agentleFS
dymchenkkodymchenkko/claude-study-agent/.claude/skills/today/SKILL.md

today

Skill2 starsChanged 7 days agoMITView on GitHub

Start a daily ~15-minute study session - due reviews first, then the next topic with micro-tasks. Use when the user says "today", "let's study", "daily session" or opens without a specific request.

18 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use update and start.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AnthropicSkill

    update

    Sync tasks and refresh memory from your current activity. Use when pulling new assignments from your project tracker into TASKS.md, triaging stale or overdue tasks, filling memory gaps for unknown people or projects, or running a comprehensive scan to catch todos buried in chat and email.

    Also in 3 projects that use this

  • AnthropicSkill

    start

    Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 3 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run ~/Study/.tools/study plan --json (add the subject name if I gave one, and --minutes N if I gave minutes: N / 5 picks, at least 1, at …

    line 11
  2. Very specific:

    todo has picks: use the pick flow below.

    line 18
  3. Distinctive:

    A subject was named and has no picks today: run the classic flow below for that subject.

    line 19
  4. Very specific:

    Read that pick's subject files: CLAUDE.md, progress.md, mistakes.md, the latest file in sessions/.

    line 27
  5. Very specific:

    If it has a Diagrams entry, diagram tasks follow the Diagrams rules in ~/Study/CLAUDE.md.

    line 28
  6. Distinctive:

    Do the pick (~5 min), following the teaching rules:

    line 29
  7. Very specific:

    Read the subject's CLAUDE.md, progress.md, mistakes.md and the latest file in sessions/.

    line 43
  8. Distinctive:

    If its reviews are paused, skip the warm-up.

    line 44
  9. Very specific:

    Update progress.md, mistakes.md, write sessions/<today>.md (append if it exists) and run study log.

    line 50
  10. Very specific:

    If syllabus.md has no topics yet, tell me to run /ingest <subject> first (or offer to run it).

    line 53

“Common” is measured: kept by at least 6 in 10 of the 15 edited versions of this file we could read. “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

Daily session (default 15 min = 3 picks of ~5 min)

Today's plan is shared with the Plan tab of study gui, so both always show the same picks.

  1. Run ~/Study/.tools/study plan --json (add the subject name if I gave one, and --minutes N if I gave minutes: N / 5 picks, at least 1, at most 3). todo is the list of unfinished picks for this session, paused lists subjects whose reviews are paused.
  2. Decide the flow:
    • A paused subject named in the argument: say its reviews are paused and ask whether to resume (replace its - **Reviews:** line with - **Reviews:** resumed <today>). Don't start until I confirm; if I say no, offer the picks of other subjects instead.
    • todo has picks: use the pick flow below.
    • A subject was named and has no picks today: run the classic flow below for that subject.
    • No picks left (all done, or the plan is empty): say so in one line. Offer the classic flow for the non-paused subject with the most overdue topics. If every subject is paused, say that and offer to resume one.
  3. Show the plan in 3 lines max, one per pick: 1. PRI · Association class — 2 open mistakes (review).

Pick flow (one pick at a time, in order, across subjects)

For each pick:

  1. Read that pick's subject files: CLAUDE.md, progress.md, mistakes.md, the latest file in sessions/. If it has a Diagrams entry, diagram tasks follow the Diagrams rules in ~/Study/CLAUDE.md.
  2. Do the pick (~5 min), following the teaching rules:
    • review: up to 3 short recall questions on that topic only, unfixed mistakes first (as in /review).
    • lesson: start the topic as in /learn, small: one idea, one micro-task, grade, adapt.
    • drawing: one drawing task on that topic in draw.io (the chat answers were right, the diagram slipped).
  3. Save right away, before moving on: progress.md, mistakes.md, append to sessions/<today>.md of that pick's subject, and study log (Event log rule in ~/Study/CLAUDE.md). A pick counts as done when its topic's Last studied is today, so stopping early loses nothing.

Finish (≈2 min, once at the end): one exam-style question on the finished pick where I scored best. Log it like the rest (it is a recall on that topic). End with: what improved, what's due tomorrow, and a one-line suggestion for next time.

Classic flow (one subject, no picks)

  1. Read the subject's CLAUDE.md, progress.md, mistakes.md and the latest file in sessions/. If its reviews are paused, skip the warm-up.
  2. Plan in 3 lines max, e.g. Warm-up: 3 reviews · Main: <topic> · Finish: 1 exam-style question.
  3. Warm-up (≈3 min): up to 3 due items (Next review ≤ today), unfixed mistakes first. One question at a time.
  4. Main (≈10 min): continue the topic from the last session log, or the next unstarted topic in syllabus.md. Follow the teaching rules in ~/Study/CLAUDE.md: explain small → micro-task → grade → adapt.
  5. Finish (≈2 min): one exam-style question on today's main topic.
  6. Update progress.md, mistakes.md, write sessions/<today>.md (append if it exists) and run study log. End with: what improved, what's due tomorrow, and a one-line suggestion for next time.

If syllabus.md has no topics yet, tell me to run /ingest <subject> first (or offer to run it).

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.