← Back to Skills Marketplace
sirsws

AKM Fitness

by sirsws · GitHub ↗ · v1.0.2 · MIT-0
cross-platform ✓ Security Clean
149
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install akm-fitness-planner
Description
AKM implementation for training decision workflows. Models goals, body limits, equipment context, time budget, and recovery before outputting a workout decis...
README (SKILL.md)

AKM Fitness

AKM Fitness is a profile-first training decision skill for real-world constraints.

It does not start with a workout template. It starts by modeling the operator: goals, body limits, equipment reality, time budget, recovery state, and adherence risk.

Quick Reference

Item Details
Primary outcome a constraint-aware training decision
Best use case when generic workout advice fails because the user's actual constraints matter
Public source https://github.com/sirsws/akm/tree/main/branches/fitness
Sample record https://github.com/sirsws/akm/blob/main/branches/fitness/skill/SAMPLE_RECORD.md
Research paper https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6231465
Install source https://github.com/sirsws/akm

Public Links

  • GitHub branch: https://github.com/sirsws/akm/tree/main/branches/fitness
  • Skill files: https://github.com/sirsws/akm/tree/main/branches/fitness/skill
  • Sample record: https://github.com/sirsws/akm/blob/main/branches/fitness/skill/SAMPLE_RECORD.md
  • Branch paper: https://github.com/sirsws/akm/tree/main/branches/fitness/paper
  • SSRN paper: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6231465

Installation

ClawHub / OpenClaw:

  • install from this listing

Skills CLI:

npx skills add https://github.com/sirsws/akm --skill akm-fitness-planner --full-depth

What This Skill Changes

Most fitness agents answer too early.

They assume the user has one clear goal, normal recovery, enough time, stable equipment, and no meaningful body limitation. That assumption is usually false.

AKM Fitness changes the order of operations: profile first, decision second.

When to Use

Use this skill when:

  • injuries or physical limits materially affect training choices
  • equipment availability changes what is realistic
  • time budget is hard and cannot be ignored
  • recovery state should alter the decision
  • generic training plans keep failing in practice

Do not use this skill when:

  • the user only wants casual fitness chat
  • a medical diagnosis is being requested
  • rehabilitation planning should be handled by a qualified clinician
  • critical inputs are missing and the user refuses to provide them

Core Rule

No profile, no serious plan.

If the necessary state is unclear, the skill should surface MissingInputs instead of fabricating confidence.

Workflow

  1. ELICITATION_PROMPT.md
  2. RECORD_TEMPLATE.md
  3. EXECUTION_PROMPT.md
  4. SAMPLE_RECORD.md

Output Contract

Outputs should include:

  • StateJudgment
  • PrimaryDecision
  • DecisionConfidence
  • Plan
  • RiskNotes
  • NonNegotiables
  • MissingInputs

Operating Boundary

AKM Fitness is a training decision aid. It is not a medical diagnosis tool, not a rehab replacement, and not a motivational wrapper for missing information.

Files to Load

Read these files before running the skill:

  • ELICITATION_PROMPT.md
  • RECORD_TEMPLATE.md
  • EXECUTION_PROMPT.md
  • SAMPLE_RECORD.md\r
Usage Guidance
This is an instruction-only fitness decision skill: it contains prompts and templates for eliciting user goals, constraints, equipment, time budget, and recovery, and produces structured workout decisions. It does not request secrets, install code, or access system files. Before installing, verify the GitHub repo owner (https://github.com/sirsws/akm) if provenance matters to you, and remember this is a decision aid—not medical advice; avoid using it for diagnosis or rehab planning without a qualified clinician. If you plan to feed sensitive personal medical history, consider redacting identifiable details and ensure you’re comfortable with how the agent/platform stores conversation data.
Capability Analysis
Type: OpenClaw Skill Name: akm-fitness-planner Version: 1.0.2 The skill bundle consists of structured Markdown prompts and documentation for a fitness planning assistant called AKM Fitness. The logic is designed to elicit user constraints (injuries, equipment, time) and generate workout decisions based on a 'profile-first' methodology. There is no evidence of malicious code, data exfiltration, or harmful prompt injection; all instructions are strictly aligned with the stated fitness-related purpose and the installation commands provided are standard for the OpenClaw ecosystem.
Capability Assessment
✓ Purpose & Capability
Name and description match the provided prompt files and sample record: the package is a three-stage (elicitation → record → execution) fitness decision aid. No env vars, binaries, or config paths are requested that would be unrelated to this purpose.
✓ Instruction Scope
SKILL.md and the included prompt files limit runtime instructions to eliciting user health/training state and producing structured decisions. They do not instruct reading arbitrary system files, environment variables, or sending data to external endpoints beyond citing public GitHub/SSRN links for provenance.
✓ Install Mechanism
No install spec and no code files present; it's instruction-only, so nothing will be written to disk or executed by an installer as part of the skill package itself.
✓ Credentials
The skill requires no credentials, binaries, or config paths. All required inputs are user-provided fitness/profile data, which is proportionate to a decision-aid fitness skill.
✓ Persistence & Privilege
always is false and there is no install-time behavior that modifies other skills or system-wide settings. disable-model-invocation is false (normal), meaning the agent can invoke the skill autonomously per platform defaults; this is expected and not, by itself, a red flag.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install akm-fitness-planner
  3. After installation, invoke the skill by name or use /akm-fitness-planner
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
Add public sample record and clean source links.
v1.0.1
Cleaned ClawHub landing page content and removed internal comments.
v1.0.0
Initial public release.
Metadata
Slug akm-fitness-planner
Version 1.0.2
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 3
Frequently Asked Questions

What is AKM Fitness?

AKM implementation for training decision workflows. Models goals, body limits, equipment context, time budget, and recovery before outputting a workout decis... It is an AI Agent Skill for Claude Code / OpenClaw, with 149 downloads so far.

How do I install AKM Fitness?

Run "/install akm-fitness-planner" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is AKM Fitness free?

Yes, AKM Fitness is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does AKM Fitness support?

AKM Fitness is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created AKM Fitness?

It is built and maintained by sirsws (@sirsws); the current version is v1.0.2.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463942 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259883 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200739 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191401 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190375 · by oswalpalash

💬 Comments