skills/ts-web-tdd-orchestrator/SKILL.md
Plan-first staged TDD orchestration for TypeScript web repositories. Use when a TypeScript, React, Next.js, or Node web task benefits from a short spec, explicit red/green/refactor/verify stages, deterministic validation, and keeping code changes behind explicit user approval. Best suited for small feature additions, policy changes, and bug fixes where tests should act as the primary oracle.
npx skillsauth add strongorange/strong-orange-agent-skills ts-web-tdd-orchestratorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Guide TypeScript web changes through a strict plan-first workflow. Favor staged progress and deterministic gates over one-shot implementation.
package.json, test config, and TypeScript config.AGENTS.md, package scripts, and nearby test files before proposing changes.spec.
red, the minimum implementation expected in green, and the verification commands for verify.진행해, 계획대로 진행, 구현해, 수정해도 돼, or equivalent confirmations as approval to edit.red: add or update only the failing test. Do not edit production code.green: make the smallest production change that passes the approved test. Preserve test intent.refactor: improve structure while preserving passing behavior. Do not expand scope.verify: run deterministic checks and report the result.red, green, and refactor into one edit batch.specbehavior, non-behavior, edge cases, and oracle.red.redskip, todo, .only, or equivalent narrowing shortcuts.greenBLOCKED: test intent needs review, then return to spec or red instead of silently rewriting the test.refactorspec.spec.npm testnpx tsc --noEmitpackage.json.
test, check, or typecheck script.pnpm.spec, report only the compact behavior contract and oracle.red, report the exact failing behavior the test captures.green, report the minimal implementation change.refactor, report only structural cleanups and any preserved invariants.verify, report the commands run, whether they passed, and any residual risk.development
Use when extracting honest resume bullets, 1-minute interview stories, or likely interviewer questions from a defined work period (a project, week, sprint, or custom date range). Collects evidence from git, GitHub, and an Obsidian vault, filters strictly to verified self-attribution, refuses to invent impact metrics, and marks AI-assist where material. Triggers on "이력서 bullet", "주간 회고 이력서", "프로젝트 X 회고 이력서 톤", "포트폴리오 자료 뽑아줘".
data-ai
사람의 주관 판단이 필요한 A/B·before-after·model·prompt·UX·design 품질 비교 평가에서 가벼운 HITL 평가 루프를 설계하고 구현하도록 안내한다. 다음 상황에서 먼저 호출하세요: - "직접 봐야 판단 가능", "A/B 비교", "before/after", "품질 평가", "점수 남기기", "평가 대시보드", "HITL", "리포트 만들기"를 언급 - 자동화 테스트만으로는 품질 판단이 부족하고 사람의 주관이 필요한 경우 - AI 출력, 디자인 생성물, 프롬프트 변경, 파이프라인 변경, UX 후보를 비교할 때 - 평가 결과를 나중에 집계하거나 재개할 수 있어야 하는 경우 구현 스캐폴드가 아니라 가이드형이다. 코드를 바로 만들지 말고 먼저 설계를 확인한다.
tools
Split large git changes into readable, review-friendly, revert-safe commit stacks in Toolditor. Use when preparing a PR, reorganizing staged/unstaged changes, enforcing Korean `[type] message` commit convention, or producing commit history that is easy to review and selectively revert.
development
Decide between Strategy, Template Method, or Hybrid for architecture and refactor tasks across frontend/backend systems. Use when evaluating branching logic, adding new variants/providers/modes, introducing shared execution pipelines, or debating runtime algorithm switching versus fixed skeleton workflows. Trigger especially for AI feature flows and payment/provider integrations where pattern choice affects extensibility, testability, and change risk.