Borrowing it
Nothing to install: this file belongs to ashishpatill/tell-proof. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ashishpatill/tell-proof/master/.cursor/skills/sport-site-research/SKILL.mdgit clone --depth 1 https://github.com/ashishpatill/tell-proofWrote 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/ashishpatill/tell-proof/sport-site-research)<a href="https://agentmods.dev/skills/ashishpatill/tell-proof/sport-site-research"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/sport-site-research/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/ashishpatill/tell-proof/sport-site-research"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/sport-site-research.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 | $0.00080 | $0.00824 |
| Opus 5.5 | $0.00032 | $0.00330 |
| Sonnet 5.5 | $0.00016 | $0.00165 |
| Haiku 4.5 | $0.00008 | $0.00082 |
Grade A, and why
sport-site-research 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 1mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sport-site-research
Hard gate: Do not design, code, or run agency:run for a sport site until a research brief exists for that sport.
Extends: website-domain-research via parent graph sport-matchday-web (LoadPriorDomain first).
Auto-trigger: Always-applied tell-domain-research + engine routes website-domain-research then sport-matchday-web when sportId is set or query language matches.
Full playbook: agent-skills/web-design/premium-content-custom-web/sport-vernacular-craft/SKILL.md
Parent graphs: website-domain-research → sport-matchday-web
Engine packs: @tell/design-skills → loadPriorDomain / getSportPack / routeDomainResearchSkills / sportResearchBriefTemplate
Deep notes: research/SPORT_SITE_VERNACULAR.md
Why this exists
Generic “sports website” templates fail fans. Each sport has:
- A cultural tempo (overs vs minutes vs periods vs nested points)
- A glance grammar (what must be readable in one second on a mid-range phone)
- Format lenses that change which facts matter
- Category gaps major portals leave open (layout jitter, wrong tempo UI, buried situation)
- Multipage IA (home / live / scorecard / series / rankings / notebook) — not a single hash page
Building without research produces another purple/card-grid sports shell.
Workflow (every sport brief)
1. website-domain-research → load-prior-domain(sport:<id>)
2. requirement-gap-diff — reuse pack fields; walkthrough only for gaps
3. Identify sport → getSportPack(id) / DomainResearchPack multipage fields
4. Write research/SPORT_BRIEF_<sport>.local.md from sportResearchBriefTemplate(id)
(gitignored local notes OK; committed principles stay in research/SPORT_SITE_VERNACULAR.md)
5. Fill Fresh research notes: fan behavior, anonymised category failures, latency budget
6. Choose default format lens + access-mode priority (usually glance-live first)
7. Plan score spine stability + progressive disclosure + Core route classes
8. emit-training-episode (required)
9. Only then: agency:run / hand craft / evolve specimen
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.
- 1mo ago First seen · 77 lines · 80 tokens per session scan A c598ac56420b
sport-site-research is a skill published in the GitHub repository ashishpatill/tell-proof (2 stars, last pushed 22d ago), licensed MIT. It adds 80 tokens to every session and 824 once invoked, about $0.0003 per session on Opus 5.5. 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
vfx-text-cursor
Cursor light trail, chromatic rays, and directional flares for word-by-word quote reveals in video intros.
animate-text
Curated text animation catalog with exact JSON specs for headings, labels, counters, and text swaps. Use when an agent needs to pick or translate named effects like soft blur in, typewriter, shared axis, line reveal, stagger, crossfade, or kinetic builds into WAAPI, Motion, Framer Motion, GSAP, CSS, Lottie, Rive, or…
better-design
Build, improve, and review production interfaces with the Better Design MCP. Use for frontend design, UI, UX, interactions, flows, forms, navigation, components, styling, design systems, accessibility, responsive layouts, motion, React Native, Expo, Shopify, Three.js, and product video work, especially when creating…
orchestrate
START HERE for HackerRank Orchestrate. Master plan for the 24-hour challenge - scoring targets, the phase order, which orchestrate- skill to run next, what to do when a step fails, and the transcript discipline that applies all day. Use at the start of the challenge, whenever you are unsure what to do next, or when…
orchestrate-score
Estimate the Orchestrate score the way HackerRank weights it - four signals (Code ZIP 30%, Output CSV 30%, AI Interview 30%, Chat Transcript 10%) with the published sub-weights. Uses the kit's scoring module as a heuristic and clearly separates measured facts from estimates. Use before submission, after each…
orchestrate-build
Orchestrate phases 1 and 2 - turn the problem statement into a written design (DESIGN.md) and then build the agent so it runs end to end on the sample with validation, failure handling and secrets handled. Use after reading the problem statement and sample data, and until the pipeline writes a valid CSV for the whole…