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 CodeCodex
A Russian-language diagnostic workflow for OpenClaw, an agent system. It checks areas such as the gateway, memory database, scheduled jobs, tokens, files, and security, and reports possible fixes.
Skill Claude Code
Data analysis workflow kit using the ALIVE loop (Ask, Look, Investigate, Voice, Evolve).
Skill Claude Code needs its repo
Guide creating and reviewing skills that extend Claude with specialized knowledge, workflows, or tool integrations. Covers SKILL.md structure, frontmatter quality, trigger design, eval pipelines, and packaging. Triggers on create a skill, review this skill, new skill, optimize skill, skill quality.
Skill Claude CodeCodex
Decomposes a high-level goal into multiple independent child tasks.
christian289/dotnet-with-claudecode
Skill Claude Code
Creates WPF animations using Storyboard, Timeline, and EasingFunction patterns. Use when implementing UI transitions, state change visualizations, or interactive feedback effects.
Skill Claude CodeCodex
Texting as a person's proxy — reading threads, sending irreversibly, and watching conversations without over-answering.
Skill Claude CodeCodex
Prepare a Copilot CLI or agent session for live STS2 play by checking MCP access, explaining persistent setup, and verifying the runtime is ready before piloting starts.
Skill Claude CodeCodex
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
Skill Claude CodeCodex
Instance inheritance for JavaScript/TypeScript: types built from parent INSTANCES, so the prototype chain back to the root is the data's own lineage. Use when the user mentions mnemonica, define(), lookup(), TypeRegistry, tactica, @decorate(), instance inheritance, or when writing code that declares or constructs…
Skill Claude Code
Generate images via OpenRouter using direct chat-completions calls (gpt-5.4-image-2, gpt-5-image, gemini-3-pro-image, etc.) — POST to /chat/completions with modalities=["image","text"], decode the base64 data URL, save to disk, return the file path.
vincitamore/claude-org-template
Skill Claude CodeCodex
Copy this folder to /.claude/skills/org/ for global availability, or .claude/skills/org/ for project-specific.
Skill Claude CodeCodex
Use when writing or reviewing Kotlin code that stores CoroutineScope, launches from init/non-suspending APIs, calls runBlocking, or catches broad exceptions around suspend calls.
SpillwaveSolutions/mastering-langgraph-agent-skill
Skill Claude CodeCodex
Build stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents with LLM-tool loops, branching workflows, conversation memory, human-in-the-loop oversight, and production monitoring. Use when - (1) building agents that use tools and loop until task complete, (2) creating multi-step…
gunheeaug/web-seo-aeo-geo-google-naver-skill
Skill Claude CodeCodex
Implements SEO, AEO, and GEO for Next.js App Router: Google Search Console + Naver Search Advisor (sitemap, robots, verification, Naver 80-char metadata), plus Answer/Generative Engine optimization (FAQPage, Review, Organization, BreadcrumbList JSON-LD, SSR crawlable pages, dynamic OG). Use when deploying a web app…
rawveg/skillsforge-marketplace
Skill Claude CodeCodex
Use proactively when you need to implement features or fix bugs using strict Test-Driven Development (TDD) methodology. This agent should be activated for any coding task that requires writing new functionality, refactoring existing code, or ensuring comprehensive test coverage, but should not be used for any…
Skill Claude CodeCodex
Generate text, images and videos on Flowith's canvas from the CLI, headless or with a live cursor. Use for any image/video generation (Seedance, Veo, Kling, gpt-image, Gemini image), "canvas", "Flowith", "Neo", drawing/creating visual content, or past canvas work. /canvas-cowork.
Skill Claude CodeCodex needs its repo
Use when building or editing an AgentGem miniapp / mini-game — the sealed, single-file HTML app under /.agentgem/miniapps/. Covers the seal, the host capability protocol, consent, privacy, and the sizing traps. Also read before changing the miniapp platform itself (packages/play, the host, the Play console surfaces) …
Skill 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.
yellow-hammer/skills-onescript
Skill Claude CodeCodex
A framework for building component-based OneScript applications, a scripting language related to 1C, with automatic dependency setup and annotations. It creates objects and supplies their required constructor values.
Skill Claude CodeCodex
Skill "skill-sanitizer" from cyberxuan-XBX/skill-sanitizer, covering skill sanitizer, why you need this, the 7 layers, usage and in python.
Skill Claude Code
Estimate what Claude Cowork / Claude Code conversations would cost if run on the pay-per-token Claude API instead of the subscription. Reports token counts and cache-aware API cost in USD and EUR, for the current conversation or for the whole history (cost per conversation). Trigger when the user asks things like "how…
Skill Claude CodeCodex
A setup guide for connecting a personal WeChat account to Hermes Agent through WeChat's iLink Bot API, the interface used to exchange messages with the account.
Skill Claude CodeCodex
Hand-computes a system's execution with explicit state at each step. Use when debugging races, state machines, async bugs, regressions; stress-testing a fix; scoping features on existing state; or approaching unfamiliar code. Especially useful for bugs involving client/server sequencing, background refreshes, recovery…
Skill Claude CodeCodex
Whenever the user says something like: 'Begin task: ' - always read this skill to understand how to proceed.
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: