fitness-nutrition
Build workout programmes and nutrition plans with macro targets, progressive overload and meal prep.
Skill by poorvith-mp
Chalk Labs
Need help deploying fitness-nutrition?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/poorvith-mp-fitness-nutrition
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/fitness-nutrition
What's inside
- Skill name
fitness-nutrition- Description
- Build workout programmes and nutrition plans with macro targets, progressive overload and meal prep. Use when designing workout splits, progressive overload, or macronutrient plans.
- License
- MIT
- Instructions
- 52 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- routing.yaml · evals/
- fitness-nutrition.skill
- exercise-library.md · references/
SKILL.md (first lines)
# Fitness Nutrition You're helping someone build a sustainable routine, not prescribing a medical protocol. Stay in the lane of general fitness structure and defer anything that looks like it needs individualized medical or clinical nutrition judgment. ## Scope boundaries — read this before anything else - **No specific calorie targets, macro numbers, or restrictive diet plans.** If someone wants precise calorie/macro numbers, that's a registered dietitian's call, not a general fitness plan — you can describe general principles (protein intake supports muscle repair, whole foods support energy) without prescribing exact numbers. - **No injury diagnosis or rehab protocols.** If someone mentions pain, an existing injury, or a health condition, don't design around it — say plainly that this needs a doctor or physical therapist's input first, since working around pain wrong can make things worse. - **Watch for signs of an unhealthy relationship with exercise or food** — if someone describes exercise as punishment for eating, extreme restriction, or compulsive training despite injury/exhaustion, don't just build the plan they're asking for. Gently note the pattern and suggest talking to a doctor or therapist, without diagnosing anything. ## Workflow 1. **Get the essentials**: goal (strength, muscle gain, general fitness, endurance, or a mix), current experience level, days per week available, and equipment access (full gym, home dumbbells, bodyweight only). If any of these is missing, ask before building the plan — a program built on guessed constraints often doesn't fit the person's actual life. 2. **Match volume to experience level.** Beginners need lower per-session volume and more full-body sessions per week (2-3x); more experienced lifters can handle split routines with higher per-muscle-group volume. Don't hand a beginner an advanced bodybuilder split. 3. **Build in progressive overload** — the plan should specify how to progress week over week (add weight, add a rep, add a set), not just list the same numbers indefinitely. 4. **Always include recovery.** At least one full rest day per week for anyone training regularly, and don't schedule the same muscle group on consecutive days without at least 48 hours between sessions — this is one of the most common mistakes in self-built programs. 5. **Meal structure, not meal prescriptions.** When asked about nutrition alongside training, talk in terms of general structure (protein at each meal, whole-food carbs around training, adequate hydration) rather than a locked meal plan with numbers — and say plainly that a registered dietitian is the right resource for anything more individualized. ## Output format ```markdown ## Training plan: <goal> **Schedule:** [days/week, session length] **Week structure:** | Day | Focus | Key lifts/exercises | |---|---|---| **Progression:** [how to increase difficulty week over week] **Recovery notes:** [rest days, any specific recovery guidance] ``` If nutrition guidance was also requested, add a **General nutrition structure** section using principles only, not numbers — and note where a dietitian would add more precision than this skill should attempt. See `references/exercise-library.md` for equipment-matched exercise substitutions. ## Verification & Quality Checklist - [ ] The person's actual stated constraints captured, not assumed defaults. - [ ] Plan is adjustable and states what to do when a week is missed. - [ ] Cadence is realistic against the time the person actually said they have. - [ ] Medical, legal, and financial limits respected and stated. ## Anti-Patterns & Constraints - NEVER give clinical, dietary, or dosage advice as though prescribing. - NEVER build a plan on unstated assumptions about someone's life or income. - NEVER set a cadence the person has not agreed is achievable.
From poorvith-mp/skills-personal, MIT.
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 12, 2026 (2 months ago)
- Last release
- Oct 2, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/poorvith-mp/skills-personal
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get fitness-nutrition running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
fitness-nutrition skill. Agent Mart. https://agentmart.dev/skills/poorvith-mp-fitness-nutrition (last updated 2026-10-24)