메뉴
Development effort estimation with T-shirt sizing and risk adjustment
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
Multi-expert AI/ML specification review with scoring gate — model architecture, evaluation rigor, safety/alignment, and production readiness for AI systems and LLM apps
Multi-expert architecture review — boundaries, integration patterns, failure modes, evolvability
Multi-expert business analysis with advisory recommendations (no scoring gate)
Multi-expert intelligence pipeline review — discovery quality, ingestion resilience, scoring validity, platform compliance, taxonomy coherence, cost efficiency
Multi-expert mobile/native app specification review with scoring gate — Android, iOS, Swift, SwiftUI
Multi-expert personal-development review with scoring gate — learnability, adoption, human-centeredness, and capability impact for talent/learning/AI-augmentation designs
| name | sh-estimate |
| description | Development effort estimation with T-shirt sizing and risk adjustment |
Estimate development effort for tasks, features, or projects. T-shirt sizing aligned with task management. Risk-adjusted.
Break into concrete sub-tasks:
1. [Sub-task] — [what changes]
2. [Sub-task] — [what changes]
3. Tests — [scope of test coverage needed]
4. Integration — [what needs wiring up]
| Size | Meaning | Typical Scope |
|---|---|---|
| S | Contained change | Single file, clear pattern, < 1 hour |
| M | Multi-file change | 2-5 files, some design needed, 1-4 hours |
| L | Cross-cutting change | 5+ files, new patterns, 4-16 hours |
| XL | Requires breakdown | Too large for single task -- split first |
Identify risk factors that increase effort:
| Risk Factor | Multiplier |
|---|---|
| Unfamiliar code area | 1.5x |
| No existing tests | 1.3x |
| External API dependency | 1.5x |
| Database migration | 1.3x |
| Cross-platform concerns | 1.5x |
| Unclear requirements | 2x |
Apply the highest applicable multiplier (don't stack).
## Estimate: [Feature/Task Name]
### Sub-tasks
| # | Task | Size | Risk | Adjusted |
|---|------|------|------|----------|
| 1 | [task] | M | Unfamiliar (1.5x) | M-L |
| 2 | [task] | S | None | S |
| 3 | Tests | M | No existing (1.3x) | M |
### Overall: [M-L]
### Confidence: [High/Medium/Low]
### Key Assumptions: [list]
### Unknowns: [list — each unknown reduces confidence]
Will: Analyze scope, decompose work, size tasks, identify risks, present estimate. Will not: Execute the work, create timelines, make commitments, or start implementation.
After estimation, user decides priority and scheduling. Proceed with implementation when ready.