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

save-progress

Skill9 starsChanged 2 months agoMITView on GitHub

Save new learning evidence after explanations or assessments, or when the student says "save this". Preserve existing records and avoid duplicate events without ending the lesson. Does not require a hook reminder.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. charlie947/save-progress★ 13same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository15 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    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. Distinctive:

    Read and merge each topic touched this session using the shared contract.

    line 32
  3. Very specific:

    Update last_session and current_topic

    line 61
  4. Very specific:

    Add entries to <education-db>/sessions/[date].jsonl for any events not yet logged:

    line 65
  5. Very specific:

    If you learned anything new about the student (preferences, background, goals), update <education-db>/student.json.

    line 73
  6. Distinctive:

    Don't end the session — just save and continue

    line 95
  7. Distinctive:

    If there's nothing new to save, say so: "Everything is already saved — nothing new since last checkpoint."

    line 96
  8. Distinctive:

    Keep the confirmation brief — the student wants to keep learning, not read a report

    line 97

≈ “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

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}.

Save Progress

Mid-session checkpoint that persists everything learned so far to the global education DB. Unlike /claude-teacher:summary (which ends the session), this saves state and keeps going.

Invocation

/claude-teacher:save-progress — save everything from the current session so far

Process

1. Analyze Current Session

Review the conversation so far and identify:

  • New topics explained (not yet in DB)
  • Quiz results (not yet saved)
  • Challenge results (not yet saved)
  • New misconceptions discovered
  • Misconceptions resolved
  • Depth changes observed
  • Any new info about the student's preferences

2. Update Topic Files

Read and merge each topic touched this session using the shared contract. This is an example for a newly taught topic, not a replacement for an existing record. Preserve assessment dates and intervals on repeated saves. Create or update <education-db>/topics/<slug>.json:

{
  "name": "Topic Name",
  "slug": "topic-name",
  "status": "weak|learned|solid",
  "depth": "surface|working|deep",
  "first_seen": "[date first encountered]",
  "last_reviewed": null,
  "next_review": "[first review or existing date]",
  "review_interval_days": 1,
  "quiz_scores": [],
  "misconceptions": [],
  "prerequisites": [],
  "related_topics": [],
  "notes": ""
}

3. Save Any Unsaved Quiz Records

For each quiz taken this session that hasn't been saved yet, write to <education-db>/quizzes/[date]_[topic-slug]_[quiz-id].json.

4. Update Dashboard

Update <education-db>/dashboard.json:

  • Refresh all topic statuses
  • Recalculate stats
  • Update last_session and current_topic

5. Append to Session Log

Add entries to <education-db>/sessions/[date].jsonl for any events not yet logged:

{"time": "[now]", "event": "checkpoint", "topics_saved": ["..."], "note": "mid-session save"}

6. Update Student Profile

If you learned anything new about the student (preferences, background, goals), update <education-db>/student.json.

7. Update Project-Local Tracking

Sync memory/knowledge_gaps.md with the current state if it exists.

8. Confirm

── Progress Saved ────────────────────────
  Topics updated: [list]
  Quizzes saved: [count]
  Misconceptions recorded: [count]
  Dashboard synced: ✓

  Keep going! Your progress is safe.
──────────────────────────────────────────

Rules

  • This is a NON-DESTRUCTIVE operation — it only adds/updates, never deletes
  • Don't end the session — just save and continue
  • If there's nothing new to save, say so: "Everything is already saved — nothing new since last checkpoint."
  • Keep the confirmation brief — the student wants to keep learning, not read a report

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.