Wayhhow/ai-video-shot-prompt-skill
Skill Claude CodeCodex
A guide for writing, reviewing, and refining Chinese shot prompts for AI video generators such as Sora and Runway.
not rated 16 17d ago A 280 tokens
pdf-watermark-remover
10970Skill Claude CodeCodex
Remove watermarks from PDF files. Use when users request watermark removal, cleaning watermarks, or de-watermarking PDF documents. Supports tiling pattern watermarks (repeated image/text tiles) and semi-transparent text overlay watermarks.
not rated 16 7mo ago B 53 tokens
original MIT
falcoschaefer99-eng/muse-brain
Skill Claude CodeCodex
Cinematic image and video prompt discipline.
not rated 16
+1 21d ago A 15 tokens
better-search-console
10972houtini-ai/better-search-console
MCP server Claude CodeCodexCursor +2
MCP server that syncs Google Search Console data into SQLite for analysis. Runs locally from the @houtini/better-search-console npm package. Needs 2 environment variables to run.
not rated 16
+1 1mo ago A
tokens not measured
original Apache-2.0 archived
code-formatting
10973jonlwowski012/copilot-agent-factory
Skill Claude CodeCodex
Format code according to project standards and fix linting issues.
not rated 16 23d ago A SkillSpector: warn 15 tokens
original MIT
mcp
10974MCP server Claude CodeCodexCursor +2
A Model Context Protocol server for Wix AI tools. Remote server at mcp.wix.com.
not rated 16 2mo ago A
tokens not measured
react-test-engineer
10975GrishaAngelovGH/gemini-cli-agent-skills
Skill Claude CodeCodex needs its repo
Expert guidance for testing React applications using React Testing Library and Vitest. Focuses on user-centric testing, accessibility, and best practices for unit and integration tests to ensure robust and maintainable code.
not rated 16 6mo ago A 44 tokens
original MIT
blindspot-check
10976soheilmomeniii/blindspot-check
Skill Claude CodeCodex
Checks a big decision for blind spots against a catalogue of 95 cognitive biases before the user commits. Use when the user is about to make or has just justified a major life decision and wants to be checked for self-deception — buying a house, relocating, signing a long lease or contract, quitting or taking a job…
not rated 16 1mo ago A 219 tokens
original MIT
Skill Claude CodeCodex
Comprehensive LinkedIn personal branding analysis, profile optimization, and visibility improvement skill using Claude for Chrome browser tools. Use when users request LinkedIn profile analysis, personal branding audit, profile optimization recommendations, LinkedIn visibility improvement, headline optimization, About…
not rated 16 8mo ago A Socket: passSnyk: warn 108 tokens
original MIT
skill-creator
10978Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
not rated 16 13d ago A 64 tokens
nix-agent-init
10979Skill Claude CodeCodex
Onboard an unfamiliar NixOS or Home Manager flake by running nix-agent inspect-flake and generating AGENTMAP.md, CLAUDE.md, and .mcp.json from observed facts. Use on first contact with a config repo, when the user asks how the flake is laid out, or when making the repo agent-ready. Requires the nix-agent MCP server.
not rated 16 13d ago A SkillSpector: warn 81 tokens
original MIT
jahro-logging
10980jahro-console/unity-agent-skills
Skill Claude CodeCodex
Reviews and improves Debug.Log usage in Unity C# projects following structured logging principles: context tags, severity contracts, boundary-based placement, and criticality tiers. Detects common antipatterns (naked Debug.Log, logging in Update, stringly-typed errors), adds missing logs at system/state/error/external…
not rated 16 6mo ago A 111 tokens
original MIT
ElmatadorZ/Genesis-Mind-ClaudeSkill-Agent
Skill Claude CodeCodex
Use this skill for ANY of the following — do not skip it even if the query seems simple: strategic decisions, business analysis, thesis building, complex problem solving, geopolitical analysis (non-market), philosophical reasoning, academic research, system design, decision under uncertainty, long-form thinking, or…
not rated 16 1mo ago A 179 tokens
original Apache-2.0
bbc-skill
10982Skill Claude CodeCodex
A read-only tool for collecting all comments from a Bilibili video, including replies and pinned comments. Bilibili is a Chinese video-sharing platform.
not rated 16 25d ago A 86 tokens
original MIT
github-demand-radar
10983geekjourneyx/github-demand-radar
Skill Claude CodeCodex
A research workflow for examining issues and pull requests in a GitHub repository to find unmet needs that could become commercial tools. Pull requests are proposed code changes, and issues are reported problems or requested improvements.
not rated 16 4mo ago A 122 tokens
original MIT
coff0xc-office-doc-tools
10984Skill Claude CodeCodex
A guide for creating and checking editable Office files, including PowerPoint presentations, Word documents, PDFs, and Excel workbooks. It also covers checking layout, formulas, and file structure.
not rated 16 4mo ago A 85 tokens
chapplin-mcp-app-builder
10985Skill Claude CodeCodex
Build and debug MCP App-enabled tools in existing projects scaffolded by create-chapplin. Use when extending tools/.tsx with defineTool and defineApp , wiring structuredContent and meta for UI data flow, handling runtime differences across react/preact/solid/hono targets, or troubleshooting chapplin preview and…
not rated 16 6d ago A 77 tokens
original MIT
ida-pro-mcp
10986MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
MCP server "ida-pro-mcp" as configured in Gindhar2112/frida-mcp. Launched with /opt/homebrew/opt/[email protected]/bin/python3.11 /Volumes/Realtek/project/idapython/.
not rated 16 today A
tokens not measured
code-runner
10987formulahendry/agent-skill-code-runner
Skill Claude CodeCodex
Run code snippets in 30+ programming languages including JavaScript, Python, TypeScript, Java, C, C++, Go, Rust, Ruby, PHP, and more. Use when the user wants to execute code, test algorithms, verify output, run scripts, or check code behavior. Supports both interpreted and compiled languages.
not rated 16 9mo ago A 69 tokens
original MIT
Skill Codex
Use when thinking through or changing a production software architecture, or when reviewing or verifying architecture work inside the same design flow: greenfield systems, decomposition, migration, scale, reliability, security, data ownership, distributed workflows, clients, platform governance, or rewrites. Use…
not rated 16
changed 19d ago A SkillSpector: warn 88 tokens
original MIT
craft-repository-readme
10989Skill Codex
Create or overhaul polished, trustworthy GitHub repository READMEs with a logo, meaningful badges, hero visuals, navigation, quickstart instructions, verified links, sponsor content, and repository metadata. Use when a user asks to write, beautify, professionalize, brand, audit, or publish a project README, especially…
not rated 16 1mo ago A 88 tokens
original MIT
company-diligence
10990useful-skills/job-application-skills
Skill Claude CodeCodex
A company-research skill that investigates whether an employer appears financially and operationally safe. It separates official information, informal reports, and public records such as filings or labor data.
not rated 16 1mo ago A SkillSpector: pass 199 tokens
original MIT
acceptance-testing
10991onfire7777/universal-ai-skills-library
Skill Claude CodeCodex
Use for verifying business requirements with executable specifications using BDD frameworks. Covers Cucumber (Java, JS, Ruby), SpecFlow/Reqnroll (C#), Behave (Python), Gauge (ThoughtWorks), and Godog (Go). Includes Gherkin feature files, step definitions, BDD workflow, and cross-language examples. USE FOR: Cucumber…
not rated 16 12d ago A 163 tokens
original MIT
phantom-secrets-mcp
10992MCP server Claude CodeCodexCursor +2
Stop AI coding agents from leaking API keys. Local proxy swaps real secrets for phm tokens. Runs locally from the phantom-secrets-mcp npm package.
not rated 16 6d ago A
tokens not measured
original MIT
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: