Use when the user's request is too vague or ambiguous to act on safely, even if they haven't explicitly asked for clarification. Also use when another skill says "clarify first" or when jumping to implementation would be risky because the problem statement isโฆ
onejaejae/skills
SkillsMP has collected 91 skills from onejaejae/skills. Open a skill to review its source and details.
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 91
- GitHub stars
- 2
- GitHub forks
- 0
Skills in this repository
Showing 40 of 91 collected skills.
any input (code, docs, papers, images) โ knowledge graph โ clustered communities โ HTML + JSON + audit report
Migrate Notion pages or child pages into Jira subtasks. Use when the user says "๋ ธ์ ํ์ด์ง๋ฅผ ์ง๋ผ ํ์์์ ์ผ๋ก ์ฎ๊ฒจ์ค", "๋ ธ์ ํ์ ํ์ด์ง๋ฅผ ์๋ธํ์คํฌ๋ก", "notion to jira", "jira subtask๋ก ์ด์", "ํ์ ์์ ์ถ๊ฐ", "์ง๋ผ๋ก ์ฎ๊ฒจ", or provides a Notion page URL and a Jira parent issue together. Prefer aโฆ
Source text: Korean
Use when the user wants to read, summarize, analyze, compare, or ask questions about a PDF and the built-in PDF reader produces noisy or incomplete results. Also use when the user mentions PDF parsing, markdown extraction, OCR, scanned PDFs, or preparingโฆ
Use when the user shares a YouTube video URL and wants transcript extraction, a structured digest, expanded insights, a quality audit, or a polished Notion page. Trigger on requests like "์ ํ๋ธ ์์ ์ ๋ฆฌ", "์์ ์คํฌ๋ฆฝํธ ๊ฐ์ ธ์", "์ด ์ ํ๋ธ ๋ ธ์ ์ ์ ๋ฆฌ", "transcript this YouTubeโฆ
GitHub Draft PR ์์ฑ ์คํฌ. push ์ ์ lint/ํฌ๋งท ๊ฒ์ดํธ, ์ปค๋ฐ ๋ฉ์์ง ์ปจ๋ฒค์ , ํ ์คํธ ์์ ์ฑ ํ์ธ ๊ฐ์ pre-flight ์ฒดํฌ๋ฅผ ๋จผ์ ๋๋ฆฐ ๋ค draft PR์ ์์ฑํ๋ค. Use when "PR ์์ฑ", "PR ์ฌ๋ ค์ค", "draft PR", "gh pr create", "/ship", "ํ๋ฆฌํ์คํธ ๋ง๋ค์ด์ค", "create PR", "open PR", "PR ์ด์ด์ค", "PR ๋ง๋ค์ด", "pushํ๊ณ PR ์ฌ๋ ค์ค", "์ฝ๋ ์ฌ๋ ค์ค",โฆ
Source text: Korean
Snowflake Korea Hackathon 2026 ํ ํฌํธ๋ ๊ณต์ ํ๊ฐ ๊ธฐ์ค(5 ์นดํ ๊ณ ๋ฆฌ ร 3 ํญ๋ชฉ ร 4 ์ฒดํฌํฌ์ธํธ = 60์ ๋ฃจ๋ธ๋ฆญ)์ผ๋ก ์ ํ์ ์ง์ ํ๊ฐ/๊ฐ์ ํ๋ค. ์ฆ๊ฑฐ ๊ธฐ๋ฐ ์ฒดํฌํฌ์ธํธ ์ฑ์ โ action plan ์์ฑ โ dry-run diff โ ์ฌ์ฉ์ ์น์ธ โ ์ผ๊ด ๊ตฌํ โ ์ฌํ๊ฐ ๋ฃจํ. 95์ ๋ฌ์ฑ OR 3 cycle ์๋ ด OR ๋ง๊ฐ 4์๊ฐ ์ ์ข ๋ฃ. ์ด ํ๋ก์ ํธ(์ด์ฌ ๊ฒฐ์ AI ์๋ฎฌ๋ ์ดํฐ) ์ ์ฉ.
Source text: Korean
Use when the user asks for restaurant recommendations with trust/ad concerns, date spot suggestions, reliable dining places, or HIDDEN GEM spots. Triggers on: "๋ง์ง ์ถ์ฒ", "๋ฐ์ดํธ ๋ง์ง", "๊ด๊ณ ์๋ ๋ง์ง", "์ง์ง ๋ง์ง", "๋ฏฟ์๋งํ ๋ง์ง", "๋ฐ์ด๋ด ๋ง๊ณ ", "์ฒดํ๋จ ์๋", "๋ธ๋ก๊ทธ ๊ด๊ณ ๋ง๊ณ ", "๋ฐ์ดํธ ์ฅ์", "๊ธฐ๋ ์ผโฆ
Source text: Korean
Use when "/jira:assess", "์ง๋ผ ์ค์ฝํ", "์ง๋ผ ์ํฅ๋", "์ฝ๋๋ฒ ์ด์ค ๋ถ์", "jira assess", "jira scope", "ticket scope", "impact assessment", "์ค์ฝํ ๋ถ์ํด์ค", "์ํฅ๋ ๋ถ์", "์ฝ๋ ์ํฅ ๋ถ์", "์ด ํฐ์ผ ์ฝ๋๋ฒ ์ด์ค์์ ๋ญ ๋ฐ๊ฟ์ผ ํด". Also use as the second step after /jira:recon completes.
Source text: Korean
Use when "/jira:dispatch", "์๋ธํ์คํฌ ์์ฑ", "์ง๋ผ ํ์คํฌ ์์ฑ", "jira dispatch", "jira subtask", "create subtasks", "ํ์คํฌ ๋์คํจ์น", "์ด ํ์คํฌ๋ค ์ง๋ผ์ ์ฌ๋ ค์ค", "์๋ธํ์คํฌ ๋ง๋ค์ด์ค". Also use as the final step after /jira:assess completes.
Source text: Korean
Use when "/jira:ops", "์ง๋ผ ์คํผ๋ ์ด์ ", "์ง๋ผ ์ ์ฒด ํ์ดํ๋ผ์ธ", "jira ops", "jira pipeline", "ํฐ์ผ ์ฒ๋ฆฌ", "ํฐ์ผ ์ ์ฒด ํ๋ก์ธ์ค", "์ด ํฐ์ผ ๋ถ์๋ถํฐ ์๋ธํ์คํฌ๊น์ง", "๋ฆฌ์์น๋ถํฐ ๋์คํจ์น๊น์ง".
Source text: Korean
Use when "/jira:recon", "์ง๋ผ ๋ฆฌ์์น", "์ง๋ผ ๋ถ์", "ํฐ์ผ ๋ถ์", "ํฐ์ผ ๋ฆฌ์์น", "์ง๋ผ ์ ๋ฆฌ", "jira research", "jira recon", "ticket research", "analyze jira ticket", "์ด ํฐ์ผ ์ ๋ฆฌํด์ค", "JIRA ํฐ์ผ ์กฐ์ฌ". Also use when the user shares a Jira URL containing "atlassian.net/browse/" and asks forโฆ
Source text: Korean
Use when the user says "logged in Chrome", "my browser session", "current Chrome profile", "persistent user-data-dir", "already signed in", or asks for a private LinkedIn, Notion, X, Slack, SSO dashboard, paywalled page, chromux, cookies, or JS-heavy pageโฆ
๋น์ฆ๋์ค ๊ด์ ์์ ์์ด๋์ด/๊ณํ์ ๊ฒ์ฆํ๋ ์คํฌ. ๊ธฐ์ ์ ํ๋น์ฑ์ด ์๋๋ผ "์ด๊ฑธ ์ ๋ง๋๋๊ฐ?", "ROI๋?", "์ค์ฝํ๊ฐ ์ ์ ํ๊ฐ?" ๊ด์ ์์ 10๊ฐ ํ์ ์ง๋ฌธ์ ๋ตํ๊ณ BUILD/PIVOT/KILL ํ์ ์ ๋ด๋ฆฐ๋ค. /plan-eng-review๊ฐ ๊ธฐ์ ๋ฆฌ๋ทฐ๋ผ๋ฉด, /plan-ceo-review๋ ๋น์ฆ๋์ค ๋ฆฌ๋ทฐ. Use when: "/plan-ceo-review", "CEO ๋ฆฌ๋ทฐ", "๋น์ฆ๋์ค ๋ฆฌ๋ทฐ", "์ด๊ฑฐ ๋ง๋ค ๊ฐ์น๊ฐ ์์ด?", "ROI ๋ถ์", "์ค์ฝํโฆ
Source text: Korean
Forced 20-question engineering plan review before high-risk work begins. Reads the plan, answers ALL 20 questions with evidence from the codebase, and produces a READY/NEEDS_WORK/NOT_READY verdict with an action-item list. Use PROACTIVELY before starting anyโฆ
PR diff๋ฅผ ๋ฐ์ ์ฝ๋ ๋ฆฌ๋ทฐ ์๋ ์์ฝ์ ์์ฑํ๋ ์คํฌ. ํต์ฌ ๋ณ๊ฒฝ์ ์ 3์ค๋ก ์์ฝํ๊ณ , ๋ณ๊ฒฝ ํ์ผ๋ณ๋ก what changed / why it matters / risk level์ ์ ๋ฆฌ. Use when: "PR ์์ฝ", "diff ์์ฝ", "PR ๋ณ๊ฒฝ์ ์ ๋ฆฌ", "์ฝ๋ ๋ณ๊ฒฝ ์์ฝ", "summarize PR", "PR summary", "diff summary", "what changed in this PR", "๋ณ๊ฒฝ์ ์์ฝํด์ค", "PR ํต์ฌ ์ ๋ฆฌ",โฆ
Source text: Korean
PR ๋ฆฌ๋ทฐ ์ํฌํ๋ก์ฐ์ ์ฒดํฌ๋ฆฌ์คํธ๋ฅผ ์ ๊ณตํ๋ ์คํฌ. "PR ๋ฆฌ๋ทฐํด์ค", "์ฝ๋ ๋ฆฌ๋ทฐ ํด์ค", "์ด PR ๋ด์ค", "review this PR" ๋ฑ PR ๋ฆฌ๋ทฐ ์์ฒญ ์ ์ฌ์ฉ. GitHub/GitLab PR URL ๋๋ ๋ก์ปฌ ๋ธ๋์น diff๋ฅผ ๊ธฐ๋ฐ์ผ๋ก ์ฒด๊ณ์ ์ด๊ณ ์ผ๊ด๋ ๋ฆฌ๋ทฐ๋ฅผ ์ํ. ์ฝ๋ ํ์ง, ์์ ์ฑ/๋ณด์, ์ฑ๋ฅ, ํ ์คํธ, ๋ฌธ์ํ ๊ด์ ์์ ๊ฑด์ค์ ์ธ ํผ๋๋ฐฑ ์ ๊ณต.
Source text: Korean
CLAUDE.md ๊ธฐ๋ฐ ํ๊ฒฝ ์์ ์ฒดํฌ. ์์ ์์ ์ ์ ํ๋ก์ ํธ์ ์์ ๊ท์น, ์ปจ๋ฒค์ , ํ๊ฒฝ ์ค์ ์ ์๋ ๊ฒ์ฆํ์ฌ CLEAR/WARNING/BLOCKED ์ํ๋ฅผ ๋ณด๊ณ ํ๋ค. /check๊ฐ "๋ณ๊ฒฝ ํ ๊ฒ์ฆ"์ด๋ผ๋ฉด, /pre-flight๋ "์์ ์ ํ๊ฒฝ ๊ฒ์ฆ"์ด๋ค. Use PROACTIVELY before starting work, especially after switching branches, pulling changes, or resuming aโฆ
Source text: Korean
Use when ์ด๋ ฅ์ PDF๋ฅผ ๋ฐ์ A-Z ๋ถ์์ด ํ์ํ ๋. ๋ฉํ ์ ์ฉ ๋ถ์ ๋ฆฌํฌํธ + ๋ฉํ ๋ง ์ฝ์นญ ์ ๋ต์ ์์ฑ. "์ด๋ ฅ์ ๋ฆฌ๋ทฐ", "์ด๋ ฅ์ ๋ถ์", "์ด๋ ฅ์ ํผ๋๋ฐฑ", "์ด๋ ฅ์ ๋ด์ค", "์ด๋ ฅ์ ์ฒจ์ญ", "resume review" ํธ๋ฆฌ๊ฑฐ.
Source text: Korean
Use when starting a work session and you need to lock down the target branch, PR, scope, and approach before making any changes. Prevents pushing to wrong branches, modifying out-of-scope files, or losing context between sessions. Use when: "/session-init",โฆ
Source text: Korean
Verify Streamlit in Snowflake (SiS) app deployment automatically by attaching to chromux's CDP port and driving the cross-origin iframe directly. Use after `snow streamlit deploy` succeeds, BEFORE asking the user to confirm. Detects render errors, exercisesโฆ
Source text: Korean
Unified orchestrator for creating high-quality Claude Code skills through iterative test-score-improve loops. Chains define โ research/clarify โ plan โ create โ test โ score โ improve in a single pipeline with multi-model evaluation and automatic improvementโฆ
Source text: Mixed languages
3๋จ๊ณ ๊ธฐํ ํ์ดํ๋ผ์ธ์ ์์ฐจ ์คํํ๋ค: spec-interview โ spec-generator โ spec-reviewer. ์ ์ฒด ํ์ดํ๋ผ์ธ์ ํ ๋ฒ์ ๋๋ฆฌ๊ฑฐ๋, ํน์ ๋จ๊ณ๋ถํฐ ์์ํ ์ ์๋ค. ์ ํ๋ณ ๋๋ฉ์ธ knowledge + ์ฝ๋๋ฒ ์ด์ค ์์ฝ์ context๋ก ์ฃผ์ ํ์ฌ ์ฐ์ถ๋ฌผ quality๋ฅผ ๋์ธ๋ค. Triggers: "๊ธฐํ ํ์ดํ๋ผ์ธ", "spec pipeline", "๊ธฐํ ์ ์ฒด ํ๋ก์ธ์ค", "์๊ตฌ์ฌํญ๋ถํฐ ๋ฆฌ๋ทฐ๊น์ง", "spec ์ ์ฒด", "๊ธฐํ์โฆ
Source text: Korean
Use when a spec or planning document needs development-readiness validation. Detects missing edge cases, state transitions, data constraints, and gives PASS/FAIL judgment. For developers reviewing specs or planning teams wanting pre-development qualityโฆ
Source text: Korean
์คํฌ๋ฆฐ์ท vs ๋ ํผ๋ฐ์ค ์ด๋ฏธ์ง ๋น๊ต๋ฅผ ํตํ ์๊ฐ์ QA ํ์ ์คํฌ. ๋์์ธ ์์(Figma export ๋ฑ)๊ณผ ์ค์ ๊ตฌํ ์คํฌ๋ฆฐ์ท์ ๋น๊ตํ์ฌ score/verdict/differences/suggestions๋ฅผ ๊ตฌ์กฐํ๋ JSON์ผ๋ก ๋ฐํํ๋ค. Ralph ๋ฃจํ์ ํตํฉํ์ฌ 90+ ์ ์๊น์ง ๋ฐ๋ณต ๊ฐ์ ํ ์ ์๋ค. Use when: "/visual-verdict", "๋น์ฃผ์ผ ์ฒดํฌ", "๋์์ธ ๋น๊ต", "์คํฌ๋ฆฐ์ท ๋น๊ต", "visual check", "visualโฆ
Source text: Korean
Use when the user wants thorough alignment before building and a quick discussion or single clarification pass isn't enough. Use for exposing hidden assumptions, removing ambiguity, or fully syncing on what to build. Triggers: "๋ฅ ์ธํฐ๋ทฐ", "์ ๋๋ก ์ฑํฌ ๋ง์ถ์", "๊ฐ์ โฆ
Source text: Korean
Use when ์ฌ์ฉ์๊ฐ URL/๋งํฌ๋ฅผ ๊ณต์ ํ๊ณ ์ดํด๋ฅผ ์ํ ๋. Triggers: "/digest", "์ด๊ฑฐ ์ฝ์ด์ค", "์ด ๊ธ ์ค๋ช ํด์ค", "๋งํฌ ๋ถ์", "digest this", "์ด๊ฑฐ ๋ญ์๋ฆฌ์ผ", "์์ฝํด์ค", "์ด ๊ธ ๋ญ ๋ด์ฉ์ด์ผ", "์ฝ๊ณ ์ ๋ฆฌํด์ค", "์ด ์ํฐํด ๋ถ์ํด์ค", "what does this article say", "explain this link", "์ด๊ฑฐ ๋ญ์ผ", "์ฝ๊ธฐ ๊ท์ฐฎ์", "์ ๋ฆฌํด์ค". ๋จ์ ์์ฝ ์์ฒญ("์์ฝํด์ค")์ด๋ผ๋โฆ
Source text: Korean
ํ์์๊ฒ ์์ ๋ด์ฉ์ ๊ณต์ ํ๋ Google Chat ๋ฉ์์ง๋ฅผ ์์ฑํ๋ ์คํฌ. Use when: "์์ ๊ณต์ ", "ํ ๊ณต์ ", "work share", "ํ์ํํ ์๋ ค์ค", "๊ณต์ ๋ฉ์์ง ์จ์ค", "์์ ๋ด์ฉ ์ ๋ฆฌํด์ค", "ํ์ ๊ณต์ ํ ๋ฉ์์ง", "ํ๊ณ ๊ณต์ ", "์์ ๋ณด๊ณ ", "์งํ ์ํฉ ๊ณต์ ", "์๊ฒฌ ์์ฒญ ๋ฉ์์ง", "ํธ๋ฌ๋ธ์ํ ๊ณต์ ", "์๋ฃ ๋ณด๊ณ ". ์์ ๊ด๋ จ ๋ด์ฉ์ ํ์์๊ฒ ์ ๋ฌํด์ผ ํ ๋ ์ด ์คํฌ์ ์ฌ์ฉํ๋ผ. ์ฌ์ฉ์๊ฐ "์ ๋ฆฌํด์ค", "๊ณต์ ํด์ผโฆ
Source text: Korean
Use when user asks about calendar, schedule, or agenda. Triggers: '์ค๋ ์ผ์ ', '์ด๋ฒ ์ฃผ ์ผ์ ', '๋ด์ผ ๋ญ ์์ด', 'calendar', '์บ๋ฆฐ๋', '์ผ์ ํ์ธ', '์ค์ผ์ค', 'what do I have today'.
Source text: Korean
Use after deploying code to production or staging for real-time monitoring with baseline comparison and health scoring. Observation only โ no code changes during monitoring. Triggers: "/canary", "canary check", "post-deploy watch", "๋ฐฐํฌ ํ ๋ชจ๋ํฐ๋ง", "์นด๋๋ฆฌ", "๋ฐฐํฌโฆ
Use when performing security audits, vulnerability scanning, or threat modeling. Two modes: Daily (zero-noise quick scan) and Comprehensive (monthly deep audit). Observation only โ no code changes, no exploitation. Triggers: "/cso", "security audit", "๋ณด์ ์ ๊ฒ",โฆ
Use when debugging complex, intermittent, or hard-to-reproduce bugs that resist simple fixes. Systematic hypothesis-driven investigation with scope lock and 3-strike escalation. Triggers: "/investigate", "investigate this", "deep debug", "์กฐ์ฌํด์ค", "์์ธ ๋ถ์", "๊ฐํ์ โฆ
This skill should be used when the user wants to verify their changes before pushing, or update the project's rule checklists. Phase 1: validate changed files against .dev/rules/ checklists and report PASS/WARN. Phase 2 (conditional): propose rule additionsโฆ
This skill should be used when the user says "/compound", "compound this", "document learnings", "save what we learned", or after completing a PR. Extracts knowledge from PR context and saves to docs/learnings/.
Deep web research skill using parallel subagents + chromux browser-explorer + Gemini. Spawns multiple WebSearch research agents AND browser-explorer agents (via chromux for JS-heavy/dynamic sites), plus a Gemini CLI deep research source, then synthesizesโฆ
Spec-driven orchestrator that reads spec.json via cli, routes by meta.type, and dispatches agents/skills accordingly. spec.json-native execution (no PLAN.md). Use when: "/execute", "execute", "์คํํด์ค", "์คํ ์คํ"
Google search via real Chrome browser (chromux). Use when the user asks to "search Google", "๊ตฌ๊ธ ๊ฒ์", "๊ตฌ๊ธ์์ ์ฐพ์์ค", "find articles about", "search the web for", or needs web search results with full page content. Also trigger when: searching a specific siteโฆ
Notion AI Articles Curation DB์ ์ํฐํด ๋งํฌ๋ฅผ ์ถ๊ฐํ๋ ์คํฌ. Use when "์ํฐํด ์ถ๊ฐ", "๋งํฌ ์ถ๊ฐ", "article curation", "ํ๋ ์ด์ ", "๋งํฌ ์ ๋ฆฌํด์ค", "์ด ๋งํฌ๋ค ๋ ธ์ ์ ์ถ๊ฐ", "์ํฐํด ํ๋ ์ด์ ", "add articles".
Source text: Korean
This skill should be used when the user asks about "technical decision", "what to use", "A vs B", "comparison analysis", "library selection", "architecture decision", "which one to use", "tradeoffs", "tech selection", "implementation approach", or needsโฆ
Fast parallel change-scope analyzer. Launches 5+ agents concurrently to identify what files need changing, what could break, and the recommended approach. Lighter than /specify โ no interview, no spec.json, just a quick scoped report. Use this skill wheneverโฆ