prompt-master
claude레퍼런스 사이트를 실측 분석해, 약한 모델이 실행해도 상위 모델급 결과가 나오는 완성 구현 프롬프트를 생성합니다.
1 skill
Claude Code and Codex plugins their authors filed under "productivity". All categories.
레퍼런스 사이트를 실측 분석해, 약한 모델이 실행해도 상위 모델급 결과가 나오는 완성 구현 프롬프트를 생성합니다.
1 skill
애드센스·네이버 애드포스트 등 퍼블리셔 광고 수익을 RPM·뷰어빌리티·배치·정책 준수 관점에서 최적화하는 패턴입니다.
1 skill
네이버 생태계(블로그·스마트스토어·플레이스) SEO를 C-Rank·D.I.A+ 기준으로 다루는, 구글 SEO와 다른 마케팅 패턴입니다.
1 skill
Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives
1 command
Official GitHub MCP server for repository management. Create issues, manage pull requests, review code, search repositories, and interact with GitHub's full API directly from Claude Code.
1 MCP server
Search, read, draft, and manage email.
1 MCP server
Search, read, create, and share files.
1 MCP server
Search events and schedule meetings.
1 MCP server
Mobile notifications for Claude Code approvals and decisions. Receive push alerts on your Android phone and respond directly from the ShadowAI app.
hooks
Write any content in Amy Benson's authentic voice (Diolog Founder & CEO), routed through eight persona variants: LinkedIn posts and thought leadership, long-form articles/blog posts, marketing content (announcements, launch/landing copy grounded in the diolog.app copy she curated and aligned with the Diolog voice & audience guide), sales/partnership outreach email (cold intros, consultative follow-ups, objection handling, gracious declines), Diolog investor updates, Slack/chat messages, short-form, and speaking notes for panels/podcasts/pitches. One evidence-anchored base voice (warm first, sharp underneath, direct questions with low-pressure asks, spaced-hyphen habit, no em dashes, AU spelling) synthesised from ~5,000 words of her verbatim email, LinkedIn, Slack and interview corpus (bundled, redacted), with a deterministic voice lint carrying her measured stylometric fingerprint. Generated with the create-voice-persona factory. v1.3 folds in Amy's own editorial review: broken-up LinkedIn formatting, genuine-question closes, peer-audience floor, referent discipline, register fencing for marketing, plain offer phrasing, no meta-labels, and retired phrases (bricks/Rome, 'came up through') enforced by the lint. v1.4 refreshes the bundled AI-signs field guide with the July 2026 empirical research layer and encodes the research-backed guards (plain copulas, epigram budget, hook-transition bans) in the base voice and lint config. v1.4.1 syncs the field guide's once-per-document epigram/contrast rule. v1.5 syncs the repeated-phrase lint check and the updated field guide (countable texture budgets, scaffold-slot trap). v1.5.1 field-guide sync. v1.5.2 lint pattern sync. v1.6 adds the meetings corpus: ~150k words of Amy's live sales/discovery calls (2025-26, six segments, redacted) distilled into references/research/amy-meetings-corpus.md - spoken hedge hierarchy corrected (kind of / I guess / to be honest dominate; I'd say / I find demoted to interview register), signature
1 skill
Create a structured session handoff document that captures decisions, code changes, progress, and next steps so later sessions can resume work cleanly.
1 skill
Generate images through MaxPlus Responses image_generation.
1 skill
Skills for writing and maintaining documents alongside the people who own them.
1 skill
題材・構成・スタイルを個別に指定し、編集可能なPowerPointを生成します。
1 skill
Cut Claude Code system-prompt bloat by disabling unused tools/skills in settings.json. Use when reducing token usage.
1 skill
Reusable SiYuan skill with SKILL.md and direct HTTP API runtime.
1 skill
Report personal dev productivity: active hours from local Claude Code and Codex CLI session transcripts, lines-of-code contributed across your repos via git log, and token usage with an estimated cost (priced against LiteLLM's public pricing data). Runs entirely locally, no dependencies beyond Python 3 stdlib.
1 skill
Unofficial skill. Write, edit, and review Proxmox technical documentation with the rules of the Proxmox Technical Writing Style Guide.
1 skill
Reusable skills shared across projects, including repository-local Markdown change request management.
1 skill
Apply Fabric prompt patterns natively in Claude Code sessions
1 command
Drafts GitHub PR reviews while requiring a human /show step before posting.
1 skill
AI job search pipeline — evaluate offers, generate CVs, scan portals, track applications
1 skill
AI job search pipeline — evaluate offers, generate CVs, scan portals, track applications
1 skill
AI job search pipeline — evaluate offers, generate CVs, scan portals, track applications
1 skill
AI job search pipeline — evaluate offers, generate CVs, scan portals, track applications
1 skill
AI job search pipeline — evaluate offers, generate CVs, scan portals, track applications
1 skill
Fetch and process YouTube video transcripts using yt-dlp. Supports summarizing, extracting information, or displaying full transcripts.
1 skill
Access Evernote notes via xev-cli for searching, reading, creating, and updating notes
1 skill
AI agent skills by @huanshankeji, mainly for our own development conventions.
1 skill
魔珐星云具身交互智能体 Web SDK 开发助手技能与插件
1 skill