메뉴
Structured trade-off analysis — build/buy/borrow or option comparison with weighted scoring and a firm recommendation
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
| name | tradeoff |
| description | Structured trade-off analysis — build/buy/borrow or option comparison with weighted scoring and a firm recommendation |
User runs /tradeoff with a decision or options to compare.
Also triggers automatically during /review when a significant design choice is flagged.
Run a build/buy/borrow or option-A vs option-B analysis using the format below. Always include a recommended path with explicit reasoning — never leave it "up to you." Flag any [ASSUMPTION] that would change the recommendation if false.
Decision deadline: [if known] Key constraint: [cost / speed / control / compliance / team capability]
| Criterion | Weight | Option A | Option B | Option C |
|---|---|---|---|---|
| Implementation speed | ||||
| Operational complexity | ||||
| Cost (build + run) | ||||
| Vendor/lock-in risk | ||||
| Team capability fit | ||||
| Compliance/governance | ||||
| Scalability ceiling | ||||
| Weighted Score |
Weight scale: High=3, Med=2, Low=1 Score each option 1–5 per criterion, multiply by weight.
Go with: [Option X]
Reason: [2–3 sentences. Be direct.]
[ASSUMPTION] List assumptions that underpin this recommendation.
[Trigger conditions that would make you reconsider — e.g., team grows past X, cost exceeds Y]
Audit a Google ADK tool file against the five known gotchas (DI params, thin wrappers, _j helper, async-wrap blocking calls, httpx context manager) before they bite in production
After creating an ADR, run the cross-referencing checklist — update README Artifacts table, add Related Decisions section to source proposal, cross-link sibling ADRs to each other
Mid-task durability — dump current state and a next-step file before context fills, so the next session resumes without re-deriving where you were
Generate and verify a pre-demo checklist for an ADK/agent project — env vars, GCP auth, embedding swap, ngrok/Slack wiring, dry-run, tests, real-vs-synthetic data
Scan a project's docs (README, CLAUDE.md, ADRs, runbooks) for inconsistent project naming, scope, or framing — catches the "README says retail, CLAUDE.md still says Kroger" class of bug
Refresh a project's status — derive current state from code/tests/git, regenerate the project's status memory entry and (if requested) a status section in the README
