watermelon-ui
codexSearch, compare, compose, and install free source-backed React UI from Watermelon.
2 skills · 1 MCP server
Every plugin for OpenAI Codex on GitHub — repos with a .codex-plugin/plugin.json or a Codex marketplace. Install with codex plugin marketplace add owner/repo then codex plugin add name@marketplace. Many work in both tools; see Claude Code plugins.
Search, compare, compose, and install free source-backed React UI from Watermelon.
2 skills · 1 MCP server
Turn local web projects into macOS Dock-launchable .app bundles for personal daily use.
1 skill
Turn a finished or buildable web app into a macOS Dock-launchable .app that serves the built output — no dev server, ~15 MB instead of 700 MB.
1 skill
Turn local web projects into Windows Start Menu launchable .exe apps. Beta · first real-hardware fixes landed · maintainer wanted.
1 skill
A local canvas workspace for structured Codex prompts and generated image assets.
8 skills · 1 MCP server
Redesigns existing HTML from its own content. 15 visual directions, standalone offline pages. Not a mood board.
7 skills · 1 command
One command, ultradesign: designs a marketing page, a multi-screen product or a redesign from a one-line request, one cycle at a time. Each cycle makes the work, has a cold outside eye look at it, and stops to show you; reply "one more" or "continue".
2 skills · 2 agents · 1 MCP server
A harness that gives AI coders the tools and skills to work like a senior developer
1 skill · 34 commands
A local infinite canvas for Codex, powered by tldraw — generate images onto the canvas, annotate with arrows, and let the AI redraw images from your annotations.
1 skill · 1 MCP server
Run read-only Instagram, TikTok, and LinkedIn research through Jev-directed socai CLI operations in the user's local browser.
1 skill
Composable AI skills covering the full software delivery lifecycle — for backend engineers, frontend engineers, QA, BAs, and more. Install once, invoke the skills you need.
33 skills · 1 agent
29 skills in six layers: workflow and the ARR-SPEC contract; general craft (melody, harmony, progressions, modulation, rhythm, form, counterpoint, motivic development); arrangement craft (architecture, orchestration including Chinese folk orchestra, texture, rhythm section, sound design, vocal direction, mix intent); nine style layers (J-pop, city pop & R&B, jazz, Latin, Mandarin pop, EDM, rock band, cinematic, hip-hop) each with a transfer table and declared fusion ownership; execution (compile to Suno/YuE2/MIDI, symbolic score, AI-tell audit); and a corpus layer of measured recordings. Plain text, no tooling required; answers in the language you ask in
29 skills
Autofill a .sub from a manuscript, run validate's AI checks, submit, debug a stalled portal run, and add venues.
11 skills
Continuous memory for Claude Code. Extracts, summarizes, and compresses conversations into tiered daily logs. Claude remembers what you did yesterday.
1 skill · 1 command · hooks
Install and operate oc-codex-multi-auth for OpenCode with ChatGPT Plus/Pro OAuth, Codex/GPT-5 routing, multi-account rotation, account switching, health checks, diagnostics, quota status, and recovery tools.
1 skill
Inspect Laravel requests with New Debug Bar's local MCP server.
1 skill · 1 MCP server
WOZCODE enhanced coding tools — smart search, batch editing, SQL introspection, and cost-optimized subagent delegation
7 skills · 1 MCP server · hooks
ISO 24495 Plain Language skills and plugin
8 skills
Give your coding agent a voice. Speaks responses aloud through the VoxClaw macOS/iOS app with per-project voices, speech queue, and polite multi-device sync.
3 skills · hooks
Preserve Claude Code and Codex session state around context compaction.
1 skill · hooks
Operate Canonry AEO projects through guided skills and typed MCP tools.
2 skills · 1 MCP server
Read stored Canonry measurements in a hosted workspace through a read-only OAuth connection.
1 MCP server
One installable AI law firm: a Managing Partner, 17 Specialist Lawyers, India, US, UK and Singapore Jurisdiction Counsel, 244 legal skills, 20 workflows, company registries, official legal-research connectors and local document production. Say Hello Rohas to begin.
200 skills · 22 agents · 7 MCP servers · hooks
Claude SEO Skills for the SE Ranking MCP server. Keyword research, content briefing, page intelligence, technical and content audits, structured data, drift monitoring, SXO diagnostics, competitive analysis, paid search, AI-search optimization, sitemap analysis, subdomain mapping, content opportunity mining, strategic roadmap planning, local SEO (GBP / NAP / local pack), international SEO (hreflang validation), Google APIs (GSC, PSI, CrUX, Indexing, GA4, YouTube, NLP), and SE Ranking API integration recipes (Data API + Project API).
32 skills · 1 MCP server
Claude SEO Skills for the SE Ranking MCP server. Turns raw API data into finished deliverables across keyword research, content briefing, page intelligence, technical and content audits, structured data, drift monitoring, SXO diagnostics, competitive analysis, paid search, AI-search optimization, sitemap analysis, subdomain mapping, content opportunity mining, strategic roadmap planning, Google APIs (GSC, PSI, CrUX, Indexing, GA4, YouTube, NLP), and SE Ranking API integration recipes (Data API + Project API).
32 skills · 1 MCP server
Agent-driven pipeline that turns raw material (PDFs, slides, syllabi, papers, URLs) into structured, teaching-quality Obsidian notes: ingest, compile, distribute.
1 skill · 12 commands
Spec-Driven Development pipeline: 23 atomic Socratic skills (survey/scaffold → spec → ux-flows → design → data-model → api → screens → tasks → tests → implement → review → ship) + a living decomposition roadmap (steps + dependency graph + parallel-safe execution waves) above the per-feature flow + 10 subagents, plus a TDD implementation engine with agent-team and dynamic-workflow modes. The Q&A skills are depth-tunable (easy/medium/hard); the ideation analyses (researcher/strategist/analyst/devil's-advocate) run as named subagents gated by that dial; diagrams are confirmed in prose; and every acceptance criterion is covered end-to-end. Surface-aware: declare target surfaces at design (backend/web/mobile/desktop/CLI/worker/library, as C4 containers); downstream gates the `ui` task layer, UI-driven flows, and frontend test tiers. UI features get a design pipeline (auto-skipped for backend-only work): design-system (the committed canon — Figma MCP / Pencil MCP / code-markdown; on pencil it also bootstraps and seeds the .pen library), ux-flows (user flows + SCR inventory) and screens (the per-state manifest tasks/implement/review build against, reuse-first). Every stage prints a copy-ready handoff (what changed + files to review + `/clear` + the next command).
23 skills · 10 agents
agent-talk enables any coding agent to talk to each other
15 skills
Offline security scanner for AI-agent repos, skills, plugins, and MCP servers. 29 scanners detect prompt injection, MCP tool poisoning, credential exposure, malicious lifecycle hooks, package IOCs, CVEs, CISA KEV exposure, and post-incident traces. Zero dependencies. Zero telemetry.
2 skills · hooks
Deutscher Stil-Editor für Claude Code/Codex: misst Register und Rhythmus, redigiert proportional auf ein Zielprofil, gleicht erkennbare Faktenanker konservativ ab und auditiert/entfernt KI-Schreibmuster. German AI Text Humanizer / deutscher Humanizer Skill. Supports Claude Code and Codex. 72 Muster in 10 Kategorien für deutschsprachige Texte. Kern: evidenzbewusste Redaktion und messbares Register.
2 skills