Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Skill Claude Code
The front door to the seven development dimensions: read whichever reports are on disk, say which dimensions this project should cover, cross-read them, and give one graded verdict on the code as written and tested.
Skill Claude CodeCodex
Structured human-in-the-loop debugging mode for when static code reading isn't enough. Use this skill whenever you're stuck debugging an issue where you can't tell what's actually happening at runtime — async timing, complex control flow, multiple call paths, conditional branches, or bugs that only reproduce when the…
Skill Codex
Use when the user says repository docs are stale, wrong, duplicated, scattered, or hard to search; asks where something is documented; wants a decision or glossary term written down properly; or when RCC exposes a gap in canonical docs. Maintains the trusted documentation, reading order, decisions, glossary, and…
Skill Codex
Build, install, launch, and inspect runtime logs for iOS apps on physical devices from Codex. Use when a user asks to build and run an iOS app on a real iPhone/iPad, capture live xcodebuild/devicectl/device logs, avoid launch hangs from already-running apps, read previous run logs, or filter/search iOS build and…
Skill Claude CodeCodex
Review content against the Microsoft Writing Style Guide, reporting issues by severity (Critical/High/Medium/Low) with specific fixes. Use this skill whenever the user asks you to review, edit, or check text for compliance with Microsoft style, including documentation, UI strings, developer docs, blog posts, error…
Skill Codex
Translate Figma nodes into production-ready code with 1:1 visual fidelity using the Figma MCP workflow (design context, screenshots, assets, and project-convention translation). Trigger when the user provides Figma URLs or node IDs, or asks to implement designs or components that must match Figma specs. Requires a…
Skill Claude CodeCodex
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
Skill Claude CodeCodex
Create affordance-level breadboards from a specific workflow or shaped product idea. Use for UI/code/store/wiring tables. Not for generic architecture diagrams, implementation plans, or visual mockups.
Skill Claude Code
Set up Artillery load testing for any project. Detects package manager and project type, creates a TypeScript test script (HTTP or Playwright browser), configures Artillery Cloud, and provides the run command. Use when the user wants to add load testing, performance testing, or browser-based load testing to their…
Skill Claude CodeCodex
Skill "oceanbase-skills" from weejar/oceanbase-skills, covering oceanbase db skills, how to use, category routing, skills directory and version baseline.
Skill Claude CodeCodex
Workflow for translating entire books using AI agents. Split markdown books into chapters, batch translate 5 at a time, and verify completeness. Works with any language pair.
Skill Claude CodeCodex
A browser-automation skill that uses ChromeDriver and Selenium to control a real Chrome browser for testing web pages.
Skill Claude CodeCodex
Video subtitle translation skill that downloads videos, extracts/transcribes subtitles, translates them to any language, and generates videos with burned-in subtitles (bilingual, original, or translated). Supports YouTube, Bilibili, Douyin/TikTok, and all yt-dlp compatible platforms. This skill should be used when the…
ffsshhttiikk/opencode-agents-skills
Skill Claude CodeCodex
Managing and provisioning infrastructure through machine-readable definition files.
Skill Claude CodeCodex
Affiliate program strategy, link optimization, and commission maximization.
Skill Claude Code
Research a technology, tool, framework, concept, or methodology — or compare two or more of them — through a progressive flow: preliminary gist delivered immediately from web search, informed clarifying questions, then parallel subagent research synthesised into a conversational explanation or a written study guide.…
Skill Claude CodeCodex
Specialized ripgrep wrapper to navigate code without reading full files.
SuperMalow/personal-agent-skills
Skill Claude CodeCodex
Read-only root-cause diagnosis for bugs, failures, flaky behavior, and performance regressions. Use when the user asks to diagnose, investigate, debug, explain, or find the cause of broken, throwing, failing, incorrect, intermittent, or slow behavior. Gather evidence and report the likely root cause without modifying…
Skill Claude Code
Use when asked to design, build, develop in Data Engineering. Design, build, and maintain scalable data infrastructure.
Skill Claude Code
A Python state machine that follows the dependency graph in a plan.md file. A dependency graph shows which tasks must be completed before others can start.
Skill Claude CodeCodex
Generates a structured multi-file feature implementation plan after a detailed requirements interview. Triggers ONLY on the explicit /plan-me command (optionally with a feature name, e.g. /plan-me user-auth). Do NOT trigger on natural-language planning requests like "make a plan", "help me plan X", or similar — only…
Oncorporation/Political-Agent-Skills
Skill Claude CodeCodex
Use when defending constitutional order and peaceful institutions against deliberate destabilization or revolutionary disruption tactics. Applies when identifying, analyzing, or responding to chaos exploitation strategies documented in the chaos-seize skill.
Skill Claude CodeCodex
Provides visa requirements, entry regulations, and travel document guidance for international destinations.
Skill Claude CodeCodex
Research a URL (library/package/tool/website/blog/X/YouTube) or external codebase and document it to the vault — how it fits the tech stack, comparison to existing tools, architecture patterns, and where it'd be useful. For codebase deep-dives, see references/remote-codebase-research.md.
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: