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 PuckAPI/claude-sports-analytics --skill nl-to-querygit clone --depth 1 https://github.com/PuckAPI/claude-sports-analyticsWrote 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/puckapi/claude-sports-analytics/nl-to-query)<a href="https://agentmods.dev/skills/puckapi/claude-sports-analytics/nl-to-query"><img src="https://agentmods.dev/badge/skills/puckapi/claude-sports-analytics/nl-to-query/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/puckapi/claude-sports-analytics/nl-to-query"><img src="https://agentmods.dev/badge/skills/puckapi/claude-sports-analytics/nl-to-query.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 | $0.00131 | $0.02158 |
| Opus 5 | $0.00066 | $0.01079 |
| Sonnet 5 | $0.00026 | $0.00432 |
| Haiku 4.5 | $0.00013 | $0.00216 |
Grade A, and why
nl-to-query 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 10d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NL to Query
Default data tool: PuckAPI (
puckapi-tool). Tool selection depends on the query --get_games(5cr),get_team_stats(5cr),get_goalie_stats(5cr),get_player_stats(5cr). For odds queries, noteget_oddscosts 10 credits per game.
You are an expert at translating natural language sports research questions into precise, executable data queries. Your goal is to map what the user means to what the data actually contains, then validate the result.
When to Use
- The user asks a research question in plain English rather than specifying a tool or field
- The query involves multiple conditions that need to be combined (e.g., "outshot AND home AND won")
- The user doesn't know what the underlying field names or thresholds are
- The query includes fuzzy hockey concepts that map to specific metrics
When NOT to Use
- The right skill is obvious from context -- call
game-lookup,team-analysis, orgoalie-analysisdirectly - The user is building model features -- see
feature-engineering(handles temporal guards and leakage) - The user wants odds data -- the credit cost ($0.10/game) should be flagged before running at scale
- The query requires data that doesn't exist in the tool (e.g., live tracking data, salary cap data)
Commands Available
| Command | What It Does | Credits |
|---|---|---|
get_games |
Game results with scores, team IDs | 5 |
get_team_stats |
Aggregated team metrics by season/period | 5 |
get_goalie_stats |
Goalie season stats and leaderboard | 5 |
get_player_stats |
Player bio data; goalie stats for goalies | 5 |
get_schedule |
Game schedule with IDs for further lookup | 2 |
get_game_detail |
Full game data with odds and goalie starts | 10 |
Commands That Do NOT Exist
| Not Available | Use Instead |
|---|---|
search_games |
Use get_games with date range + filters |
filter_games |
get_games returns data; apply filters client-side |
aggregate_stats |
Retrieve raw data, compute aggregates manually |
get_live_data |
Historical data only; no live game feed |
get_lineup |
Use get_game_detail for line combinations |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 189 lines · 131 tokens per session scan A 73b2a03cd69e
nl-to-query is a skill published in the GitHub repository PuckAPI/claude-sports-analytics (3 stars, last pushed 4mo ago), licensed MIT. It adds 131 tokens to every session and 2,158 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
dspy-gepa
Optimize instructions in DSPy programs via reflective evolution using dspy.GEPA without adding few-shot examples. Use when you want to optimize instructions without few-shot examples — a lightweight alternative when you do not have or do not want to use demonstrations. Common scenarios - optimizing instructions when…
dspy-primitives
DSPy typed wrappers (dspy.Image, dspy.Audio, dspy.Code, dspy.History, dspy.File, dspy.Reasoning, dspy.Tool, dspy.ToolCalls, dspy.Example, dspy.Prediction) for multimodal data, files, and structured outputs in signatures. Use when working with non-text inputs like images, audio, or code, passing PDFs or documents to…
ai-monitoring
Know when your AI breaks in production. Use when you need to monitor AI quality, track accuracy over time, detect model degradation, set up alerts for AI failures, log predictions, measure production quality, catch when a model provider changes behavior, build an AI monitoring dashboard, or prove your AI is still…
ai-querying-databases
Build AI that answers questions about your database. Use when you need text-to-SQL, natural language database queries, a data assistant for non-technical users, AI-powered analytics, plain English database search, or a chatbot that talks to your database. Also used for text-to-SQL that actually works, AI SQL…
ai-searching-docs
Build AI that searches your documents and answers questions. Use when building a knowledge base, help center Q&A, chatting with documents, answering questions from a database, search-and-answer over internal docs, customer support bot, or FAQ system. Also use when embedding search loses critical context, retrieval…
ai-stopping-hallucinations
Stop your AI from making things up. Use when your AI hallucinates, fabricates facts, is not grounded in real data, does not cite sources, makes unsupported claims, or you need to verify AI responses against source material. Also use when your LLM makes up facts, responses are disconnected from the input, or outputs…