Fitness planner

Skill zxt6991-source/fitness-agent/skills/fitness-planner

Install

npx -y skills add zxt6991-source/fitness-agent --skill fitness-planner

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Create forward-looking training plans from Strava-derived fitness notes already stored in an Obsidian vault. Use when the user wants a realistic next-week or next-two-week plan generated from recent load, consistency, sport mix, and recovery signals in their existing notes.

SKILL.md

3.3 KB, 700 tokens by cl100k_base, as published. Nobody here has run it

Fitness Planner

Use the bundled wrapper script to run the planning CLI:

scripts/run_fitness_planner.sh --help

This skill is for turning the existing Obsidian training log into an actionable upcoming plan.

When To Use It

Use this skill when the user wants to:

generate a next 7-day or 14-day training plan from historical notes
convert recent training load and sport mix into a realistic upcoming schedule
produce a conservative recover, maintain, or build plan
write the generated plan back into Obsidian as a note and planning dashboard

Do not use this skill to fetch new Strava data. Use fitness-agent for ingest and fitness-insights for retrospective analysis. Use fitness-planner for the next-step plan.

Workflow

Confirm the vault already contains fitness-log notes under Activities/.
Read the existing notes and compute recent load, consistency, and dominant sport.
Choose a planning mode:
- auto: infer recover, maintain, or build
- explicit override: force one of those modes
Generate a plan note plus planning dashboard files under Plans/.
Explain that the plan is heuristic and should be adjusted for injury status, event goals, and real-life constraints.

Command

Generate the next 7-day plan from the configured vault:

scripts/run_fitness_planner.sh plan generate

Generate a 14-day build plan with explicit overrides:

scripts/run_fitness_planner.sh \
  --vault-path "/path/to/YourVault" \
  --root-folder "Fitness/Strava" \
  plan generate \
  --days 14 \
  --goal build \
  --start-date 2026-03-16

Outputs

The skill writes these artifacts under the configured root folder:

Plans/Training Plans.base
Plans/Fitness Planner.md
Plans/Generated/YYYY-MM-DD-next-7-days-auto.md or similar

The generated plan note includes:

plan mode and rationale
weekly target sessions, duration, and load proxy
a day-by-day schedule
caution notes and review prompts

Guardrails

Treat generated plans as structured suggestions, not medical advice or coach-grade programming.
Prefer conservative progression. The default auto mode should not create aggressive load jumps.
Be explicit when the user forces build despite recovery signals in recent data.
Depend only on note-level metrics already present in the vault.
Keep generated plan notes deterministic enough to be regenerated safely.

Trigger Examples

$fitness-planner 基于我现有的运动数据生成下一周训练计划
$fitness-planner 给我做一个未来两周的 build 计划
$fitness-planner 根据最近训练量生成更保守的恢复周安排

Resources

fitness_planner.py: self-contained CLI entrypoint packaged with the skill.
src/fitness_planner/: parser, analysis engine, planning heuristics, and output generators.
scripts/run_fitness_planner.sh: stable wrapper for local execution.
references/planning_heuristics.md: heuristic planning rules and caution language.

Gives 0 of the 12 instructions most plan spec skills give in 700 tokens

Counted across 1,100 of the 1,860 authors here whose files we hold, read 2026-08-06

ask one question at a timein 46 of 1100, across 38 files
Break plans into vertical slicesin 28 of 1100, across 10 files
Publish issues in dependency orderin 27 of 1100, across 9 files
Iterate until user approves the breakdownin 24 of 1100, across 6 files
Explore the repository to understand the codebase statein 24 of 1100, across 7 files
Use domain glossary vocabularyin 23 of 1100, across 5 files
Apply correct triage labels to published issuesin 23 of 1100, across 5 files
Write failing tests before implementation codein 23 of 1100, across 18 files
Prefer AFK slices over HITLin 22 of 1100, across 7 files
ask clarifying questions until requirements are concretein 21 of 1100, across 13 files
Respect existing architecture decision recordsin 20 of 1100, across 5 files
write a specification before writing any codein 20 of 1100, across 12 files

Said here and by no other author read

confirm the vault contains fitness-log notes
read existing notes and compute recent metrics
choose a planning mode
generate a plan note and dashboard files
explain the plan is heuristic and adjustable
run the wrapper script to generate plans

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.