원클릭으로
work
Use when executing an approved plan - implements with TDD discipline, systematic debugging, worktree isolation, and progress tracking
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Use when executing an approved plan - implements with TDD discipline, systematic debugging, worktree isolation, and progress tracking
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use after implementation to run independent code review - dispatches reviewer agents based on task level, ensures author-reviewer separation
Use for the L2+ browser-QA gate. Real-browser mode (Playwright Chromium) is opt-in (--browse / SGC_QA_REAL=1); by default runs a stub returning concern (never rubber-stamps). Writes verdict + findings to reviews/{task}/qa/.
Use when starting any conversation - establishes SGC commands, routes tasks to appropriate skills, and enforces system invariants
Use to capture knowledge from solved problems - extracts structured solution documents via 4 specialized agents with dedup enforcement
Use when requirements are unclear, before planning - clarifies goals, constraints, and acceptance criteria through structured questioning
Use when starting any non-trivial task - classifies task level (L0-L3), runs appropriate planning agents, produces intent document and execution plan
| name | work |
| description | Use when executing an approved plan - implements with TDD discipline, systematic debugging, worktree isolation, and progress tracking |
Execute an approved plan; track completion in progress/feature-list.md.
Core principle: no production code without a failing test first. Evidence at every step.
/work after /plan produced an intent and feature list| Directory | Access |
|---|---|
| decisions | R |
| progress | RW |
| solutions | R |
| reviews | — |
reviews/ is intentionally locked — work must not self-select based on pending review verdicts.
src/commands/work.ts (runWork)src/dispatcher/state.ts~/.claude/CLAUDE.md §7 validate, CLAUDE-extended.md §6 debug / §7-EXT evidence ladder),
not duplicated here.plugins/sgc/CLAUDE.mdWhen this skill is invoked, dispatch to the sgc CLI:
bun src/sgc.ts work $ARGUMENTS
work does NOT spawn review agents. Call sgc review (and sgc qa for L2+) when all features are done.
For TDD discipline during implementation:
sp:test-driven-development — write failing test first, then implement