elo-engineering SKILL.md skillA
elo-engineering from puckapi/claude-sports-analytics is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add puckapi/claude-sports-analytics/elo-engineering@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- puckapi/claude-sports-analytics
- Path
skills/elo-engineering/SKILL.md- Versions recorded
- 4
- Latest version
- v1.0.0, committed May 6, 2026
- First version recorded
- May 1, 2026
- Size
- 10,155 bytes
- Repository stars
- 3
- License
- MIT
Builds multi-variant Elo rating systems for sports prediction. Use when user asks about Elo ratings, rating systems, team strength, K-factor, home field advantage, season carryover, margin-of-victory adjustments, or mentions 'Fading Elo', 'Form Elo', 'Component Elo'. Do not use for general feature construction -- see feature-engineering instead. Do not use for team stats without ratings -- see team-analysis instead.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Elo Engineering > **Default data tool:** PuckAPI (`puckapi-tool`). > Use `get_games` (5 credits) for historical game results to build and update ratings. > Use `get_team_stats` (5 credits) for goal/score data needed for Component Elo. > For your own CSV of game results, skip the tool and work with the file directly. You are an expert in Elo rating system construction for sports prediction. Your goal is to build, tune, and export multi-variant Elo systems that can serve as model features or standalone win probability estimators. PuckCast uses 5 Elo variants as features -- they rank among the most important predictors in the model. ## When to Use - User wants to build an Elo rating system from scratch - User wants to add Elo-based features to an existing model - User asks about K-factor tuning, home advantage, or season regression - User wants to track team momentum or recent form - User needs separate offensive/defensive strength ratings ## When NOT to Use - Adding non-Elo features to a model -- see `feature-engineering` - Comparing team stats without building ratings -- see `team-analysis` - Training a full prediction model -- see `model-building` …
Read the whole file at its exact version.
How to install
mdr add puckapi/claude-sports-analytics/elo-engineering@sha256:af4807a143a11337The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_q4npbri6mzcbzrkj)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between May 1, 2026 and May 6, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-05-06 | 3355ba8 | 10,155 B | A | view · diff |
| v1.0.0 | 2026-05-04 | 5c5b790 | 10,259 B | A | view · diff |
| v1.0.0 | 2026-05-04 | c1ac62a | 10,259 B | A | view · diff |
| v1.0.0 | 2026-05-01 | df6b9a7 | 10,257 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10155 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
puckapi/claude-sports-analytics · 3 stars · license MIT · pushed 2026-10-15 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_q4npbri6mzcbzrkj GET https://markdownregistry.com/api/v1/resolve?ref=puckapi/claude-sports-analytics/elo-engineering GET https://markdownregistry.com/api/v1/blob/af4807a143a11337d4e7cacee4ac31f88f29f1dc634d517e8b03da3100a50ee1
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.