Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 271,586 indexed, measured the same four ways as everything else here.
Choose, inspect, attribute, and safely adapt original-language GPT Image 2 portrait-editing prompts from a 519-record provenance-first library. Use its two-level task and scenario taxonomy for restoration, natural retouching, professional identity photos, lifestyle portraits, and identity-preserved transformations.
Review English economics papers as a portable pre-review skill. Use for theory, empirical causal, structural or IO empirical, econometrics or methodology, experimental or behavioral, computational or simulation, survey or literature review, and mixed economics papers. Also use for benchmark or validity testing of…
Builds or updates a source-grounded advisor skill from one person's books, documents, local transcript files, and YouTube video URLs. Extracts PDF/EPUB/DOCX/HTML/Markdown/text/RTF/MOBI/AZW sources, retrieves available YouTube captions, reconciles evolving or conflicting ideas, and generates a compact /ask-name-style…
Social media at your fingertips. Fetch tweets, transcribe videos with per-token confidence, extract frames at exact timestamps, download Instagram posts — from any MCP client. 30 tools across Twitter/X, YouTube, Instagram, and video processing. All transcription runs locally via Whisper with uncertainty markers so…
End-to-end production-prep workflow: extracts comprehensive scene inventories from narrative writing, extracts continuity inventory and reset-critical state before prompt writing, generates all reference images (characters, locations under multiple angles/conditions, props), produces start/end/keyframe shot references…
Verify that a portable Agent Plugin loaded correctly in Pi by checking this skill and calling the bundled official MCP everything test server. Use when testing pi-agent-plugins installation, skill discovery, MCP trust, or MCP tool connectivity.
MCP server "video-analyzer" as configured in guimatheus92/social-knowledge-base. Runs C:/Users/guilh/repos/mcp-video-analyzer/dist/index.js with node. Needs 5 environment variables to run.
★not rated 8▲
+1 3mo agoA
tokens not measured
originalMIT
Conversation-driven video editing for short-form vertical (Reels, TikTok, Shorts) and longform horizontal video. Use when asked to cut, grade, caption, add graphics, create a soundtrack, transcribe, or prepare video edits. Run Phase 1 (audio-led clean cut and grade), obtain approval, then build Phase 2/3 Remotion…
Collect the user's own authorized Douyin Creator Center analytics on macOS or Windows, validate the official exports, and update the complete data contract consumed by Personal AI Workbench. Use when the user asks to pull, refresh, validate, or display their own Douyin account data in the Workbench. Do not use for…
Een videoproces dat automatisch gemaakte ondertitels controleert met zowel de gesproken audio als de tekst die in beeld staat. Daarna kan het de ondertitels vertalen en een ingesproken versie in meerdere talen maken met een nagebootste stem.
Scan the GitHub dsh-plugin topic for new DeepSeek Harness community extensions, diff them against the local catalog CSVs, dispatch parallel review agents, and merge qualifying repos (above the star floor) into repositories.csv / dsh-plugin-topic-candidates.csv / verified-plugins.csv per the project's curation rules.…
A command-line tool for managing coding-agent skills, which are reusable instructions for particular kinds of work. It handles network requests and known installation procedures, while the agent makes search and fallback decisions.
Cria carrosséis e posts visuais pra Instagram, TikTok, LinkedIn com a identidade visual da marca. Gera HTML estilizado + renderiza em PNG 1080x1350 via Playwright, com legenda pronta no final. Suporta carrossel texto puro, carrossel com foto IA (gerada via OpenAI) e post único. Use quando o usuário pedir "carrossel"…
Implement features, components, and code functionality with intelligent expert activation, comprehensive development support, and best practices enforcement.
A guide for deciding when to use Claude Code's dynamic workflow system and for writing or reviewing scripts that coordinate agents. An agent is a separate task worker; pipeline and parallel patterns control how workers run.
★not rated 8 1mo agoA120 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: