🔌
Plugins
Loading...
Showing 30 of 24181 results
Audio cross-correlation alignment for N recordings of the same event. Outputs `.sync.json` sidecars per file — never re-encodes the originals.
Auto-syndicate your newest 微信公众号 article across platforms — auto-posts to X / Bluesky / Threads / LinkedIn and prepares a copy-paste outbox for manual platforms (Facebook / 小红书 / 即刻 / 知乎).
Turn a single English word into an HLS supercut lesson from a video base — stitches every clip where the word is spoken, prepended with a bilingual intro card (word + IPA + 中文 gloss + usage, Volcano TTS) and a follow-me CTA card.
Audio/video → timestamped SRT in the source language. Chinese uses Volcano ASR; other languages use OpenAI Whisper with word-level timestamps + punctuation-bounded re-segmentation.
Translate an SRT from one language to another with punctuation-bounded re-segmentation. Simplified Chinese and English are first-class targets. Supports bilingual output.
Post a daily X tweet inspired by your newest un-tweeted WeChat article — drafts 3 angle variants (quote / metaphor / one-liner), posts the chosen one via xurl, records history.
Batch upload videos to YouTube with per-video metadata from `UPLOAD_META.md`. Survives SOCKS/HTTP proxies by using `requests` directly for resumable upload.
VoiceDrop 配套 skill。两个模式 — (1) list：列出你在 VoiceDrop R2 上的全部文件（录音 / 文章 JSON / 标记）；(2) distill：从你的样本文章蒸馏文风，生成可贴入 VoiceDrop「设置→文风」的精简规则集，并可直接通过 Files API 上传。触发词："voicedrop list"、"列出 VoiceDrop 文件"、"voicedrop distill"、"蒸馏 VoiceDrop 文风"、"/wjs-voicedrop"。
Systematically improve X content by A/B-testing the tweet-generation prompt — git-SHA-versioned, numbered experiments judged on median impressions per tweet, with per-tweet feature mining.
Grow X followers via numbered, A/B-testable growth experiments — each with a hypothesis, target metric, rollback state, and verdict. North-star = new-follower ÷ profile-visit conversion.
Frontend design skill with patterns, design tokens, and component guidelines
HTML slides skill for amber-classified presentations
Work lifecycle management v2 — phased workflows (research, plan, implement) with agents, commands, and hooks.
WMX3.7 애플리케이션 풀스택 개발: 요구사항→시스템 설계(플랫폼 선택·축 구성·모션 기능 매핑·성능/안정성 전략) + C++/C# 구현(초기화 시퀀스·모션·이벤트·에러 처리·.NET Dispose) + 시뮬레이터 플랫폼 기반 테스트 + 기존 프로젝트 WMX3 사용 검토(API 오용·에러 처리 누락·성능·3.6u3→3.7 마이그레이션) + Robot Option 다관절 로봇 제어(기구학·Joint/Cartesian 좌표계·PTP/CP·XML/URDF 로봇 정의·충돌 감지) + EtherCAT ENI 파일 제작(WMX3 전용 ENI·ec_network.def·슬레이브 ESI(ETG.2000) 분석·PDO/CANopen 매핑·EcConfigurator/NetConfigurator 연계). 6개 스킬 + 5개 에이전트.
WMX3 모션 제어 모듈 풀스택 개발: 3-layer 모듈 스캐폴딩(Core RTDLL + C++ API + CLR) + CMake 크로스플랫폼 빌드(Linux RT/Xenomai, Windows RTX64) + gtest/gmock TDD + RT 안전성 코드 리뷰 + API 사용자 설명서 자동 생성 + /opt/lmx 배포 스크립트. 8개 스킬 + 6개 에이전트.
macOS iMessage MCP server for Claude — send and read iMessages directly from Claude Code. Enables messaging automation and integration with Apple's Messages app.
WordPress / CMS engineering team — 3 agents (wordpress-architect, wordpress-developer, wordpress-ops-engineer) for building, extending, and operating WordPress done right: the build-approach decision (classic vs block/FSE theme, plugin vs theme vs must-use, headless/decoupled vs traditional, single vs multisite), secure block & theme & plugin development (block.json, hooks/filters, WP_Query, the REST API, sanitize-in/escape-out, $wpdb->prepare, nonce + capability checks), and operations (page + object cache/Redis, security hardening, safe updates with staging & backups, migrations). 5 skills, a decision-tree knowledge bank (4 Mermaid trees + a dated 2026 stack map), 8 best-practices, 3 templates, 3 commands, 1 advisory hook. Seams: decoupled front-end -> frontend-engineering, non-WP backend/APIs -> backend-engineering, infra perf budget -> performance-engineering, formal security verdict -> security-engineering. Requires ravenclaude-core@>=0.7.0.
Develops custom WordPress themes and plugins, creates and registers Gutenberg blocks and block patterns, configures WooCommerce stores, implements WordPress REST API endpoints, applies security hardening, and optimizes performance through caching and query tuning.
Hooks, Subagents, ClickUp/Slack-Integration, 3-Layer-Eskalation für Empire-Apps.
Cross-session memory for long-running work: append-only diary (LOG) and decision (DEC) logs under .claude/memory, grouped by work item (JIRA-123, RFC-7, …), with derived open-item tracking so any later session can answer what is still pending, what changed on a ticket, and what was done since a date. Ships its own clock-in/clock-out protocol via a UserPromptSubmit hook.
Evidence-linked work objects — one work/<id>-<slug>/ dir per code-change task holding spec, captured diff, captured test output, run manifest, and review; in-review/approved transitions are gated by a checker script and enforced by a PreToolUse hook.
Track-aware daily planning over GitHub issues. Shared tracks (git-synced .work-plan/) optionally pinned to a canonical plan branch (plan-branch; push-track promotes a private track to it), AI clustering (group/auto-triage), coverage, plan-status doc liveness with drift detection, batched GraphQL fetches, and dependency-aware next-up with per-track ordering presets. Includes a theme-aware, accessible VS Code viewer — sidebar tree with a visibility×tier exposure badge, a repo-qualified Mermaid dependency graph, per-issue in-progress badge/toggle and dependency chips, next-up controls, proactive auto-slot suggestions with a compare-and-swap collision guard, and a Plans view with confirm-gated frontmatter writes and repository-contained plan links. Installer ownership is content-verified so unmanaged or modified launchers are preserved.
Git-native work tracking shared by Claude and Codex, with root, Salesforce delivery, and existing engagement paths, deterministic status, handoffs, relationships, Git landing verification, generated dashboards, and optional GitHub Issues and Projects synchronization.
Triage open PRs and issues after completing epics — identify abandoned, superseded, or stale work items and recommend close/update/keep
Orchestrated /work command with pre-computed action plans