add-planning
Create/update plan.md with sequenced tasks, file mapping, dependencies and S/M/L estimates
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Create/update plan.md with sequenced tasks, file mapping, dependencies and S/M/L estimates
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
Consolidated view of the add-pro ecosystem - commands, skills, relationships and dependencies. Loaded by /add as source of truth.
Source of truth for ADD doc rules, depth floors, IDs, refs, validation gate. Load before any doc write.
Use when running agent-judged QA validation (read-PNG by default; the playwright plugin adds live driving) — the Level C judge rubric, severity taxonomy, dual-judge (@ux-agent review ∥ @qa-agent) method, report schema/template, and the config.json/screens.json formats. Consumed by /add.qa and both judges.
Use when a state-materializing command starts or is asked to upgrade — reads the setup receipt, compares the recorded contract against the shipped one, executes the declared upgrade deltas sequentially, and rewrites the receipt even on a verified-current no-op. Consumed by /add.qa-setup STEP 1.5 and STEP 11.
Internal skill for developing ADD framework artefacts (commands, skills, agents, scripts). Use when add-framework--plan analyzes viability of new framework features, when add-framework--build implements framework artefacts, or when creating/modifying commands, skills, or agents. Always use this skill before proposing or implementing changes to the framework itself.
Use when building, styling, or theming UI components, pages, layouts, dashboards, charts, tables, or forms for SaaS products.
| name | add-planning |
| description | Create/update plan.md with sequenced tasks, file mapping, dependencies and S/M/L estimates |
Skill for creating technical implementation plans. Creates/updates plan.md with tasks, file mapping and estimates.
Principle: Concrete, executable plan — not a wishlist.
plan.mdplan.md exists but incomplete → fill missing tasksabout.md (document the feature first)discovery.md (run feature discovery first)# Read feature documentation
cat docs/features/[FEATURE_ID]/about.md
cat docs/features/[FEATURE_ID]/discovery.md
cat docs/features/[FEATURE_ID]/design.md # if it exists
Extract:
Breakdown rules:
| Size | Criteria | Action |
|---|---|---|
| Simple | 1–3 files, no deps | Single task |
| Medium | 4–10 files, sequential deps | Tasks per layer |
| Large | >10 files, multiple domains | Separate batches |
Default order (bottom-up):
1. Domain (entities, enums, types)
2. Database (migrations, repositories)
3. Business (services, use-cases)
4. API (controllers, DTOs, validators)
5. Frontend (components, hooks, stores)
6. Integration (tests, e2e)
Scale:
S = Small → 1-2 files, localized change
M = Medium → 3-5 files, moderate logic
L = Large → 6+ files, complex logic
Complexity signals:
Template plan.md (Technical Style):
# Plan: [Feature Name]
Technical plan for implementing [feature]. Based on about.md and discovery.md.
---
## Spec
### Context
{"feature":"[ID]","branch":"feature/[ID]-[name]","deps":["package@version"],"estimate":"[S/M/L]"}
### Files
{"create":["path/file1.ts","path/file2.ts"],"modify":["path/existing.ts"]}
### Tasks
[{"id":1,"task":"Create entity [Name]","estimate":"S","deps":[]},{"id":2,"task":"Create migration","estimate":"S","deps":[1]},{"id":3,"task":"Create repository","estimate":"S","deps":[2]},{"id":4,"task":"Create service","estimate":"M","deps":[3]},{"id":5,"task":"Create controller + DTOs","estimate":"M","deps":[4]},{"id":6,"task":"Create UI components","estimate":"M","deps":[5]},{"id":7,"task":"e2e tests","estimate":"S","deps":[6]}]
---
## Detailed Tasks
### Task 1: Create entity [Name]
**Estimate:** S
**Files:** `libs/domain/src/entities/[Name].ts`
**Deps:** None
**Checklist:**
- [ ] Fields per about.md
- [ ] Enums if needed
- [ ] Export in index.ts
---
### Task 2: Create migration
**Estimate:** S
**Files:** `libs/app-database/src/migrations/[timestamp]-[name].ts`
**Deps:** Task 1
**Checklist:**
- [ ] Table with fields
- [ ] Required indexes
- [ ] Foreign keys
---
[... continue for each task ...]
---
## Batching (if applicable)
**Batch 1: Foundation**
- Tasks 1-3 (domain + database)
- Commit: "feat([feature]): add [Name] entity and repository"
**Batch 2: Business Logic**
- Tasks 4-5 (service + API)
- Commit: "feat([feature]): add [Name] service and endpoints"
**Batch 3: Frontend**
- Task 6 (UI)
- Commit: "feat([feature]): add [Name] UI components"
**Batch 4: Quality**
- Task 7 (tests)
- Commit: "test([feature]): add e2e tests for [Name]"
---
## Risks and Mitigations
- **[Risk from discovery.md]:** [mitigation in plan]
---
## Metadata
{"updated":"YYYY-MM-DD","sessions":N,"by":"[subagent]"}
Checklist before saving:
| Task count | Strategy |
|---|---|
| <5 tasks | Single batch |
| 5–10 tasks | 2–3 batches per layer |
| >10 tasks | Batches per domain/module |
Commit rules: one semantic commit per batch — see add-commit skill for Conventional Commits type detection and message logic.
Do: base tasks on about.md and discovery.md; include dependencies; estimate every task (S/M/L); use concrete paths; one semantic commit per batch.
Don't: vague tasks ("implement feature"); estimates without criteria; ignore dependencies; plan without prior docs; batches >5 tasks.