with one click
gprecious-marketplace
gprecious-marketplace contains 31 collected skills from gprecious, with repository-level occupation coverage and site-owned skill detail pages.
Skills in this repository
Convert raw feature requirements, bug reports, or rough task descriptions into a goal-optimized prompt for the agentic coding tool that will run it โ Claude Code or OpenAI Codex. ๊ฑฐ์น ์๊ตฌ์ฌํญยท๋ฒ๊ทธ ๋ฆฌํฌํธยท๋์ถฉ ์ ์ ์์ ์ค๋ช ์, ๊ทธ ์์ ์ ์ค์ ๋ก ์คํํ ์ฝ๋ฉ ์์ด์ ํธ(Claude Code ๋๋ Codex)์ ๋ง์ถ goal ์ต์ ํ ํ๋กฌํํธ๋ก ๋ณํํ๋ค. Use when the user wants a requirement shaped into a prompt/spec/goal for an agent โ "์ด๊ฑฐ ํ๋กฌํํธ๋ก ๋ง๋ค์ด์ค / ๋ณํํด์ค", "์ฝ๋ฑ์ค(codex)/ํด๋ก๋์ฝ๋์ฉ์ผ๋ก", "๋ชฉํยท๋ฒ์ยท์๋ฃ์กฐ๊ฑด ๊ฐ์ถ ํ๋กฌํํธ๋ก" โ or mentions the goal feature or /goal command. By default targets the agent running the skill (Claude Code โ Claude-optimized, Codex โ Codex-optimized); honors an explicit named target. Proactively fire on vague requirements headed to a coding agent ("๋์๋ณด๋ ๋น ๋ฅด๊ฒ ํด์ค", "add auth", "๋ก๊ทธ์ธ ๋ฒ๊ทธ ๊ณ ์ณ์ค"). Not for implementing/debugging it yourself, codex code review, explaining /goal, translating, editing AGENTS.md, multi-agent orchestration (cmux/herdr), or writing a plan.
Use when the user wants to turn a repetitive, reviewable task into a controlled agent loop โ phrases like "์ด๊ฑฐ ์๋ํ/๋ฐ๋ณตํ๊ณ ์ถ์ด", "๋ฃจํ๋ก ๋๋ฆฌ๊ณ ์ถ์ด", "์ ๊ธฐ์ ์ผ๋ก ์ ๊ฒํ๊ฒ ํด์ค", "loop engineering", "agent loop ์ค๊ณ", or wants to audit existing loops ("๋ฃจํ ์ ๊ฒ", "loop audit"). Designs a loop with triggerยทstateยทverificationยทhuman-gateยทstop + 7 guardrails + 6 metrics, maps it onto an existing engine (herdr/loop/Cron/Workflow/Codex Automations), and writes a spec to docs/loops/. Does NOT execute loops itself and is NOT for one-off prompts (use goalcraft) or multi-agent run orchestration (use herdr/cmux).
Convert a recurring or repetitive task description into a Claude Code /loop prompt โ the loop sibling of goalcraft. ๋ฐ๋ณตยท์ฃผ๊ธฐ์ ์์ ์ค๋ช ์ Claude Code /loop ์ฉ ํ๋กฌํํธ๋ก ๋ณํํ๋ค(goalcraft์ loop ํ์ ). Use when the user wants a task shaped into a /loop prompt โ "๋ฃจํ ํ๋กฌํํธ๋ก ๋ง๋ค์ด์ค", "/loop ์ฉ์ผ๋ก", "์ฃผ๊ธฐ์ ์ผ๋ก ๋ฐ๋ณตํ๊ฒ", "๋งค N๋ถ๋ง๋ค ~", "~๊น์ง ๋ฐ๋ณตํด์", "์ด๊ฑฐ loop์ผ๋ก ๋๋ ค์ค" โ or mentions the /loop command, recurring/scheduled in-session execution, or babysitting/polling a long-running thing. Picks the mode (fixed interval โ cron, self-paced โ model self-paces, or loop.md default) and bakes in an objective stop condition, an iteration ceiling, and a verification check. Proactively fire on recurring-execution requests ("๋ฐฐํฌ ๋๋ ๋๊น์ง ํ์ธ", "CI ํต๊ณผํ ๋๊น์ง ๋ฐ๋ณต", "keep checking the deploy"). Not for single-shot tasks or /goal until-condition prompts (โ goalcraft, which owns /goal), running the loop yourself, deciding whether something should be a loop or auditing loop governance (โ loop-engineering), translating, or explaining /loop.
Use when creating, revising, or critiquing frontend UI (web or mobile) where visual quality, product fit, design-system fidelity, or avoiding generic "AI-slop" output matters โ e.g. "make this look good", "why does this look AI-generated", building a landing page / app screen / dashboard, or a design pass on existing UI. Turns vague design intent into a decision-first workflow: classify the surface, decide direction before code, escape default looks, build to measurable craft standards, and verify the rendered result. Portable across Claude Code and Codex.
Use when the user asks to inspect, summarize, explain, configure, connect, curate, or troubleshoot the session-journal Obsidian logging workflow for Claude Code or Codex โ including pointing it at an existing/Obsidian-Sync vault, keeping AI-generated notes distinct from hand-authored ones, multi-machine setup, distilling durable knowledge, or verifying the vault config.
Use when the user asks to save durable lessons from session-journal into the LLM-Wiki, collect mistakes or insights from agent work, create reviewable wiki draft candidates, or report those draft candidates to Slack.
Use when the user wants to add or generate an E2E / verification test harness for a project โ especially "์์ด์ ํธ๊ฐ ์์ฑยท๊ฒ์ฆยท์๊ฐ์์ ํ๋" Playwright E2E for web apps (Next.js/Vite/Remix/SvelteKit), or a verification-harness methodology for non-web (CLI/API). Detects the stack, picks a recipe, co-authors critical flows with the user, scaffolds config+seed+specs+heal docs, wires an AGENTS.md pointer so future agents auto-run the harness after changes, and runs it. Works in Claude Code and Codex.
Use when the user explicitly asks for herdr-based multi-agent orchestration, multiple visible Claude/Codex worker panes, or cross-CLI comparison inside herdr, especially when workers need distinct CLI/account/browser state.
์คํ ์ด ์ฌ์ฌ ๊ฑฐ์ ๋์. ๊ฑฐ์ ์ฌ์ ๋ถ์, ๋ฉํ๋ฐ์ดํฐ ์๋ ์์ , ์ฌ์ ์ถ.
์คํ ์ด ์คํฌ๋ฆฐ์ท ์์ฑ ๋ฐ ์ ๋ก๋. ํ ํ๋ฆฟ ๊ธฐ๋ฐ ํฉ์ฑ ํ Fastlane์ผ๋ก ์ ๋ก๋.
์ฑ์คํ ์ด/ํ๋ ์ด์คํ ์ด ์ฌ์ฌ ์ํ ํ์ธ. iOS App Store ์ฌ์ฌ ์ํ, Android Play Store ํธ๋ ์ํ ์กฐํ.
generate-copy ์ฐ์ถ๋ฌผ๊ณผ ํฌ๋ฆฌ์์ดํฐ๋ธ ๊ท๊ฒฉ์ ๋ฐํ์ผ๋ก Meta, Google Ads, Naver ๊ด๊ณ ์บ ํ์ธ ๋น๋์ DRAFT ์ํ๋ก๋ง ํ๋๋ฅผ ์ ๋ ฅํ๊ณ campaign-draft-<channel>.md/.json์ ๋ง๋ ๋ค. "์บ ํ์ธ ์ด์ ์ ๋ ฅ", "๊ด๊ณ ์ธํ ์ด์", "๋ฉํ ์บ ํ์ธ ๋๋ํํธ", "๊ตฌ๊ธ ๊ด๊ณ ์ด์", "๋ค์ด๋ฒ ์บ ํ์ธ ์ ๋ ฅ", "๊ด๊ณ ์บ ํ์ธ ๋๋ํํธ" ๊ฐ์ ์์ฒญ์ ๋ฐ๋ํ๋ค.
.growth-marketer/<slug>/ ์๋์ service-profile.json, channel-scores.json, copy/*, playbook-*, cro-audit-* ์ฐ์ถ๋ฌผ์ ๋ฐํ ์ ์ผ๊ด์ฑ QA๋ก ์ ๊ฒํ๋ค. ๋ธ๋๋ ๋ณด์ด์ค, ๋ฉ์์งยทํค ์ผ๊ด์ฑ, claim/evidence ๋ฌด๊ฒฐ์ฑ, ์ฑ๋ ์ ํฉ์ฑ, dark-pattern ์ํ์ ๊ฒํ ํ๊ณ review-checklist.md + review-checklist.json ์ ๋ง๋ ๋ค. "์ผ๊ด์ฑ ๊ฒํ ", "์์ฐ QA", "๋ธ๋๋ ๋ณด์ด์ค ์ ๊ฒ", "๋ฐํ ์ ์ฒดํฌ", "๋ฆฌ๋ทฐ ์ฒดํฌ๋ฆฌ์คํธ" ๊ฐ์ ์์ฒญ์ ๋ฐ๋. ์ด ๊ฒฐ๊ณผ๋ draft-campaign ์ publish gate ์ด๋ฉฐ gate_status ๊ฐ pass ์ฌ์ผ ๋ค์ ๋จ๊ณ๋ก ๊ฐ๋ค.
service-profile.json ์ ๋ฐํ์ผ๋ก ๊ด๊ณ ๋ฌธ๊ตฌ, CTA, ๋๋ฉ ์นดํผ, ์ด๋ฉ์ผ ์ํ์ค, ์ค๊ฐ๋ ์์ ์นดํผ๋ฅผ ์ธ์ง์ฌ๋ฆฌ ๊ธฐ๋ฐ์ผ๋ก ์์ฑํ๊ณ ๊ฐ ๋ณํ์ technique id + source ref ๋ฅผ ์ฃผ์์ผ๋ก ๋จ๊ธด๋ค. "์นดํผ ์จ์ค", "๊ด๊ณ ๋ฌธ๊ตฌ ๋ง๋ค์ด", "๋๋ฉ ์นดํผ", "์ด๋ฉ์ผ ์ํ์ค", "์ธ์ง์ฌ๋ฆฌ ๊ธฐ๋ฐ ์นดํผ", "A/B ์นดํผ", "์ ํ ์นดํผ" ๊ฐ์ ์์ฒญ์ ๋ฐ๋. analyze-service ์ downstream skill ์ด๋ค.
analyze-service ๊ฐ ๋ง๋ service-profile.json ์ ์ ๋ ฅ์ผ๋ก ๋ฐ์ ์ ํ ์ฑ๋์ ์ด์ ํ๋ ์ด๋ถ์ ๋ง๋ ๋ค. baked ์ฑ๋ reference ๋ฅผ ์๋น์ค ICP, ํฌ์ง์ ๋, market, price_model, discovery_intent ์ ๋ง์ถฐ ํ ์ผ๋ฌ๋งํ๊ณ .growth-marketer/<slug>/playbook-<channel>.md ์ ๊ฒ์ฆ์ฉ playbook-<channel>.json ์ ์ ์ฅํ๋ค. "์ฑ๋ ํ๋ ์ด๋ถ", "๋ฉํ ๊ด๊ณ ์ด๋ป๊ฒ ์ธํ ", "๋ค์ด๋ฒ ๊ด๊ณ ํ๋ ์ด๋ถ", "์ด ์ฑ๋ ์ด์ ๊ฐ์ด๋", "ASO ํ๋ ์ด๋ถ", "SEO ์ฝํ ์ธ ์ด์ ๊ฐ์ด๋", "๋ฆฌํ๊ฒํ ์ธํ " ๊ฐ์ ์์ฒญ์ ๋ฐ๋.
๋๋ฉํ์ด์ง, ๊ฐ์ ํ๋ก์ฐ, ํผ, checkout, ํ์ด์์ ์ฐ๊ฒฐ๋ ๋ธ๋ผ์ฐ์ ๋ก ์ฝ๊ธฐ ์ ์ฉ ์ ๊ฒํ๊ณ CRO ๋ฒ ์คํธํ๋ํฐ์ค ๋๋น ์ ํ ๋ง์ฐฐ์ ๊ตฌ์กฐํํด ์ฐ์ ์์ ๊ฐ์ ์์ ๋ง๋ ๋ค. "์ ํ์จ ์ ๊ฒ", "๋๋ฉ ํ์ด์ง ๊ฐ์ ", "๊ฐ์ ํผ๋ ๋ง์ฐฐ", "CRO ๊ฐ์ฌ", "ํ์ด์ ์ต์ ํ", "ํผ ์ดํ ์ค์ฌ์ค", "CTA ๊ฐ์ ํด์ค" ๊ฐ์ ์์ฒญ์ ๋ฐ๋. ๊ฒฐ๊ณผ๋ .growth-marketer/<slug>/cro-audit-<page>.md ๋ก ์ ์ฅํ๊ณ schemas/cro-audit.schema.json ๊ณ์ฝ์ validate-artifact.sh ๋ก ๊ฒ์ฆํ๋ค.
๋ด ์๋น์ค๋ฅผ ๋ถ์ํด ICP + VOC(๊ณ ๊ฐ์ ๋ชฉ์๋ฆฌ) + ํฌ์ง์ ๋์ ์ถ์ถํ๊ณ ์ ํฉ ๋ง์ผํ ์ฑ๋์ ์ ์ยท๊ทผ๊ฑฐ๋ก ์ถ์ฒํ๋ค. ์ ๋ ฅ์ (1) ์๋น์ค URL(์ฑ์คํ ์ด/๋๋ฉํ์ด์ง, ์ฐ๊ฒฐ๋ ๋ธ๋ผ์ฐ์ ๋ก ์ฝ์) ๋๋ (2) ๋ก์ปฌ ์ฝ๋๋ฒ ์ด์ค ๋๋ ํ ๋ฆฌ ๊ฒฝ๋ก(READMEยทmanifestยทdocs ๋ฅผ ์ฝ์) ๋ ๋ค ๊ฐ๋ฅ โ ์๋ ๊ฐ์ง. "๋ด ์๋น์ค ๋ถ์", "๋ง์ผํ ์ฑ๋ ์ถ์ฒํด์ค", "์ด ์ฑ ์ด๋์ ๊ด๊ณ ํ์ง", "ICP ๋ฝ์์ค", "์ด ์ฝ๋๋ฒ ์ด์ค/๋ ํฌ ๋ถ์ํด์ ๋ง์ผํ ", "๋ก์ปฌ ํ๋ก์ ํธ ๋ถ์" ๊ฐ์ ์์ฒญ์ ๋ฐ๋. "๊ฒ์๋ยทSERP ๋ก ์ฑ๋ ๊ทผ๊ฑฐ ๋ณด๊ฐ" ๋ฅ ์์ฒญ์๋ DataForSEO enrichment ๋ก ๋์ํ๋ค. ๊ฒฐ๊ณผ๋ .growth-marketer/<slug>/ ์๋ ๊ตฌ์กฐํ ํ์ผ๋ก ์ ์ฅ๋๋ค.
์คํ ์ด ์ฌ์ฌ ๊ฑฐ์ ๋์. ๊ฑฐ์ ์ฌ์ ๋ถ์, ๋ฉํ๋ฐ์ดํฐ ์๋ ์์ , ์ฌ์ ์ถ.
์คํ ์ด ์คํฌ๋ฆฐ์ท ์์ฑ ๋ฐ ์ ๋ก๋. ํ ํ๋ฆฟ ๊ธฐ๋ฐ ํฉ์ฑ ํ Fastlane์ผ๋ก ์ ๋ก๋.
์ฑ์คํ ์ด/ํ๋ ์ด์คํ ์ด ์ฌ์ฌ ์ํ ํ์ธ. iOS App Store ์ฌ์ฌ ์ํ, Android Play Store ํธ๋ ์ํ ์กฐํ.
Use when deploying or operating workloads on the hetzner-master Proxmox lab (single Hetzner box at 195.201.80.242, Proxmox VE 8 + ZFS + Tailscale subnet router) โ adding LXC containers, integrating with the Prometheus/Grafana stack, exposing services through the firewall, or troubleshooting infrastructure issues specific to this lab
์คํ ์ด ๋ฉํ๋ฐ์ดํฐ ๋๊ธฐํ. release.config.json์ store ์น์ ์ ๋จ์ผ ์์ค๋ก App Store Connect + Google Play ์ ๋ฐ์ดํธ.
์ฑ์คํ ์ด/ํ๋ ์ด์คํ ์ด ํ๋ก๋์ ์น๊ฒฉ. TestFlightโApp Store, ๋ด๋ถํธ๋โํ๋ก๋์ ๋ฆด๋ฆฌ์ฆ.
๋ชจ๋ฐ์ผ ์ฑ ํ ๋ฆด๋ฆฌ์ฆ ํ์ดํ๋ผ์ธ. ์ฌ์ ์ ๊ฒ โ ๋ฉํ๋ฐ์ดํฐ โ ์คํฌ๋ฆฐ์ท โ ๋น๋+์ ์ถ โ ํ์์๋ด. Expo/Capacitor ์ง์.
cmux ๋ฉํฐํ์ธ ํฐ๋ฏธ๋ ์์์ Claude Code์ Codex ์ธ์ ์ ์ญํ ๋ณ ํ์ธ(plan / design / test-scenario / test-code / dev / review)์ผ๋ก ์๋ ์ค์ผ์คํธ๋ ์ด์ ํด ํ ์์ ์ ๋๊น์ง ์ฒ๋ฆฌํ๋ค. ์ฌ์ฉ์๊ฐ "์ฌ๋ฌ ํ์ธ ๋์์ ๋ง๋ค์ด", "๋ฉํฐ ์์ด์ ํธ๋ก", "์ค์ผ์คํธ๋ ์ด์ ", "claude ์ codex ๊ฐ์ด", "plan-dev-review ๋ถ๋ฆฌํด์", "์ฌ๋ฌ ์ญํ ๋ก ๋๋ ์ ์์ ํด์ค", "feature ์๋ ๊ฐ๋ฐ", "๋ณ๋ ฌ๋ก ์ฌ๋ฌ agent" ๊ฐ์ ํํ์ ์ธ ๋ ๋ฐ๋์ ๋ฐ๋ํ๋ค. ๋จ์ ํ ํ์ผ ํธ์ง์ด๋ ํ ๋ฒ์ ์๋ฌธ์๋ ๋ฐ๋ํ์ง ๋ง ๊ฒ โ multi-step ๊ตฌํ ์์ ์์๋ง. Figma ๋์์ธ ์ผ์น๋ ๊ฒ์ฆ, RED ํ ์คํธ ์์ฑ ํ GREEN ๊ตฌํ, AC ๊ธฐ๋ฐ ๋จ๊ณ๋ณ ๊ฒ์ฆ์ ๋ชจ๋ ํฌํจํ๋ ํ ํ์ดํ๋ผ์ธ์ด๋ค.
cmux ์ํฌ์คํ์ด์ค ์์ ๋ค๋ฅธ ํฐ๋ฏธ๋ ํจ๋(codex, ๋ค๋ฅธ claude ์ธ์ , ์ผ๋ฐ shell)์ ๋ฉ์์ง๋ฅผ ๋ณด๋ด๊ณ ์๋ต์ ์ฝ๊ธฐ ์ํด ์ฌ์ฉ. "์ ํจ๋", "๋ค๋ฅธ ํจ๋", "codex ์๊ฒ"
YouTube Shorts ์์ ์ ์ ํ์ดํ๋ผ์ธ ์คํ (๋ค๊ตญ์ด ์ง์)
๋ชจ๋ฐ์ผ ์ฑ ํ ๋ฆด๋ฆฌ์ฆ ํ์ดํ๋ผ์ธ. ์ฌ์ ์ ๊ฒ โ ๋ฉํ๋ฐ์ดํฐ โ ์คํฌ๋ฆฐ์ท โ ๋น๋+์ ์ถ โ ํ์์๋ด. Expo/Capacitor ์ง์.
์คํ ์ด ๋ฉํ๋ฐ์ดํฐ ๋๊ธฐํ. release.config.json์ store ์น์ ์ ๋จ์ผ ์์ค๋ก App Store Connect + Google Play ์ ๋ฐ์ดํธ.
์ฑ์คํ ์ด/ํ๋ ์ด์คํ ์ด ํ๋ก๋์ ์น๊ฒฉ. TestFlightโApp Store, ๋ด๋ถํธ๋โํ๋ก๋์ ๋ฆด๋ฆฌ์ฆ.
YouTube Shorts ์์ ์ ์ ํ์ดํ๋ผ์ธ ์คํ (๋ค๊ตญ์ด ์ง์)