Przejdź do treści
Biblioteka skilli
Produktywność osobista · Konwersja i formaty

obsidian-workout-export

/obsidian-workout-export

Eksportuje dane treningowe z bieżącej rozmowy do pliku Markdown w formacie Obsidian, nazwanego datą rozmowy z danymi treningu.

Repozytorium
AI-Skills ↗
Licencja
MIT
Ostatnia zmiana repozytorium
25.10.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
8
Skrypty
1
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 25.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.

Co sprawdzić przed instalacją
  • 1 skrypt w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.

Skrypty: scripts/validate_export.py

Co robi i kiedy

Eksportuje dane treningowe z bieżącej rozmowy do pliku Markdown w formacie Obsidian, nazwanego datą rozmowy z danymi treningu.

Wyzwalacze z opisu

owdexport workoutobsidian workoutsave workout to obsidian
Oryginalny opis (EN)

Export workout data to an Obsidian-formatted Markdown file. Always trigger immediately when the user types "owd". Also trigger on "export workout", "obsidian workout", "save workout to obsidian", or related requests to export workout data into Obsidian. Read the current conversation first before searching prior conversation history. Name the file after the date of the chat that contains the workout data.

Jak działa

  1. Intent
  2. Use When
  3. Do Not Use When
  4. Validation Checklist
  5. Primary Trigger
  6. Workflow
  7. Rules
  8. Help And Examples
  9. Host Capabilities
  10. Capability Contract
Sekcje z nagłówków SKILL.md, w oryginale · 211 linii, 1 648 słów
Podgląd SKILL.md
---
name: obsidian-workout-export
description: Export workout data to an Obsidian-formatted Markdown file. Always trigger immediately when the user types "owd". Also trigger on "export workout", "obsidian workout", "save workout to obsidian", or related requests to export workout data into Obsidian. Read the current conversation first before searching prior conversation history. Name the file after the date of the chat that contains the workout data.
version: 1.1.0
---

# Obsidian Workout Export Skill

## Intent

Convert workout session data into clean Obsidian-ready Markdown logs with body stats, session details, PRs, and notes.

## Use When

- The user explicitly asks for `obsidian-workout-export`.
- The request matches the triggers or workflow described below.
- The task benefits from a reusable, structured output instead of a one-off answer.

## Do Not Use When

- Do not use for programming future training blocks, diagnosing injuries, or inventing workout details missing from the source.
- Required context is missing and cannot be reasonably inferred.
- A more specific skill in this repo is a better match.

## Validation Checklist

- [ ] The output matches the skill's intended task and platform.
- [ ] Required inputs, assumptions, and uncertainty are explicit.
- [ ] Safety, scope, and source limits are respected.
- [ ] The response follows the requested format or the skill's default output format.
- [ ] The result is practical enough to use without another cleanup pass.

Export logged workout sessions into Markdown files for an Obsidian `WorkoutData/` folder.

## Primary Trigger

Use this skill immediately when the user types `owd` in a chat that contains workout data.

Other triggers:

- `export workout`
- `obsidian workout`
- `save workout to obsidian`
- `workout to obsidian`
- `log to obsidian`

## Workflow

### 1. Locate the workout data

Always check the current conversation first. If the current chat already contains logged workout data such as exercises, sets, reps, weights, or body stats, use it directly instead of searching older history.

If the current chat does not contain workout data, search the most recent prior session using workout-related terms such as:

- `workout log sets reps`
- `leg press chest press fitness`
- `Day 1 Day 2 upper lower workout`

Use the date of the chat that contains the workout data as the filename date.

### 2. Extract all available session data

Pull every logged data point that is actually present.

**Session info**

- workout date
- day number and focus, for example `Day 2: Lower A`

**Exercises**

- exercise name
- weight
- sets
- reps
- PR flag when present

**Body stats**

- bodyweight in pounds
- body fat percentage

**PRs hit**

- each PR with weight and reps when available

**Session notes and flags**

- regressions
- injuries
- missed exercises
- anything else explicitly flagged in the session

### 3. Build the Markdown file

Use the filename `YYYY-MM-DD.md` based on the date of the chat containing the workout data.

Recommended structure:

```markdown
# Workout Log - [DAY NAME AND FOCUS]
**Date:** YYYY-MM-DD
**Program:** [program name, only if explicitly logged]

## Body Stats
| Metric | Value |
| --- | --- |
| Bodyweight | XXX lbs |
| Body Fat | XX.X% |

## Session - [Day X: Focus]

| Exercise | Weight | Sets | Reps | PR? |
| --- | --- | --- | --- | --- |
| Exercise Name | XXX lbs | X | X | yes or no |

## PRs Hit
- Exercise: XXX lbs / X reps

## Notes and Flags
- factual session notes, regressions, or flags
```

Omit sections with no data. Template program names are placeholders, not session facts; omit the Program line unless the source explicitly names a program. If there are no PRs, either omit the section or state `None this session`.

### Template variants

Match the template to the session type instead of forcing everything into the strength table:

- **Strength session**: the default structure above.
- **Ride**: replace the exercise table with distance, duration, average and max speed or power, elevation, and route name when logged.
- **Run**: distance, duration, pace, and surface or route when logged.
- **Combined day**: one section per activity in the order trained, sharing the same body stats block.

Keep column names consistent across files of the same type so Dataview queries work across the whole `WorkoutData/` folder.

### Frontmatter metadata

Add YAML frontmatter so notes are queryable:

```yaml
---
date: YYYY-MM-DD
type: strength | ride | run | combined
focus: [day focus, e.g. Lower A]
duration: [whole-session minutes, only if explicitly logged]
effort: [easy | moderate | hard, only if stated or clearly implied]
tags: [workout, plus activity tags like strength or cycling]
prs: [count, 0 if none]
---
```

Only include fields the log supports. Top-level duration always means the whole note's session duration. For a combined day, omit it unless the source explicitly supplies a whole-session total; do not copy one activity's duration or add an incomplete set of durations. Keep each known activity duration in its own section or clearly scoped activity field, such as ride_duration_minutes. Do not infer strength duration, rest time or a combined total. Add a one-line progression note at the end of the file when the session data shows a clear change from the last comparable session, and skip it otherwise.

### Duplicate protection

Before producing the file, check whether this session was already exported in the current conversation. If the same date and session were exported before:

- ask whether to overwrite or skip, unless the user explicitly asked for a re-export
- when re-exporting with corrections, produce one complete replacement file rather than a partial patch
- if two different sessions genuinely share a date, suffix the filename with the focus, such as `2026-06-10-lower-a.md`

### 4. Output expectations

Produce the Markdown content directly unless the user specifically asks for a file to be created in a local repo or folder. Build one canonical UTF-8 note whose first bytes are `---` followed by a newline, with no BOM, leading blank line, heading, prose or Markdown fence inside the note. The closing YAML delimiter precedes the Markdown body. Do not strip a failed delivered copy and report the original as valid.

When Python/file execution is available, validate the exact canonical note with [scripts/validate_export.py](scripts/validate_export.py) before delivery. Run `python scripts/validate_export.py note.md`. Only when the source explicitly logs a combined whole-session total may you include top-level duration and pass that source value with `--logged-total-minutes VALUE`; never pass a single activity duration as that total. This standard-library helper is read-only and checks the first-byte boundary, literal type/duration fields and combined-duration scope, not full YAML syntax or source truth. Parse the full YAML with an available YAML parser as a separate check; disclose if that parser is unavailable.

For chat-only delivery, start with a filename paragraph outside the note, then one fenced code block labelled `markdown`. The fence's first content line is the frontmatter delimiter `---`, with no empty line before it. Keep the entire canonical note in that block, not a rendered Markdown preview or an indented-code block. Keep filename, destination and validation commentary outside its content.

With permitted Python execution, run `python scripts/validate_export.py note.md --render-inline` and use its stdout as the complete fenced block without adding another wrapper or rebuilding its contents. The helper labels the block `markdown` and chooses a fence longer than every backtick run in the note, so embedded fences remain data. Pass an explicitly logged combined total with `--logged-total-minutes VALUE` when applicable. It refuses invalid canonical input or a missing terminal newline and never trims delivered content. Without execution, construct that same fenced block around the canonical note and disclose that validation did not run. On a correction, update and validate the canonical note, then serialize the complete replacement again.

A validated canonical file or wrapper does not prove that native Copy preserves its bytes. If readback is available, validate the exact code Copy without stripping spaces, blank lines or fences; otherwise say its Copy boundary is unverified. Never call a failed or unverified Copy an Obsidian-ready file. Respect a chat-only request. Attach the validated canonical file only when file delivery is requested or allowed; its bytes exclude all display wrappers. Report any native Copy failure separately; do not normalize it and count the original delivery as a pass.

When you finish, confirm:

- the filename
- the session date used
- that the file is intended for the Obsidian `WorkoutData/` folder

## Rules

- Never fabricate data. If a field was not logged, omit it or mark it as unlogged.
- If sets or reps are ambiguous, preserve exactly what was logged.
- If weight is missing for an exercise, note it as `bodyweight` or `unlogged` when appropriate.
- Keep the output factual. It is a data record, not a journal entry.
- Tables should stay Dataview-compatible for Obsidian use.

## Help And Examples

If the user is not sure how to use this skill, asks what it needs, or asks for examples:

- Explain in plain language what this skill can do.
- Tell the user the minimum input needed for a useful first pass.
- Show the example prompts below.
- Offer the fastest next prompt the user can send.

Minimum useful input:

- A workout log and the destination note style or vault context if relevant.

Example prompts:

- `Use obsidian-workout-export to turn this workout log into an Obsidian ready Markdown note.`
- `Export these strength and cycling notes into a clean workout entry for my Obsidian vault.`
- `Show me an example prompt for using this skill with a pasted workout session.`


## Host Capabilities

Use only tools, files, conversation history, and connected services actually available and authorized in the current host. If browsing, image/document inspection, code execution, persistent storage, or a related skill is unavailable, state the limitation and request the needed input or provide manual steps. Never claim a lookup, save, execution, publication, or installation occurred without evidence. Preserve the domain safety and confirmation rules above.

## Capability Contract

Read `capabilities.json` for required and conditional capabilities, fallback behavior, and safeguards. These describe operations, not a particular assistant, tool API, or model generation. Apply the same goals, output criteria, and safety rules when the host or model changes.
Pliki w paczce (8)
  • README.md 1 KB
  • SKILL.md 11 KB
  • build-provenance.json 1 KB
  • capabilities.json 1 KB
  • ecosystems.json 1 KB
  • instructions.md 12 KB
  • migration.json 6 KB
  • scripts/validate_export.py 3 KB

Wersje

RepozytoriumWynikLicencja
Ta strona · mickpletcher/AI-Skills100MIT
mickpletcher/AI-Skills100MIT
mickpletcher/AI-Skills100MIT

Identyczna treść występuje jeszcze w 1 innych folderach na GitHubie. Tu pokazujemy jedną, najlepiej ocenioną kopię.

Migawka bazy z 13.11.2026 · wersja paczki e735ab61d57c (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 100orangetheory-workout
    Wyszukuje podsumowania dziennych treningów Orangetheory Fitness na dziś lub jutro.
  • 96ios-workout-shortcut-builder-en
    Tworzy skrót dla iPhone, który zapisuje trening z menu i wysyła go do rutyny webhook.
  • 90workout-log-fallbacks-en
    Ustawia zapis i wprowadzanie treningów dla osób bez Notion, iPhone'a lub z Androidem.
  • 90obsidian-markdown
    Stosuje Obsidian Markdown jako ograniczony przepływ pracy agenta, z zachowaniem intencji użytkownika, prywatności i możliwości hosta.
  • 100oh-my-obsidian-session-save
    Zapisuje podsumowanie bieżącej sesji w vaulcie Obsidian, także automatycznie przez hook Stop.
  • 100obsidian
    Tworzy, eksportuje, zapisuje, dopisuje i otwiera notatki Markdown w Obsidianie przez natywne narzędzia obsidian_* oparte na oficjalnym CLI, unikając ryzykownych zapisów z bash.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.