Race Week (Grade A) logo

Race Week (Grade A)Security-tested data-ai skill for Claude AI. Grade A. Parallel race-week consult producing a race-day brief

(0)
Daniel NikulshynReviewed by Daniel Nikulshyn·Updated July 2026

Overview

Race Week (Grade A) is a security-tested data-ai skill for Claude AI. It provides a parallel race-week consult producing a race-day brief. When the runner's race is within 7 days, three specialists, the pace-strategist, fuel-advisor, and physio-advisor, consult in parallel to synthesize a single, self-contained race-day brief. The brief covers everything the runner needs without requiring multi-tab research. It is triggered by keywords such as 'race week' or 'taper' and can be explicitly requested by the runner or automatically generated based on the goal JSON and training log.

Key features

  • Parallel consult with pace-strategist, fuel-advisor, and physio-advisor
  • Safety gate for unresolved health issues
  • Personalized racing strategy brief
  • Nutrition brief with carb-loading protocol and in-race fueling schedule
  • Taper compliance review and final-week training guidance

Pricing

Model
Free
Category
Skills
Rating
No reviews yet

Use cases

Pre-Race Preparation

A runner uses Race Week to generate a comprehensive race-day brief within 7 days of their marathon, including a racing strategy, nutrition plan, and taper guidance.

Taper and Recovery

A runner uses Race Week to review their taper compliance and receive guidance on final-week training, ensuring they're well-prepared for the upcoming race.

Pros & Cons

Pros

  • Provides a comprehensive and concise race-day brief
  • Eliminates the need for multi-tab research
  • Offers personalized guidance from three specialists
  • Includes safety checks for unresolved health issues

Cons

  • Limited to runners with races within 7 days
  • Requires access to specific data files (goal.json, runner-profile.json, plan-state.json, training-log.jsonl)
  • May not be suitable for runners with complex or unusual needs

Reviews

Sign in to leave a review.

No reviews yet. Be the first!

Q&A

How It Works?

Eight specialist agents organized across four lanes. You never pick an agent — OMPB routes based on what you say.

Asked by Grzegorz Lewandowski · Aug 20, 2025

Why Not Just Ask an AI?

You could paste your data into a chatbot every week. Here's what a purpose-built coaching system does that a blank chat — or a watch app — doesn't: | | Generic AI chat | Watch app (Garmin/COROS/…) | oh-my-personal-best | |---|:---:|:---:|:---:| | Reads your full training history | ✗ re-paste each time | ◑ shows data, generic plans | ✅ reads your entire log | | Diagnoses your specific limiter | ◑ generic tips | ✗ | ✅ race-analyst | | Safety gate before every plan | ✗ | ✗ | ✅ plan-critic | | Stops you when you're hurt | ◑ inconsistent | ✗ | ✅ physio-advisor priority | | Adapts weekly to what you actually ran | ✗ manual | ◑ rigid templates | ✅ weekly-adapt | | Where your data lives | their servers | device-locked | ✅ local, in your Claude Code | The gate lane is the difference: a plan with an unsafe volume ramp or an inadequate taper never reaches you. No self-approval.

Asked by Grace Okafor · Aug 4, 2025

Why oh-my-personal-best?

It reads everything you've ever run — not last week's averages. Thousands of activities, the full arc of your fitness — the context no human coach has the hours to actually read. It finds the one thing holding you back — aerobic base? threshold? durability? Most runners train their strengths and stall. OMPB names your limiter and goes after it. A plan that's actually yours — back-calculated from your goal and your real data, not a generic sub-3:30 PDF that has no idea you ran 900 times last year. It won't get you injured — every plan clears a separate safety gate before you ever see it. Unsafe volume ramps and crushed tapers never reach you. No self-approval, ever. It knows when to stop you — one mention of pain and the plan stands down. A coach, not a doctor. Zero learning curve — no jargon, no commands, no dashboards to decode. Say it in plain language; the right specialist answers.

Asked by Margaret Whitfield · Jul 29, 2025

Not Sure Where to Start?

Just describe where you are and where you want to be — "first half marathon, I can run 10K in 55:00, race in 12 weeks." OMPB diagnoses your current fitness, judges whether the goal is realistic, and builds a plan around the gap. You don't need to know what a tempo run or a taper is.

Asked by Tomáš Novák · Jul 18, 2025

Ask a question

Skills alternatives

Using Git Worktrees (Grade A) logo
Using Git Worktrees (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktre

(0)
Free
Ga4 Bigquery Schema (Grade A) logo
Ga4 Bigquery Schema (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. GA4 BigQuery Export Schema Reference — complete field reference, nested structures, query patterns, and performance tips

(0)
Free
Meta Capi (Grade A) logo
Meta Capi (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Meta Conversions API (CAPI) Setup Reference — architecture, event types, customer information hashing, deduplication, implementation examples, AEM

(0)
Free
Callees (Grade A) logo
Callees (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. Lista o que uma funcao/metodo chama (call graph direto)

(0)
Free
Test Module Name (Grade A) logo
Test Module Name (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Name Haskell test modules after the module under test with a Spec suffix in the same namespace. Use when writing or reviewing Haskell test module

(0)
Free
Board Of Directors (Grade A) logo
Board Of Directors (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Simulate a 5-member expert board deliberation for major decisions. Use when evaluating plans, architecture choices, feature designs, or any decisi

(0)
Free
Advpl Mvc Avancado (Grade A) logo
Advpl Mvc Avancado (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. MVC avançado via PE (Pontos de Entrada) — adicionar grids customizadas em telas MVC padrão (CNTA300/MATA070/MATA440/MATA460/FINA040 via *STRU)

(0)
Free
D
Docs Writer (Grade A)Skills

Security-tested devops skill for Claude AI. Grade A. **WORKFLOW SKILL** — Maintains repository documentation accuracy and freshness across the docs site, agent files, and changelog. WHEN: "update docs

(0)
Free