CCM
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
starchild-ai-agent avatar

Worldcup

starchild-ai-agent/official-skills
1.4k installs22 stars
Summary

Pulls live FIFA World Cup 2026 data and wraps a points-based prediction game into a single script skill. You get match schedules, live scores, and results, plus functions to place bets on outcomes (win/draw/loss, exact score, total goals, first goal), cancel them before they settle, and check leaderboards sorted by points or accuracy. It's all Python imports from core.skill_tools.worldcup that return JSON, no external API keys needed. The prediction types are nicely structured, stakes are multiples of 10, and there's a full betting status check so you can confirm balance before placing. Good for World Cup chat where users want both info and a lightweight game layer without leaving the conversation.

Install to Claude Code

npx -y skills add starchild-ai-agent/official-skills --skill worldcup --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.mdView on GitHub

⚽ World Cup 2026 Skill

FIFA World Cup 2026 data + the points-based prediction game. Script skill — call the functions in core.skill_tools.worldcup from bash and read the JSON. Auth is automatic (container JWT); no API key needed.

How to call

python3 -c "from core.skill_tools import worldcup; import json; print(json.dumps(worldcup.get_today_matches()))"

Every function returns a dict like {"success": true, "data": ...} (or {"success": false, "error": ...} on failure).

When to use

  • Matches — today / upcoming / live / finished, or one specific match.
  • Predictions — place, cancel, or review prediction history.
  • Stats — point balance, betting limits, win rate, total staked.
  • Leaderboard — top predictors by points or accuracy.

Functions (from core.skill_tools import worldcup)

FunctionReturns
get_today_matches()today's matches + your prediction status
get_upcoming_matches(limit=10)next scheduled matches
get_live_matches()matches in progress now
get_finished_matches(limit=20)recent results
get_match_detail(match_id)one match in full
place_bet(match_id, predict_type, prediction, stake)places a prediction
cancel_prediction(prediction_id)cancels an unsettled prediction, refunds stake
get_betting_status()point balance, pending stakes, min/max stake
get_my_predictions(match_id=None, settled_only=False)your prediction history
get_prediction_detail(prediction_id)one prediction in full
get_my_stats()your win rate, total staked, etc.
get_leaderboard(limit=50, sort_by="points")top predictors (sort_by: points|accuracy)

Placing a bet — predict_type and prediction

prediction is a dict whose shape depends on predict_type. Fill ONLY the keys for that type:

predict_typepredictionmeaning
win_draw_loss{"choice": "home"|"draw"|"away"}match result
exact_score{"home": N, "away": N}exact final score
total_goals{"range": "0-1"|"2-3"|"4+"}total goals bucket
first_goal{"team": "TEAM_CODE"}which team scores first (e.g. BRA)

stake = points to wager: multiple of 10, min 10, max 10000.

Recommended place_bet flow

  1. get_betting_status() — confirm enough available points.
  2. get_match_detail(match_id) or get_today_matches() — confirm the match is open and get team codes (needed for first_goal).
  3. place_bet(match_id, predict_type, prediction, stake).
  4. Read back the returned prediction ID to the user.

Example:

python3 -c "from core.skill_tools import worldcup; import json; print(json.dumps(worldcup.place_bet(42, 'win_draw_loss', {'choice':'home'}, 100)))"

Notes

  • Points are the prediction-game currency, not real money — present as a game, never as financial advice.
  • cancel_prediction only works while a prediction is unsettled; it refunds the stake.
  • Match times are UTC; convert to the user's timezone when relevant.
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Categories
AI & Agent BuildingGame Development
First SeenJul 14, 2026
View on GitHub

More from starchild-ai-agent/official-skills

All 43 skills →
  • Feishu Binding1.3k
  • Upbit1.2k
  • Coinglass11.4k
  • Wallet8.8k
  • Hyperliquid8.5k
  • Coingecko7.8k
  • Twitter7.8k
  • Skill Creator7.7k
  • Twelvedata7.7k
  • Skillmarketplace7.1k
  • Orderly Onboarding7k
  • Project Builder5.2k
  • Browser Preview4.5k
  • Charting4.4k
  • Composio4.3k
  • Coder4.1k
  • Wallet Policy4.1k
  • Slide Creator4k
  • Community Publish4k
  • Preview Dev4k
  • Chart3.8k
  • Web Crawler3.8k
  • User Onboarding2.9k
  • Agentx2.7k

Recommended

More AI & Agent Building →
affaan-m avatar
codehealth-mcp

affaan-m/ecc

Real-time structural Code Health via CodeScene MCP — review before edits, verify score deltas after changes, gate commits and PRs. Use when reviewing code quality, refactoring, checking if AI changes degraded a file, or before commit/PR.
1.4k
240.8k
dotnet avatar
code-testing-agent

dotnet/skills

MANDATORY ENTRY POINT for generating or writing tests. Invoke this skill before editing files whenever the user asks to generate tests, write/add unit tests, scaffold a test project or suite, improve/achieve coverage, extend an existing suite to cover an untested method, or test an app, API, service, module, library, or package. Applies to a single function, method or file as much as to a whole project — scope changes how much of the workflow runs, never whether the skill applies. Invoke it when the workspace looks sparse, gutted or partially deleted — then test only the source that remains and never restore missing source. Polyglot: C#/.NET, Python, TypeScript/JavaScript, Go, Rust, Java, Ruby. DO NOT USE FOR: running existing tests (use run-tests); analyzing coverage reports (use coverage-analysis or crap-score); MSTest-specific test authoring or modernization (use writing-mstest-tests).
1.4k
5.1k
google-gemini avatar
vertex-ai-api-dev

google-gemini/gemini-skills

Guides the usage of Gemini API on Google Cloud Vertex AI with the Gen AI SDK. Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.
1.3k
3.9k
starchild-ai-agent avatar
feishu-binding

starchild-ai-agent/official-skills

Feishu/Lark binding: device flow authorization, connect, disconnect, status check. Use when setting up or managing Feishu/Lark connection (e.g. connect Feishu, connect Lark, bind 飞书, check Feishu status, disconnect Lark).
1.3k
22
aradotso avatar
anthropic-cybersecurity-skills

aradotso/security-skills

anthropic cybersecurity skills
1.3k
6
aradotso avatar
copaw-ai-assistant

aradotso/trending-skills

copaw ai assistant
1.3k
61