agentleFS
kubilaiswfkubilaiswf/claude-tutor/.claude/skills/progress/SKILL.md

progress

Skill0 starsChanged 3 months agoMITView on GitHub

Show the learner's tutor dashboard — courses, mastery map, streak, due reviews, weak spots, and recommended next step. Use when the user asks how they're doing, where they left off, or for their learning progress/stats.

23 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use report.

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.
  • MicrosoftSkill

    report

    Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read-only view over the learner's state (formats in ../teach/references/state-format.md).

    line 8
  2. Very specific:

    Read ~/.claude/tutor/profile.json and every courses/*/ (resolve ~ to an absolute path yourself).

    line 14
  3. Very specific:

    Use the exact four status names from state-format.md (new, learning, learned, mastered).

    line 25

“Common” is measured: kept by at least 6 in 10 of the 16 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

Progress — Learner Dashboard

Read-only view over the learner's state (formats in ../teach/references/state-format.md). Present it in the learner's language. Change no files.

Because this skill writes nothing, it never touches the streak: opening a dashboard is not study activity. Report streak.days exactly as stored and leave last_study_date alone — the study day is recorded by teach, quiz, exam, and review under the idempotent-per-calendar-day rule in state-format.md.

Flow

  1. Read ~/.claude/tutor/profile.json and every courses/*/ (resolve ~ to an absolute path yourself). No state at all → explain the system in three lines and offer to start a course with the teach skill.
  2. Render, per course:
Music Theory — Harmony          Unit 3/6 · Lesson 2
   Mastery  ████████░░░░░░░  9 mastered · 5 learned · 6 learning · 12 new
   Quizzes  U1 85% · U2 92%      Midterm: pending (after U3)
   Reviews  7 due today · next batch Fri · 4 cards retired
   Weak     secondary dominants · cadence identification (2 open misconceptions)
  • Use the exact four status names from state-format.md (new, learning, learned, mastered). Never invent buckets and never fold learned into mastered — that would violate the honesty rules below.
  • The due count excludes retired cards. Count only cards with due ≤ today and retired not true, so this number matches what a review session would actually ask. Report retirements separately; they are the durable milestone and worth seeing.
  1. Global footer: streak (neutral framing), XP and level, and the calibration trend.
    • Calibration trend — show it once there are at least three assessments whose predicted is a number. predicted and score are both fractions from 0 to 1, so take the mean of score − predicted and state it in percentage points: "your predictions run about 10 points under your scores — you underestimate yourself."
    • Skip assessments with "predicted": null; they were refused, not missing. If fewer than three numeric predictions exist, say the trend isn't available yet, and if the nulls carry per-item "sure / not sure" summaries in their note, report that pattern instead ("on the items you marked sure, you were right 9 times out of 10").
  2. Progress evidence, not just numbers: one concrete then-versus-now line pulled from state history. "March 10: couldn't name the chord under a melody note → today: analyzing a modulation you'd never seen." Specific beats flattering.
  3. One recommended next action with a reason, chosen by priority: ≥ 5 non-retired cards due → the review skill · a finished unit with no quiz → the quiz skill · remediation pending → the teach skill for a re-teach · otherwise → the teach skill to continue. Name the skill and let the learner invoke it however they installed it (/review, /tutor:review, or just "review my cards"). Offer it; don't command it — the learner chooses.

Honesty rules

Report exactly what the state files say — no rounding up, no motivational inflation. If the streak broke, show the new count without commentary. If a unit looks stalled (no activity for two weeks or more), name it kindly and ask whether the plan still fits; a course that stopped being right is a plan problem, not a learner problem.

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.