Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Predict FIFA World Cup matches, full tournament paths, and champion probabilities through Codex-native subagents that analyze live news, weather, injuries, markets, Polymarket, tactics, and…
Install World Cup Predictor
$ npx skills add agentara/skills --skill world-cup-predictor -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agentara/skills world-cup-predictor --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/entertainment/world-cup-predictor .claude/skills/world-cup-predictor && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "world-cup-predictor" agent skill from https://github.com/agentara/skills/tree/main/skills/entertainment/world-cup-predictor into .claude/skills/world-cup-predictor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "world-cup-predictor", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/agentara/skills/tree/main/skills/entertainment/world-cup-predictorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add agentara/skills --skill world-cup-predictor -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agentara/skills world-cup-predictor --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/entertainment/world-cup-predictor .agents/skills/world-cup-predictor && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "world-cup-predictor" agent skill from https://github.com/agentara/skills/tree/main/skills/entertainment/world-cup-predictor into .agents/skills/world-cup-predictor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "world-cup-predictor", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agentara/skills --skill world-cup-predictor -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agentara/skills world-cup-predictor --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/entertainment/world-cup-predictor .cursor/skills/world-cup-predictor && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "world-cup-predictor" agent skill from https://github.com/agentara/skills/tree/main/skills/entertainment/world-cup-predictor into .cursor/skills/world-cup-predictor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "world-cup-predictor", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/agentara/skills.git --path skills/entertainment/world-cup-predictor--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add agentara/skills --skill world-cup-predictor -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agentara/skills world-cup-predictor --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/entertainment/world-cup-predictor .gemini/skills/world-cup-predictor && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "world-cup-predictor" agent skill from https://github.com/agentara/skills/tree/main/skills/entertainment/world-cup-predictor into .gemini/skills/world-cup-predictor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "world-cup-predictor", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install agentara/skills world-cup-predictorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add agentara/skills --skill world-cup-predictor -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/entertainment/world-cup-predictor .github/skills/world-cup-predictor && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "world-cup-predictor" agent skill from https://github.com/agentara/skills/tree/main/skills/entertainment/world-cup-predictor into .github/skills/world-cup-predictor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "world-cup-predictor", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agentara/skills --skill world-cup-predictor -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agentara/skills world-cup-predictor --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/entertainment/world-cup-predictor .opencode/skills/world-cup-predictor && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "world-cup-predictor" agent skill from https://github.com/agentara/skills/tree/main/skills/entertainment/world-cup-predictor into .opencode/skills/world-cup-predictor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "world-cup-predictor", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
world-cup-predictor- GitHub stars
- 602
- Token cost
- ~1.9k tokens
- SKILL.md length
- 849 words
- Files
- 36 (incl. scripts, references, assets)
- Skills in repo
- 20
- Repo updated
- First seen
- Licence
- MIT
At a glance
Predict FIFA World Cup matches, full tournament paths, and champion probabilities through Codex-native subagents that analyze live news, weather, injuries, markets, Polymarket, tactics, and…
- Works in 10 steps: Start the dashboard server first. → Initialize the page state. → Lock finished results. → …
- Asked to forecast World Cup games
- SKILL.md covers Overview, Default Action, Regression Checks and Prediction Contract, plus 2 more sections
- Runs JavaScript scripts from its folder; calls python3; needs ODDS_API_KEY
What it does
World Cup Predictor is an agent skill from agentara/skills. Predict FIFA World Cup matches, full tournament paths, and champion probabilities through Codex-native subagents that analyze live news, weather, injuries, markets, Polymarket, tactics, and tournament context while updating a real-time web dashboard. Use when asked to forecast World Cup games, predict the full World Cup outlook, compare match forecasts, or show prediction progress live in a browser.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 39 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/dashboard/app.js` and `assets/dashboard/data/final-subagent-dashboard.json`).
It sits in Agent Workflows, covering Subagents. It works with Polymarket. The repository describes itself as: Original and practical skills for AI builders. The licence is MIT.
When your agent uses it
- Asked to forecast World Cup games
- Predict the full World Cup outlook
- Compare match forecasts
- Show prediction progress live in a browser
Example prompts
- “/world-cup-predictor”
Requirements
- Python 3
- Node.js
- A credential in ODDS_API_KEY
Workflow steps
10 steps, taken from the first numbered list in SKILL.md.
- Start the dashboard server first.
- Initialize the page state.
- Lock finished results.
- Collect current signals.
- Read references/agent-native-workflow.md, references/research-protocol.md, and references/dashboard-data-contract.json.
- Spawn subagents using the layered workflow in references/agent-native-workflow.md.
- As subagent results arrive, publish partial dashboard JSON with scripts/publish_dashboard.py.
- Final output must include settled results plus forecasts for the remaining complete tournament path.
- Publish final data with scripts/publish_dashboard.py --complete.
- Run the local regression checks, then verify the dashboard and replay controls in the Browser plugin.
What it can do on your machine
Read from SKILL.md and the folder at commit 950e1bf. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (JavaScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
ODDS_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
World Cup Predictor loads about 1.9k tokens when it runs, and up to ~7.3k if it reads all its reference files. Until then it costs about 106 tokens; SKILL.md has 849 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from agentara/skills at commit 950e1bf, republished under its MIT licence (© agentara). 849 words, ~1,908 tokens.
Download SKILL.mdSave it as
.claude/skills/world-cup-predictor/SKILL.md (or your agent's skills folder). This skill also uses 35 other files; get the full folder from GitHub.- name
- world-cup-predictor
- description
- Predict FIFA World Cup matches, full tournament paths, and champion probabilities through Codex-native subagents that analyze live news, weather, injuries, markets, Polymarket, tactics, and tournament context while updating a real-time web dashboard. Use when asked to forecast World Cup games, predict the full World Cup outlook, compare match forecasts, or show prediction progress live in a browser.
World Cup Predictor
Overview
Use this skill to run an agent-native World Cup prediction room. The invoking Codex agent starts the web dashboard first, collects current signals, spawns subagents for independent analysis, and publishes each prediction update to the page as subagent results arrive.
Do not substitute deterministic, static, or hardcoded forecasts. The model reasoning must come from the current Codex agent and its subagents.
Default Action
For broad requests such as "predict this World Cup", "predict the tournament path", "who will win", or "预测这一届世界杯走向":
- Start the dashboard server first.
- Run
python3 scripts/start_dashboard.py --port 8789from the skill root in a long-running foreground tool session. - The helper chooses the next free port if 8789 is occupied. Report the printed URL.
- Do not rely on shell backgrounding with
&; some Codex shells clean up detached processes before the browser can connect.
- Run
- Initialize the page state.
- Run
scripts/bootstrap_worldcup.py --out assets/dashboard/data. - Run
scripts/set_live_state.py --stage kickoff --message "Starting subagent World Cup prediction room" --progress 0.03.
- Run
- Lock finished results.
- Verify official or reputable live score sources for already-finished matches.
- Write them to
assets/dashboard/data/locked-results.jsonwithscripts/sync_locked_results.py. - Do not ask subagents to predict locked matches.
- Collect current signals.
- Run
scripts/collect_signals.py --out assets/dashboard/data/signals.json. - If
signals.jsoncontains Polymarket rows withstatus: "fallback-required"or odds withstatus: "missing ODDS_API_KEY", preserve those rows and have the market subagent manually inspect the listed public pages. Do not treat empty market data as zero probability. - Run
scripts/set_live_state.py --stage signal-collection --message "Collected news, markets, weather, and optional odds" --progress 0.10.
- Run
- Read
references/agent-native-workflow.md,references/research-protocol.md, andreferences/dashboard-data-contract.json. - Spawn subagents using the layered workflow in
references/agent-native-workflow.md.- Keep
marketsandnews-weatheras sidecar signal agents. - For the group stage, spawn one subagent per group (
group-athroughgroup-l). - For knockouts, spawn one subagent per current-round match and advance round by round until the Final.
- The Final is predicted by one final-match subagent after semifinal winners are fixed.
- Keep
- As subagent results arrive, publish partial dashboard JSON with
scripts/publish_dashboard.py.- If a subagent takes longer than the first wait, continue waiting in longer intervals and publish heartbeat live-state updates so the dashboard stays alive.
- Do not interrupt slow role agents just to force a compact result. Only synthesize a missing role after an explicit failure, unavailable subagent tooling, or a user request to stop waiting.
- Final output must include settled results plus forecasts for the remaining complete tournament path.
- Publish final data with
scripts/publish_dashboard.py --complete. - Run the local regression checks, then verify the dashboard and replay controls in the Browser plugin.
Regression Checks
After publishing final dashboard data, run the local regression suite:
python3 -m unittest discover -s tests -vIf invoking from the repository root instead of the skill root, use:
python3 -m unittest discover -s world-cup-predictor/tests -vThese tests use Python's standard unittest framework. Do not require pytest unless a future dependency file explicitly adds it. Treat missing pytest as an environment/tooling issue, not a failed regression.
Show full SKILL.md (377 more words)Show less
Prediction Contract
- The web page is the live display surface. Keep it changing while work proceeds by updating
assets/dashboard/data/live-state.jsonandassets/dashboard/data/predictions.json. - Published prediction and live-state updates append snapshots to
assets/dashboard/data/replay.json; preserve it through the run so the completed dashboard can replay the forecast room. - Subagent reasoning is the prediction engine. Do not substitute deterministic ratings or hardcoded forecasts.
- Finished matches are settled results, not forecasts. Lock them before prediction and exclude them from subagent prediction scopes.
- Every match packet must include probabilities, predicted score, event timeline, momentum, evidence, risks, and environmental factors.
- The final dashboard JSON must match
references/dashboard-data-contract.json. - If subagent tools are unavailable, perform the same analysis in the main agent and state that parallelization was unavailable.
Evidence Rules
- Date every source. The World Cup is live and information changes quickly.
- Separate observed results from forecasts. Already-played matches must be locked as facts.
- Flag missing or stale data instead of filling it with guesses.
- If a live data connector fails, use the explicit fallback URLs in
signals.jsonand state the connector failure in the dashboard narrative. - For Polymarket and odds, capture market title, URL, timestamp, liquidity/volume when visible, price, and normalized implied probability.
- For tactical claims, cite concrete matchups: press resistance, buildup shape, transition defense, set pieces, wide overloads, goalkeeper distribution, squad rotation, altitude/travel/rest, and suspension risk.
- For simulation claims, cite the factor behind each event when possible: heat fatigue, humidity-driven tempo drop, injury limitation, set-piece mismatch, bench depth, goalkeeper profile, or tactical change.
Resources
references/agent-native-workflow.md: default no-key workflow for Codex agents that spawn subagents.references/research-protocol.md: source checklist, probability calibration, and confidence rubric.references/subagents.md: role prompts and handoff contracts for subagents.references/prediction-schema.json: JSON contract for match-level agent outputs.references/dashboard-data-contract.json: JSON contract for dashboard-level tournament predictions.references/worldcup-2026-groups.json: bootstrap group snapshot.scripts/bootstrap_worldcup.py: create dashboard data scaffolding.scripts/start_dashboard.py: start the static dashboard on 8789 or the next free port.scripts/collect_signals.py: collect current news RSS, Polymarket, weather, and optional odds signals.scripts/set_live_state.py: update the dashboard broadcast strip.scripts/replay_history.py: append dashboard snapshots for post-run replay.scripts/sync_locked_results.py: maintain already-finished match results that should not be predicted.scripts/publish_dashboard.py: publish partial or final subagent-derived dashboard predictions.scripts/merge_predictions.py: merge role-specific match packets when subagents produce overlapping outputs.scripts/validate_skill.sh: create a local virtualenv, install validation dependencies, and run the official skill validator.assets/dashboard/: static live dashboard.
© agentara, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 35 other files (scripts, references, assets) in skills/entertainment/world-cup-predictor of agentara/skills.
- SKILL.md
- agents/openai.yaml
- assets/dashboard/app.js
- assets/dashboard/data/FWC2026_regulations_EN.pdf
- assets/dashboard/data/final-subagent-dashboard.json
- assets/dashboard/data/groups.json
- assets/dashboard/data/live-state.json
- assets/dashboard/data/locked-results.json
- assets/dashboard/data/partial-subagent-dashboard.json
- assets/dashboard/data/predictions.json
- assets/dashboard/data/replay.json
- assets/dashboard/data/signals.json
- assets/dashboard/data/source-log.json
- assets/dashboard/data/third-place-annex-c.json
- assets/dashboard/index.html
- assets/dashboard/styles.css
- references
- … and 19 more
Open the folder on GitHubat commit 950e1bf
Compare with similar skills
World Cup Predictor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| World Cup Predictor this skillagentara/skills | 602 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 7 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 37 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 40 repos | ~1.5k | Automated safety check: Pass | None | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
- Official
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Dispatching Parallel Agents
ultralisp/ultralisp
A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Paseo Advisor Second Opinion
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
More from agentara/skills
All 20 skills in this repoPresentation Design
agentara/skills
Generate a premium 6-slide presentation design board as one single composite image.
Publish Research Site
agentara/skills
Turn a thesis, proposition, trend, question, or explainer topic into a citation-backed, image-rich, interactive website and deploy it with Vercel CLI.
Portrait Clone
agentara/skills
Turn any n reference images (with at least one person) into one exhaustively locked, always de-slopped, JSON-only AIGC image prompt whose every variable is pinned so each generation is nearly…
Torn Paper Collage Poster
agentara/skills
Create AI image-generation prompts and image-generation workflows for torn-paper editorial collage style posters with layered ripped paper, rough typography, stamps, tape, stickers, cutout subjects…
Article To HTML
agentara/skills
Render a markdown draft / any document in the conversation context into a single-file "paper proposal" HTML — serif body, monospace meta, numbered sections, inline SVG figures, callouts, tables…
Engineering Change Descriptions
agentara/skills
A skill your agent uses when writing, rewriting, or reviewing PR/CL descriptions, commit messages, or code-change summaries that explain what changed and why.
Related
Works with
Categories
Questions about World Cup Predictor
What does World Cup Predictor do?
Predict FIFA World Cup matches, full tournament paths, and champion probabilities through Codex-native subagents that analyze live news, weather, injuries, markets, Polymarket, tactics, and…. World Cup Predictor is an agent skill from agentara/skills. Predict FIFA World Cup matches, full tournament paths, and champion probabilities through Codex-native subagents that analyze live news, weather, injuries, markets, Polymarket, tactics, and tournament context while updating a real-time web dashboard.
When should I use World Cup Predictor?
World Cup Predictor fits situations like: asked to forecast World Cup games; predict the full World Cup outlook; compare match forecasts; show prediction progress live in a browser.
How do I install World Cup Predictor in Claude Code?
Run `npx skills add agentara/skills --skill world-cup-predictor -a claude-code`. Or copy the skill folder (skills/entertainment/world-cup-predictor in agentara/skills) into .claude/skills/world-cup-predictor in your project. Claude Code loads it when a task matches its description.
How do I install World Cup Predictor in Codex?
Run `npx skills add agentara/skills --skill world-cup-predictor -a codex`. Or copy the skill folder (skills/entertainment/world-cup-predictor in agentara/skills) into .agents/skills/world-cup-predictor in your project. Codex loads it when a task matches its description.
Can I use World Cup Predictor in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agentara/skills --skill world-cup-predictor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/world-cup-predictor, .gemini/skills/world-cup-predictor, .github/skills/world-cup-predictor and .opencode/skills/world-cup-predictor in your project.
What does World Cup Predictor need to run?
Going by SKILL.md and its folder, World Cup Predictor needs JavaScript for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named ODDS_API_KEY. Our summary lists: Python 3; Node.js; A credential in ODDS_API_KEY.
Does World Cup Predictor access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is World Cup Predictor safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does World Cup Predictor use?
World Cup Predictor is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does World Cup Predictor use?
About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.4k tokens, read only when the agent opens those files.
What are the alternatives to World Cup Predictor?
Skills that share tags, products or a category with World Cup Predictor: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains World Cup Predictor?
agentara (a GitHub organization) maintains it in agentara/skills, which has 602 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on September 29, 2026.
Source: agentara/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.