Skip to content
Skills Library
Education · Automation

learning-memory

/learning-memory

Use when capturing or restoring a learner's persistent profile to personalize teaching across sessions.

Licence
MIT
Last repository change
19.05.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
3
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 19.05.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use when capturing or restoring a learner's persistent profile to personalize teaching across sessions.

Original author description

Use when capturing or restoring a learner's persistent profile to personalize teaching across sessions.

How it works

  1. Session Start (Restore)
  2. Session End (Save)
Original SKILL.md headings · 62 lines, 432 words
SKILL.md preview
---
name: learning-memory
description: Use when capturing or restoring a learner's persistent profile to personalize teaching across sessions.
version: 1.1.0
authors:
  - edu-agent-skills contributors
tags: [memory, personalization, cross-session, learner-profile]
status: stable
---

# Purpose

Maintain a structured learner profile across sessions so agents start at the right depth, avoid re-teaching covered material, and prioritize known weak areas.

# Activation

- New session begins and prior context may exist. Learner references prior sessions or covered topics. Session ends and state should be preserved. Agent needs to personalize without re-asking onboarding questions.
- **Skip if**: one-off session with no continuity desired, no persistent storage available, or narrow stateless task.
- **Routing**: run at session start (restore) and end (save). Feed weak areas to `weak-area-tracker`. Profile drives `find-your-level` for returning learners with uncertain level.

# Inputs

- Prior session summary/profile, current session transcript, concepts + outcomes, learner self-reports, error patterns from assessment skills.

# Profile Schema (compact)

```yaml
learner_profile:
  level: beginner | intermediate | advanced
  stated_goal: "<goal>"
  learning_style: code-first | concept-first | mixed
  weak_areas: [{topic, type, last_seen, correction_attempted}]
  covered_topics: [{topic, confidence: low|medium|high, last_confirmed}]
  active_checkpoint: "<last concept/milestone in progress>"
  session_count: N
  last_session: "<ISO date>"
```

# Workflow

## Session Start (Restore)
1. **Retrieve** — Check for prior profile. If exists: summarize and confirm accuracy with learner. If none: run `find-your-level`.
2. **Staleness Check** — Last session 2+ weeks ago → flag for light review. Goal changed → update target.
3. **Inject** — Feed relevant profile data (level, weak areas, last checkpoint) into current session. Don't re-explain confirmed material unless requested.

## Session End (Save)
4. **Extract** — Record: concepts covered, understanding outcomes, new weak areas, self-reported confidence.
5. **Update** — Merge into profile. Promote "in-progress" → "covered" when confirmed. Add new weak areas.
6. **Handoff** — Output compact summary: where to resume, what to skip, top 1–2 priorities for next session.

# Rules

- DO: confirm profile accuracy with learner at session start — never assume stale data is current.
- DO: base profile updates on observable evidence, not assumptions.
- DO: cap weak-area list at 5 active items.
- DO: frame all profile data as "what we'll focus on" not "what went wrong."
- DON'T: re-teach confirmed topics without request or regression evidence.
- DON'T: skip the session-end save — always output the handoff note.
- DON'T: treat "covered" as "fully mastered" — watch for regression signals.

# Output

Session start: restored profile summary + confirmation prompt. Session end: concepts covered with outcomes, new/resolved weak areas, and handoff note (resume point + priorities + skip list). Format naturally.

# Checklist

- [ ] Profile confirmed with learner at session start.
- [ ] Staleness check performed if 2+ week gap.
- [ ] Session outcomes logged with evidence.
- [ ] Handoff note produced at session end.
Files in this package (3)
  • README.md 1 KB
  • SKILL.md 3 KB
  • examples.md 2 KB

Versions

The database has no other skills named learning-memory.

Database snapshot: 13.11.2026 · package version b4ac7cde5cd4 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100fin-guru-learner-profile
    Build or update the owner's learner profile for teaching and onboarding, covering literacy level, learning preferences, risk tolerance, goals, time limits, and ADHD-friendly pacing. Use when the owner starts learning sessions, asks to be taught a concept from scratch, or wants…
  • 90learn-profile
    Interview the learner and write .alvar/LEARNER.md so one teacher can fit one mind — pace, voice, solid ground, and how they want to struggle. Use when the user runs /learn-profile or /skill:learn-profile, or says how I learn, learning philosophy, teaching style, set up tutoring,…
  • 90build-with-me
    Use when guiding a learner through real project implementation while preserving their ownership and teaching through the build process.
  • 100learning-workspace
    Use when a human wants a persistent learning workspace across sessions, resumes lessons from recorded evidence, reports practice or a misconception to revisit, or changes an ongoing learning mission. Not for a one-off repository explanation, teaching the agent a convention, or…
  • 95learner-orchestrator
    Use when a learner wants a guided study session and needs help choosing among learning plans, Socratic tutoring, teach-back, retrieval practice, analogies, or critical review; route to one available learning skill at a time.
  • 90learning-tutor
    Teach a field, concept, or paper through one-question-at-a-time dialogue, Feynman explanations, and evidence-based assessment; query or resume persistent learning records across sessions. Use for 开始学习, 带我学, 学过没有, 学习进度, 继续学习, or 重新学 with learning intent. Includes learning-session…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.