with one click
nuri-quant
nuri-quant contains 6 collected skills from researcherhojin, with repository-level occupation coverage and site-owned skill detail pages.
Skills in this repository
Deploy to Mac Mini production server. Use when asked to "deploy", "๋ฐฐํฌ", "push to production", or "์๋ฒ ๋ฐ์".
STRATEGY ยง2.7 7-phase Flow (ThinkโPlanโBuildโReviewโTestโShipโReflect) orchestrator. **Recommend-only** โ ์๋ chain ์์ด ์ฌ์ฉ์ ํ์ฌ phase ์ถ์ ํ ๋ค์ ์ก์ /์คํฌ ๊ถ๊ณ . ์ฌ์ฉ์๊ฐ "๋ค์ ๋จ๊ณ ๋ญ?", "์ง๊ธ phase ๊ฐ ๋ญ์ผ?", "Reflect ํด์ผ ํ๋?", "Build ๋๋ฌ๋๋ฐ ๋ญ ํด์ผ ํด?" ๊ฐ์ด ์งํ ๋จ๊ณ ์ง๋ฌธ ์ ๋ฐํ. nuri-quant ํ๋ก์ ํธ์ 1 issue = 1 PR โค 3 commits ๋ฃฐ ์ค์ ๋ณด์กฐ.
Code review checklist. Use when asked to "review", "๋ฆฌ๋ทฐ", "์ฝ๋ ๊ฒํ ", or when reviewing a PR diff.
SIEGE predictivity measurement (E4-0b v2) audit ์ฌ์คํ + ํด์ ์ ์ฐจ. Use when re-running 60-month predictivity audit, interpreting gate-level ฮ results, or adding new variant templates. audit route ๋ 2026-04-22 currently closed state โ ์ฌํ์ฑํ ์กฐ๊ฑด ํ์ธ์ฉ.
Pre-commit verification. Use when about to commit, asked to "verify", "๊ฒ์ฆ", "์ปค๋ฐ ์ ํ์ธ", or before any git commit.
LLM ์์ด์ ํธ ์คํจ ํจํด ๋๋ฒ๊น โ ์ฝ๋/ํด ๋ ๋ฒจ (ยง5.1-5.6: hallucination, phantom fix, test illusion, scope creep, context bias, stale number drift) + ๋ํ/์ถ๋ก ๋ ๋ฒจ (ยง5.14.1-2: dataโrecommendation slide, cross-context inconsistency). Use when user reports "test passes but doesn't cover the code", "fix applied but bug persists", "why does this keep failing the same way", "Claude is hallucinating API", "๊ฐ์๊ธฐ ์ถ์ฒํ ์ด์ ๊ฐ ๋ญ๊ฐ์", "์ KR/US ๋ค๋ฅด๊ฒ ์ ์ฉํ๋์", or when a regression test needs a Gotcha-Test Pair citation. Case study narrative: git log of PR #272, #300-#307, session 2026-05-27.