Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add topprismdata/cultivating-ml-agent --skill trueskill-simulation-competition-strategygit clone --depth 1 https://github.com/topprismdata/cultivating-ml-agentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/trueskill-simulation-competition-strategy)<a href="https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/trueskill-simulation-competition-strategy"><img src="https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/trueskill-simulation-competition-strategy/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/trueskill-simulation-competition-strategy"><img src="https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/trueskill-simulation-competition-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00170 | $0.01190 |
| Opus 5 | $0.00085 | $0.00595 |
| Sonnet 5 | $0.00034 | $0.00238 |
| Haiku 4.5 | $0.00017 | $0.00119 |
Grade A, and why
trueskill-simulation-competition-strategy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TrueSkill Simulation Competition Strategy
Problem
Kaggle simulation competitions (Pokémon TCG AI Battle, Orbit Wars, etc.) use TrueSkill Bayesian scoring where each submission has N(μ,σ²). This creates counterintuitive dynamics that trap unwary competitors:
- LB scores swing wildly (±200 points) with no code changes
- Re-submitting to "test" destroys convergence progress
- Identical agents score 150-400 points differently (confirmed by forum)
- The latest 2 submissions are the only ones that count for final scoring
Context / Trigger Conditions
Use this skill when:
- Competing in any Kaggle Simulation Competition (not regular ML competitions)
- Your agent's LB score drops and you're tempted to debug the code
- You want to test a new agent variant by re-submitting
- You're within 2 weeks of the deadline and deciding final strategy
- You see rank swings that seem disproportionate to code changes
Solution
Lesson 1: Re-submitting Resets Convergence (Critical)
Each new submission starts at μ₀=600 (the prior). σ is high initially, causing large μ swings per game. σ decreases over time as more games are played.
DO NOT re-submit to "test" improvements. Every re-submit resets weeks of convergence progress.
Evidence (PTCG AI Battle, 2026-07):
| Submission | Submit-day score | After 3 days |
|---|---|---|
| v37 (anti-Arch) | 600.0 | 882.9 (+283) |
| v35 (anti-Psychic) | 559.0 | 847.7 (+289) |
| Nithin A (Archaludon) | 600.0 | 967.8 (+368) |
These "failed" agents weren't broken — they just hadn't converged. Re-submitting to "restore" them reset the convergence clock again.
Lesson 2: Latest 2 Rule — Final Scoring
Only the latest 2 submissions count for final scoring. All other submissions continue playing games but don't affect the final result.
Strategy: Ensure your latest 2 are your BEST 2 agents. Submit early enough for them to converge before the deadline.
Lesson 3: LB is a Bayesian Lottery (Not a Measurement)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 107 lines · 170 tokens per session scan A 498291bd2fbe
trueskill-simulation-competition-strategy is a skill published in the GitHub repository topprismdata/cultivating-ml-agent (5 stars, last pushed 13d ago), licensed MIT. It adds 170 tokens to every session and 1,190 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
huggingface-hub
Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.
tensorboard
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit.
mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.
datachain-knowledge
Use whenever datasets, cloud storage buckets, or data pipelines are mentioned — creating, saving, querying, listing, exploring, deleting, or processing data in S3, GCS, Azure Blob, or local storage. Also use when running any script that may create datasets as a side effect. Maintains a knowledge base at dc-knowledge/…
prompt-scanner
A scanner for text sent to an AI agent, looking for prompt injection and jailbreak attempts. Prompt injection is text that tries to override an agent's instructions; a jailbreak tries to bypass its safety limits.
install-openviking-memory
Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…