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.
FrankS-IntelLab/agentic-kaggle-skill
Skill Claude CodeCodex
Kaggle-first end-to-end competition workflow for scored submissions. Use when Codex must run Kaggle or competitive ML workflows through scored submission, including code competitions, validation, metrics, policy-safe public notebook/discussion intel, tabular/text/image modeling, tuning, ensembling/stacking, proactive…
Skill Claude CodeCodex
Sync and manage Overleaf LaTeX projects from the command line. Pull projects locally, push changes back, compile PDFs, and download compile outputs like .bbl files for arXiv submissions. Use when working with LaTeX, Overleaf, academic papers, or arXiv.
Skill Claude Code
Run one bounded eGEOagents loop iteration over a workspace domain - read the charter and fresh collector data, do ONE unit of work, write substrate artifacts, append one Timeline entry and one LOG line. Use for loop mode, /geo:loop, scheduled GEO runs, or continuous monitoring.
Skill Claude CodeCodex
Analyze images, websites, and Figma files to extract their design and generate a design.md with token system, component inventory, and reconstruction notes. Use this skill whenever the user wants to understand, document, replicate, or audit the design of something visual: a screenshot, a URL, a Figma link, a Pinterest…
Skill Claude CodeCodex
Browser automation skill for AI agents using the mb CLI. Use when the agent needs to browse the web, take screenshots, scrape text, fill forms, click elements, record screencasts, run JS in pages, or audit designs. Triggers on: "browse", "open a page", "take a screenshot", "scrape", "fill form", "click button", "web…
Skill Claude CodeCodex
A sample skill that demonstrates a skill registry index and the pattern “do X for Y.”
Skill Codex
Run a lightweight Ultracode workflow for serious coding tasks: plan, split, delegate when useful and allowed by the host, integrate, and verify. Use when the user explicitly invokes ultracode, $ultracode, ultra code, dynamic workflow, workflow orchestration, multi-agent workflow, subagent workflow, parallel agents…
Skill Claude CodeCodex
Claim and implement one ready GitHub issue, run fail-closed gates, obtain independent verification, and open a draft pull request.
Skill Claude CodeCodex
A skill for giving tarot readings in Chinese, including card draws, upright or reversed cards, and spreads. It covers topics such as relationships, work, decisions, and daily guidance.
Skill Claude CodeCodex
Business logic vulnerability playbook. Use when reasoning about workflows, race conditions, price manipulation, coupon abuse, state machines, and multi-step authorization gaps.
Skill Claude CodeCodex
After building any UI component, extract the visual patterns that matter for consistency and save them to ui-registry.md. So every component built after this one matches what came before.
Skill Claude CodeCodex
Propose skills from wiki patterns and traces (WikiSkill).
mattgierhart/PRD-driven-context-engineering
Skill Claude Code
Execute implementation within EPICs following test-first development, continuous SoT updates, and code traceability during PRD v0.7 Build Execution. Triggers on requests to start building, implement an epic, begin coding, or when user asks "start building", "implement epic", "coding", "development", "build execution"…
Skill Codex
Domain expertise for Ai2 Asta MCP tools (Semantic Scholar corpus). Intent-to-tool routing, safe defaults, workflow patterns, and pitfall warnings for academic paper search, citation traversal, and author discovery.
Skill Claude CodeCodex
Manage the task pipeline. All commands use $TASKCTL from the project root.
Skill Claude CodeCodex
Find official portals, APIs, and download paths for authoritative primary data sources (governments, international organizations, research institutions, etc.). Use when users need to know "where to find this data from an official source", "which source is more authoritative", or "how to cite primary data". Covers…
Skill Claude CodeCodex
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
Skill Claude CodeCodex ✓ vendor
Review a proposed Agent Skill for structural validity and content quality before publishing. Runs the skill-validator CLI to check for structural issues, scores the skill with an LLM judge, and interprets results to advise SMEs on what to address. Use when a user wants to review, validate, or quality-check an Agent…
Skill Claude CodeCodex
Implement OAuth 2.0 authentication flows including authorization code with PKCE, client credentials, and device code for secure API integration. Use when the user requests oauth 2 0 setup or provides relevant inputs for this workflow.
Skill Claude CodeCodex needs its repo ✓ vendor
A tool for creating and modifying importable JSON dashboards for Alibaba Cloud SLS, a service for searching and monitoring logs. It maps checked queries and analysis needs to dashboard charts.
Skill Claude Code
A planning and decision-making skill that evaluates whether an action is justified, why it should be taken, and whether the available conditions are sufficient. It observes and recommends but does not perform operations or verify facts.
Skill Claude CodeCodex
A search-and-question-answering helper for a local knowledge-base folder. It uses different methods for different file types, including PDFs and spreadsheets.
Skill Claude CodeCodex
Use when the user wants to swap tokens on Base Sepolia (or Base mainnet) using Uniswap V3. Handles any ERC-20 token pair including ETH wrapping/unwrapping. The agent discovers pools, gets quotes, constructs calldata, and executes swaps via keypo-wallet. Also use when the user says "swap", "trade", "exchange tokens"…
Skill Claude Code needs its repo
Guide through the Cortex TMS release process — version bump, changelog, sync, tag, publish. Every step requires user approval.
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: