deep-work

Plugin deep-work from marketplace claude-deep-suite in Sungmin-Cho/deep-suite. Commands read from the repo's manifest — today.

Skills (27)

• deep-assumptions

  Assumption health report — per-assumption Wilson Score confidence, verdict (justified / loosen / drop), model-aware split, decay history. Triggers on `/deep-assumptions`, `/deep-status --assumptions`, \"assumption health\", \"rule justification\", \"loosen enforcement\", \"어썸션 헬스\", \"규칙 정당화\", \"가정

• deep-brainstorm

  Use when clarifying the goal, boundaries and approach for a deep-work task.

• deep-cleanup

  Scan and clean up stale deep-work git worktrees (`dw/*` branches) plus fork worktrees, and prune idle fork sessions from the registry. Triggers on `/deep-cleanup`, \"clean worktrees\", \"stale worktree\", \"worktree 정리\", \"fork 정리\", \"deep-work 정리\".

• deep-debug

  Debug sub-mode for Phase 3 — Investigate → Analyze → Hypothesize → Implement, with the iron rule that no fix ships before root-cause investigation. Triggers on `/deep-debug`, \"systematic debug\", \"root cause investigation\", \"디버그 모드\", \"근본 원인 분석\", `verification_cmd` 실패 시 자동 진입, or \"fix this\".

• deep-finish

  Use when finishing an authorized deep-work session with keep, PR, merge or discard and a durable receipt.

• deep-fork

  Create an isolated deep-work branch for a parallel slice, alternative experiment, independent review, recovery, or security isolation. Same-goal context continuation is not a fork reason.

• deep-history

  Cross-session deep-work history — completed sessions, TDD compliance rates, model usage, aggregate trend indicators. Triggers on `/deep-history`, `/deep-status --history`, \"session history\", \"deep-work history\", \"세션 이력\", \"이전 세션\", \"TDD 준수율 트렌드\". Sub-page of the deep-status hub.

• deep-implement

  Use when implementing dependency-ready deep-work slices with their sealed strict or outcome verification basis.

• deep-insight

  Code-metrics, complexity and dependency report for a file/directory/glob — analysis only, never modifies code. Triggers on `/deep-insight`, \"code insight\", \"complexity report\", \"code metrics\", \"메트릭 분석\", \"복잡도 리포트\", \"의존성 분석\", or `/deep-test` running it as the Insight Tier (never blocks).

• deep-integrate

  Use when completing requested integrations after deep-work verification or exploring optional next actions.

• deep-mutation-test

  Mutation testing on changed files to verify AI-generated test quality, with an auto-fix loop that returns to Implement for survived mutants. Triggers on `/deep-mutation-test`, \"mutation test\", \"test quality\", \"mutation score\", \"뮤테이션 테스트\", \"테스트 품질 검증\".

• deep-phase-review

  Manual deep-work phase document review. Parses --phase, --structural and --adversarial, then enters the canonical adaptive review protocol.

• deep-plan

  Use when authoring or revising the implementation plan for an approved deep-work goal.

• deep-receipt

  View, dashboard, or export deep-work slice receipts (`receipts/SLICE-*.json`). Triggers on `/deep-receipt`, `/deep-status --receipts`, \"receipt dashboard\", \"slice receipt\", \"리시트 보기\", \"리시트 대시보드\", \"에비던스 리시트\". Sub-page of the deep-status hub.

• deep-report

  Generate or view the deep-work session report — lifecycle, slice summary, evidence trail, TDD compliance, model usage. Triggers on `/deep-report`, `/deep-status --report`, \"session report\", \"deep-work report\", \"세션 리포트\", \"세션 보고서\", \"리포트 생성\". Sub-page of the deep-status hub.

• deep-research

  Use when a deep-work task needs repository research or a research-phase continuation.

• deep-resume

  Use when resuming an interrupted or parked deep-work session from its current phase.

• deep-sensor-scan

  Run computational sensors (linter, type checker, coverage) inside or outside a deep-work session. Triggers on `/deep-sensor-scan`, \"run sensors\", \"lint check\", \"type check\", \"coverage\", \"센서 실행\", \"린트 검사\", \"타입 검사\". Flags: `--detect`, `--lint`, `--typecheck`, `--coverage`.

• deep-slice

  Use when inspecting, activating or recovering a deep-work slice or selecting its model.

• deep-spec

  Use when authoring or reviewing a deep-work executable goal contract, /deep-spec or $deep-work:deep-spec.

• deep-status

  Current deep-work session status — dashboard, badge, tree, or routing to the receipts / history / report / assumptions sub-pages. Triggers on `/deep-status`, \"session status\", \"deep-work status\", \"세션 상태\", \"세션 현황\", \"상태 확인\". Flags: `--compare`, `--receipts`, `--history`, `--report`, `--assum

• deep-test

  Use when validating a deep-work goal, consuming completion evidence or retrying failed slices.

• deep-work-orchestrator

  Use when starting or continuing a deep-work task with durable goal, verification and completion evidence.

• deep-work-workflow

  High-level overview of the deep-work workflow (Brainstorm → Research → Spec → Plan → Implement → Test → Integrate). Use for how deep-work works, 'which phase should I start from', and the phase-to-phase contracts; prefer the phase-specific skills to execute a phase. Triggers: 'deep-work overview', '

• deep-work

  Use when the user invokes /deep-work or requests a new deep-work session.

• drift-check

  Plan-alignment verification — approved plan vs actual implementation, reporting unimplemented items, out-of-scope changes and design drift. Read-only. Triggers on `/drift-check`, \"plan drift\", \"drift detection\", \"plan alignment\", \"플랜 드리프트\", \"계획 정합성\", \"드리프트 검증\", or `/deep-test` running it

• solid-review

  SOLID design-principles review (SRP / OCP / LSP / ISP / DIP) on a file/directory/glob. Review-only. Triggers on `/solid-review`, \"SOLID review\", \"design review\", \"design principles\", \"SOLID 검증\", \"디자인 리뷰\", \"원칙 검증\", or `/deep-test` running it as the Advisory Gate.

Subagents (4)

• implement-slice-worker

  Delegated implementation worker for deep-work's Implement phase. Runs the sealed strict/outcome verification protocol for each assigned slice ID. Dispatched by the deep-implement skill, never by the user. <example> prompt: "cluster_ids=[SLICE-001,SLICE-002]; sequential; tdd_mode=strict" </example> -

• research-codebase-worker

  Delegated research worker for deep-work's Research phase on existing codebases. Analyzes the requested area and writes findings to $WORK_DIR/research{-area}.md. Dispatched by the deep-research skill, never by the user. <example> prompt: "area=architecture; work_dir=/.../deep-work; task=..." </exampl

• research-zerobase-worker

  Delegated research worker for deep-work's Research phase on new projects (project_type=zero-base). Researches technology choices, conventions and data models, with explicit authority to search the web. Dispatched by the deep-research skill, never by the user. <example> prompt: "area=tech-stack; work

• session-recommender

  Deep-work 세션 초기화 시 task description + workspace meta + capability를 분석하여 4개 ask 항목(team_mode, start_phase, tdd_mode, git)에 대한 추천 값과 task_difficulty를 fenced JSON으로 반환합니다. <example> prompt: { "task_description": "Refactor authentication module", "workspace_meta": {...}, "capability": {...} } expected_o

Hooks (6)

• SessionStart

  if command -v node >/dev/null 2>&1; then exec node -e "var e=process.env,c=e.CLAUDE_PLUGIN_ROOT,p=e.PLUGIN_ROOT,v=(c!==undefined&&c!=='')?'CLAUDE_PLUGIN_ROOT':((p!==undefined&&p!=='')?'PLUGIN_ROOT':'n

• SessionStart

  if command -v node >/dev/null 2>&1; then exec node -e "var e=process.env,c=e.CLAUDE_PLUGIN_ROOT,p=e.PLUGIN_ROOT,v=(c!==undefined&&c!=='')?'CLAUDE_PLUGIN_ROOT':((p!==undefined&&p!=='')?'PLUGIN_ROOT':'n

• PreToolUse

  if ! command -v node >/dev/null 2>&1; then echo 'deep-work hook bootstrap: node executable not found on PATH' >&2; exit 2; fi; s=0; node -e "var e=process.env,c=e.CLAUDE_PLUGIN_ROOT,p=e.PLUGIN_ROOT,v=

• PostToolUse

  if command -v node >/dev/null 2>&1; then exec node -e "var e=process.env,c=e.CLAUDE_PLUGIN_ROOT,p=e.PLUGIN_ROOT,v=(c!==undefined&&c!=='')?'CLAUDE_PLUGIN_ROOT':((p!==undefined&&p!=='')?'PLUGIN_ROOT':'n

• PostToolUse

  if command -v node >/dev/null 2>&1; then exec node -e "var e=process.env,c=e.CLAUDE_PLUGIN_ROOT,p=e.PLUGIN_ROOT,v=(c!==undefined&&c!=='')?'CLAUDE_PLUGIN_ROOT':((p!==undefined&&p!=='')?'PLUGIN_ROOT':'n

• Stop

  if command -v node >/dev/null 2>&1; then exec node -e "var e=process.env,c=e.CLAUDE_PLUGIN_ROOT,p=e.PLUGIN_ROOT,v=(c!==undefined&&c!=='')?'CLAUDE_PLUGIN_ROOT':((p!==undefined&&p!=='')?'PLUGIN_ROOT':'n

Similar plugins