NoxInfluencer
claudecodexNoxInfluencer marketing workflows through MCP.
2 skills · 1 MCP server
Every plugin for Claude Code we can find on GitHub, read straight from each repo's .claude-plugin manifests. Install one with claude plugin marketplace add owner/repo and claude plugin install name@marketplace — each page has the exact lines. Looking for Codex? See Codex plugins.
NoxInfluencer marketing workflows through MCP.
2 skills · 1 MCP server
아이디어를 실제 제품으로 만드는 스킬 모음. sharpen으로 명세를 다듬고 productify로 제품 형태와 로드맵을 설계합니다.
2 skills
Org-mode knowledge and note management via emacsclient
2 skills
Orchestrate a multi-agent adversarial review panel. 4-6 reviewers with distinct personas independently evaluate work, debate findings across 1-3 rounds, then a supreme judge renders the final verdict. Bundles plan-review-integrator for applying findings back into implementation plans. Auto-detected Precise/Exhaustive mode, severity verification, tiered L0/L1/L2 knowledge mining, 10 signal groups with domain checklists. Based on ChatEval, AutoGen, DMAD, CONSENSAGENT, and Trust or Escalate research.
2 skills
Async task coordination with co.multiply.quiescent: q/task, qlet, qfor, structured concurrency, cancellation, grounding.
2 skills
BSL Language Server — LSP for 1C:Enterprise (BSL) and OneScript (OS) languages
hooks · LSP
Draft and revise prose for clarity, usefulness, tone, and a natural human voice.
2 skills
Pick the tests a diff can plausibly break, across eight runners, and hand the runner its own filter arguments
1 skill · 1 command
python-hwpx 프로젝트가 직접 유지보수하는 first-party HWPX 에이전트 스킬. 편집은 순수 Python이며 최종 시각 검증은 필요 시 한컴 오라클을 사용합니다.
1 skill · 1 MCP server
HarmonyOS NEXT offline reference library for AI coding assistants
1 skill · 1 MCP server
Bridge skill from PRD to /goal for Claude Code — auto-generates 5 review docs (VALIDATION/RECOVERY/PLAN with per-milestone task checklists/PROGRESS/goal-command) in the user's language (auto-detected; ko/en first-class with deterministic heading validation) with 4,000-character compact and Korean+English OR protected-clause regex enforcement. Step 8 shows a review summary directly in chat and prepends a 4-line summary to PROGRESS.md (no separate brief file). After a mandatory human approval gate, the assistant emits /goal on the last line of its reply and the plugin's hook runs it as the /goal command when the turn ends (no retyping).
1 skill · 1 command
Orchestrator mode for Claude Code: the main session plans and delegates the work to subagents instead of doing it inline.
1 skill · hooks
Back up, analyze, and reuse ChatGPT | Claude | Codex | Cursor | DeepSeek | Qwen | Openclaw data + skills + attachments locally
1 skill
QIT testing skills for Claude Code - test packages, managed tests, environments, debugging
1 skill
Multi-engine AI web search — Perplexity, Google AI, ChatGPT, and Gemini in parallel. No API keys needed.
1 MCP server
Power utilities: auto-titling sessions and sound notifications on session end
hooks
변화이론 에이전트 (Theory of Change Agent) — KOICA PDM (Project Design Matrix) 생성. 진입 시 세 가지 방식(컨셉부터 / 자료 보유 / 표 먼저) 중 무엇으로 할지 먼저 묻고, 변화이론 인터뷰를 거쳐 PDM 매트릭스 + 모니터링 매트릭스를 만든다. 2단 자가검증(결정적 구조 규칙 + LLM 품질 규칙)으로 게이트하며, 검증기는 jq 없이 순수 파이썬으로 동작한다.
1 skill
Optional companion to tale-mode: the read-only stuck-loop governor (Layer 2). Zero idle cost — a free bash gate escalates to ONE read-only model call (claude -p on Claude Code, sandboxed codex exec on Codex) exactly when a goal first fails twice, and returns an advisory finding. Install if you want anchor-breaking on stuck loops.
hooks
Skills for using the Reflect CLI
1 skill
Autonomous experiment loop — modify, test, keep/discard, repeat forever
1 command
Reconstruct what you worked on from your AI coding sessions: recent, stats, and redacted export. Reads session content, so it ships separately from the guard.
1 skill
MCP tools for the Almide compiler (check / test / API outline / explain / fmt-check) plus the .almd language server.
1 MCP server
Check a draft against your house writing rules and get back which rule it trips, on which line, and how sure the checker is. The countable rules are regular expressions and run locally. The judgment rules are a model call you opt into once.
1 skill
UI 메뉴판 — 말로 설명하던 UI에 이름을 붙여 주는 사전 + 실물 HTML 132종(웹 연출 24 · 카드 줄이기 2 · 커버플로 포함) + shadcn 매핑 59항목
1 skill
앱 UI 메뉴판 — 모바일 앱 UI를 말이 아니라 이름으로 시키는 사전. 8코스 76항목, 별칭 → 정식 명칭 → 요청 문장 → 네이티브(SwiftUI·Flutter·React Native) 매핑. 웹은 ui-menu
1 skill
CSS 증상 사전 — 깨진 화면을 증상으로 찾는 사전. 8코스 42항목, 깨진/고친 실물 나란히 + 즉방형/분기형 처방
1 skill
Detect and fix AI-generated writing patterns. 35+ patterns, tiered scoring, editor mode.
1 skill
Blocks known-malicious and typosquatted package installs before Claude runs them, and warns on known advisories for an exact pinned version.
hooks
Registers the Astrolabe MCP server (7 tools). Install the `astrolabe` binary first: see README.
1 MCP server
Live browser view for Claude Code: each session is a floor of a pixel-art office, each subagent a worker at a desk. Companion to foreman.
1 skill