agentleFS
chellehonikerchellehoniker/claude-code-storytelleros/skills/time-tracking/SKILL.md

time-tracking

Skill1 starsChanged 12 days agoMITView on GitHub

Use when the user wants to start, stop, or review time spent writing. Triggers on "start a writing timer", "stop the timer", "how long did I spend on [project]", "log my pomodoro", "log a writing session", "my writing time this week".

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user doesn't specify a pen name + title, ask which they're tracking against (or default to their active one).

    line 23
  2. Very specific:

    If the user worked offline and wants to log retroactively, use stos_time_tracking_create({ fields: { start_time, end_time, notes } }) with …

    line 27
  3. Distinctive:

    If the user references pomodoro defaults:

    line 41
  4. Distinctive:

    Use this when the user says "set a goal of 1500 words/day" or "I'm aiming to finish by [date]".

    line 57
  5. Distinctive:

    Auto-stopping the user's timer: Don't stop a timer unless the user asked.

    line 61
  6. Distinctive:

    Starting a timer without scope: If you can't infer pen name + title, ask — otherwise the entry hangs unattributed.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Time Tracking

Two related concepts

ConceptWhat it isTools
Time-tracking entryA timed work block — start + stop, optional word counts. Also called a "writing session"; it's the same record either way.stos_time_tracking_*
Writing goalA target (words per day, hours per week, deadline)stos_writing_goals_*

Flow: start / stop a timer

stos_time_tracking_start({ penNameId, bookId: titleId, chapterId, note: 'Drafting' })
// later
stos_time_tracking_stop({ id })  // sets end_time = now

If the user doesn't specify a pen name + title, ask which they're tracking against (or default to their active one).

Flow: log a completed session

If the user worked offline and wants to log retroactively, use stos_time_tracking_create({ fields: { start_time, end_time, notes } }) with both times set (ISO timestamps).

Flow: review

For "how much time did I spend on [X]":

stos_time_tracking_list({ penNameId, limit: 'all' })

The list has no title filter, so narrow to the title yourself where the entries carry it. Sum the (end_time − start_time) differences and report. If the user wants a per-day breakdown, group locally.

Pomodoro settings

If the user references pomodoro defaults:

stos_pomodoro_settings_get()
stos_pomodoro_settings_update({ fields: { focus_minutes: 25, ... } })

Writing goals

Goal-tracking is a separate flow:

stos_writing_goals_list()
stos_writing_goals_create({ fields: { goal_name, goal_type: 'daily', target_words: 1500, start_date } })

Use this when the user says "set a goal of 1500 words/day" or "I'm aiming to finish by [date]".

Anti-patterns

  • Auto-stopping the user's timer. Don't stop a timer unless the user asked. They may have walked away and want the elapsed time counted.
  • Starting a timer without scope. If you can't infer pen name + title, ask — otherwise the entry hangs unattributed.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.