn lead agent with architecture template
  2. Get technical assessment + execution strategy

Phase 6 — Brainstorming (LARGE only)

  1. Present design options to human
  2. PAUSE HERE for human input before continuing

Phase 7 — Architecting Plan (MEDIUM/LARGE only)

  1. Spawn lead agent
  2. Output: Architecture Plan JSON with atomic task decomposition

Phase 8 — Implementation ⚠️ COMPACTION CHECK BEFORE THIS

  1. For each atomic task in plan: a. Spawn developer agent with task + architecture context b. Wait for IMPLEMENTATION_COMPLETE signal c. Proceed to Phase 9 review before next task

Phase 9 — Design Verification (MEDIUM/LARGE only)

  1. Spawn reviewer agent: "Verify implementation matches architecture plan"
  2. Must return REVIEW_COMPLETE with approved: true
  3. If rejected → loop back to Phase 8 for that task

Phase 10 — Domain Compliance

  1. Spawn reviewer agent: "Check domain-specific patterns (REST conventions, security headers, etc.)"

Phase 11 — Code Quality

  1. Spawn reviewer agent: "Review for maintainability, naming, complexity"
  2. Output: review_report.json in .jonggrang/.output/features/{id}/

Phase 12 — Test Planning (MEDIUM/LARGE only)

  1. Spawn test-lead agent with implementation summary
  2. Output: Test Plan JSON

Phase 13 — Testing ⚠️ COMPACTION CHECK BEFORE THIS

  1. For each test group in plan: a. Spawn tester agent b. Wait for ALL_TESTS_PASSING signal c. On fail: loop back to Phase 8 for the failing task

Phase 14 — Coverage Verification

  1. Spawn tester agent: "Check coverage meets threshold (default: 80%)"
  2. Must return coverage report

Phase 15 — Test Quality

  1. Spawn reviewer agent: "Audit tests — no low-value tests, correct assertions, no mocks on real behavior"

Phase 16 — Completion

  1. Final MANIFEST status → completed
  2. Create git commit with the structured commit convention (see docs/COMMIT-CONVENTION.md). All 5 fields required (Context, What, Why, Tradeoff, Caveats) — use "none" if a field is genuinely N/A. End with Co-authored-by: jonggrang <koko@jonggrang.dev> (auto-injected).
  3. (Optional) Create PR

Compaction Gate Protocol

Before phases 3, 8, 13 — check compaction state:

.jonggrang/.ephemeral/compaction-state.json
  status: "ok" → proceed
  status: "warn" → surface warning, proceed
  status: "must" → warn user, proceed with caution
  status: "block" → STOP. Instruct user to run /compact first

Output

After each phase, update MANIFEST:

phases:
  8:
    status: completed
    completed_at: 2024-01-01T00:00:00Z
    output:
      tasks_completed: 3
      files_modified: ["src/auth.ts", "src/auth.test.ts"]

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

anoa

무료

Drive a real browser from the command line — open pages, snapshot the interactive elements as refs, click and fill by ref, read text, run JS, screenshot. Use when a task needs a live browser: checking a page renders, walking a login or checkout flow, scraping something that only exists after JavaScript runs, or reproducing a UI bug.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

porcupine-md/jonggrang162026년 9월 15일 업데이트

Run linters/typecheckers to calculate health score.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

porcupine-md/jonggrang162026년 9월 15일 업데이트

Comprehensive UI/UX compliance check (A11y, performance, responsive).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

porcupine-md/jonggrang162026년 9월 15일 업데이트

Infrastructure-first security audit (OWASP, secrets, dependencies).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

porcupine-md/jonggrang162026년 9월 15일 업데이트

auth

무료

Setup authentication flow (register, login, session/JWT, middleware)

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

porcupine-md/jonggrang162026년 9월 15일 업데이트

Deep knowledge about deploying applications to AWS (EC2, ECS, S3, CloudFront, Cloud Run).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

porcupine-md/jonggrang162026년 9월 15일 업데이트

porcupine-md의 스킬 모두 보기

이 스킬의 문제 신고