agentleFS
yarikletoyarikleto/claude-teacher-plugin/skills/progress/SKILL.md

progress

Skill9 starsChanged 2 months agoMITView on GitHub

Use when the student wants to see their knowledge dashboard — shows what they know, what's weak, what's due for review, misconceptions, and overall stats across all projects

22 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use quiz, teach and 1 more.

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.
  • andrewn6Skill

    quiz

    Test understanding with targeted questions — adapts to skill level and researches the stack for relevant questions

    Also in 4 projects that use this

  • GoogleSkill

    teach

    Teach the user a new skill or concept, within this workspace.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 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.

  • 3

    Very specific

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

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

    Before accessing education data, read ${CLAUDE_PLUGIN_ROOT}/references/education-data.md.

    line 7
  2. Very specific:

    Read <education-db>/student.json for goals/deadlines

    line 16
  3. Very specific:

    If dashboard doesn't exist, say: "No progress tracked yet.

    line 17
  4. Distinctive:

    If all topics are Solid with no due reviews: congratulate and suggest exploring advanced subtopics or increasing depth

    line 89

“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

Before accessing education data, read ${CLAUDE_PLUGIN_ROOT}/references/education-data.md. Resolve every <education-db> below using that contract. Current session ID: ${CLAUDE_SESSION_ID}.

Progress Dashboard

Shows a visual overview of the student's knowledge state from the global education DB.

Process

  1. Read <education-db>/dashboard.json
  2. Read <education-db>/student.json for goals/deadlines
  3. If dashboard doesn't exist, say: "No progress tracked yet. Run /claude-teacher:init-edu first."
  4. For topics with unresolved misconceptions, read individual topics/<slug>.json files
  5. Render the dashboard

Dashboard Format

══════════════════════════════════════════════════
  KNOWLEDGE DASHBOARD
══════════════════════════════════════════════════

  Overall: N topics tracked · M quizzes taken · avg score: X%

  Solid (N)          ████████████░░░░░░░░  60%   depth: ██ working
  Learned (N)        █████░░░░░░░░░░░░░░░  25%   depth: █░ surface
  Weak (N)           ██░░░░░░░░░░░░░░░░░░  10%

──────────────────────────────────────────────────
  🔴 DUE FOR REVIEW (next_review <= today)
──────────────────────────────────────────────────
  · tcp-basics — was solid, due since 2026-03-18
  · recursion — learned, due since 2026-03-17

──────────────────────────────────────────────────
  WEAK — address these first
──────────────────────────────────────────────────
  ✗ tcp-congestion — last score: 40% (2026-03-15)
    ⚠ Misconception: "confused slow start with congestion avoidance"
  ✗ udp — never quizzed, marked weak in session

──────────────────────────────────────────────────
  LEARNED — needs more practice
──────────────────────────────────────────────────
  ~ docker-networking (working) — next review: 2026-03-22
  ~ osi-model (surface) — next review: 2026-03-20

──────────────────────────────────────────────────
  SOLID — proven understanding
──────────────────────────────────────────────────
  ✓ tcp-basics (deep) — last reviewed: 2026-03-16
  ✓ socket-api (working) — last reviewed: 2026-03-14

──────────────────────────────────────────────────
  UNRESOLVED MISCONCEPTIONS (N total)
──────────────────────────────────────────────────
  · tcp-congestion: "confused slow start with congestion avoidance" (2026-03-15)
  · udp: "thought UDP has flow control" (2026-03-14)

──────────────────────────────────────────────────
  GOALS
──────────────────────────────────────────────────
  · Pass OS exam — deadline: 2026-06-15 (88 days away)
    Progress: 3/10 topics solid

══════════════════════════════════════════════════
  Suggestion: 2 topics are due for review. Start
  with /claude-teacher:quiz-me tcp-basics, then address the
  misconception in tcp-congestion.
══════════════════════════════════════════════════

Rules

  • Show planned new topics separately. Calculate mastery percentages over studied topics only; use 0% when none have been studied. Do not divide by zero for an empty DB
  • Progress bar: 20 characters wide, █ for filled, ░ for empty
  • Show depth level next to status categories; treat solid as a status, never a depth
  • Due for review section appears at the TOP if studied topics have a valid, non-null next_review <= today — this is the most actionable info
  • Misconceptions section — show all unresolved misconceptions across all topics. Read individual topic files to get these.
  • Goals section — show goals from student.json with days remaining and estimated progress
  • Sort weak topics by last score (lowest first — most urgent)
  • Sort learned topics by next review date (soonest first)
  • End with a concrete, actionable suggestion
  • If all topics are Solid with no due reviews: congratulate and suggest exploring advanced subtopics or increasing depth

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.