summary
Skill9 starsChanged 2 months agoMITView on GitHub
Use when the student is ending a learning session — generates a recap of what was covered, updates knowledge tracking in the global DB, and suggests what to start with next time
11 other projects use a version of this.
Adopted by
Most recently taken up by
- geneontology/go-skillstheir own version, first seen Nov 1, 2026
- saksham10arora-dotcom/everything-claude-codextheir own version, first seen Nov 1, 2026
- robo311/devflowtheir own version, first seen Oct 20, 2026
- Dev-PGVAA/skillstheir own version, first seen Oct 16, 2026
- finos/git-proxytheir own version, first seen Oct 9, 2026
- isas1/skillstheir own version, first seen Sep 21, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- finos/git-proxy★ 263same name
- isas1/skills★ 210same name
- saksham10arora-dotcom/everything-claude-codex★ 74same name
- geneontology/go-skills★ 1same name
- robo311/devflow★ 1same name
- timsvoice/skills★ 1same name
- Dev-PGVAA/skills★ 0same name
- kys42/claude-skills★ 0same name
- postproxy/postproxy-claude-plugin★ 0same name
- TechHU-GS/cc-discipline★ 0same name
1 more not listed
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.
- .claude/CLAUDE.mdCLAUDE.md
- asciiSkill
- challengeSkill
- compareSkill
- demoSkill
- excalidrawSkill
- flashcardsSkill
- init-eduSkill
- motivateSkill
- progressSkill
- quiz-meSkill
- researchSkill
- reset-eduSkill
- roadmapSkill
- save-progressSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 3 are distinctive, and 10 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
Before accessing education data, read ${CLAUDE_PLUGIN_ROOT}/references/education-data.md.
- Very specific: line 20
Read <education-db>/dashboard.json for current state
- Very specific: line 21
Read relevant <education-db>/topics/*.json for topics covered this session
- Very specific: line 22
Read <education-db>/student.json for goals
- Distinctive: line 24
Update ALL DB files with session results
- Very specific: line 25
Update project-local memory/knowledge_gaps.md if it exists
- Distinctive: line 90
Create the file if it doesn't exist
- Very specific: line 91
Update status based on session performance
- Very specific: line 92
Update depth if student demonstrated deeper understanding
- Distinctive: line 94
Add any new misconceptions discovered
- Very specific: line 100
Update last_session to today
- Very specific: line 103
Update all topic entries with current status/depth/next_review
- Very specific: line 122
If you learned new things about the student during this session (e.g., they mentioned a new goal, showed a preference for a different …
“Common” is measured: kept by at least 6 in 10 of the 9 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.
Files
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}.
Session Summary
Generates an end-of-session recap and persists all progress to the global education DB.
Invocation
/claude-teacher:summary — run at the end of a learning session
Process
- Review the current conversation — what topics were discussed, quizzed, challenged?
- Read
<education-db>/dashboard.jsonfor current state - Read relevant
<education-db>/topics/*.jsonfor topics covered this session - Read
<education-db>/student.jsonfor goals - Generate the summary
- Update ALL DB files with session results
- Update project-local
memory/knowledge_gaps.mdif it exists
Summary Format
══════════════════════════════════════════════════
SESSION SUMMARY — [date]
══════════════════════════════════════════════════
Duration: [from recorded timestamps, or omit if unknown]
Project: [current directory]
LEARNED TODAY
─────────────
✓ [topic 1] — [one-line what was covered]
✓ [topic 2] — [one-line what was covered]
~ [topic 3] — [started but not finished]
QUIZ RESULTS
─────────────
· [topic]: 8/10 (80%) — promoted to solid!
· [topic]: 5/10 (50%) — stays at learned, review scheduled
DEPTH CHANGES
─────────────
↑ [topic]: surface → working (used correctly in challenge)
↑ [topic]: working → deep (explained reasoning correctly)
MISCONCEPTIONS
─────────────
⚠ [topic]: "[what they said wrong]" — [addressed/still open]
✓ [topic]: "[old misconception]" — resolved this session!
KNOWLEDGE CHANGES
─────────────
↑ [topic] moved from Weak → Learned
↑ [topic] moved from Learned → Solid
↓ [topic] — struggled, stays in Weak
GOAL PROGRESS
─────────────
· Pass OS exam (2026-06-15): 5/10 topics solid (+2 today)
SPACED REPETITION SCHEDULE
─────────────
Tomorrow: [topic] (review due)
In 2 days: [topic]
In 4 days: [topic]
NEXT SESSION
─────────────
Start with:
1. Review: [topics due for spaced repetition]
2. Resolve: [unresolved misconception to address]
3. Continue: [where we left off]
4. Next new topic: [what comes next]
══════════════════════════════════════════════════DB Updates
1. Update/create topic files (<education-db>/topics/<slug>.json)
For each topic covered this session:
- Create the file if it doesn't exist
- Update
statusbased on session performance - Update
depthif student demonstrated deeper understanding - Preserve assessment dates and intervals unless a new completed assessment has not yet been saved; apply each assessment once using the shared contract
- Add any new misconceptions discovered
- Mark any resolved misconceptions as
resolved: true - Add session notes
2. Update dashboard (<education-db>/dashboard.json)
- Update
last_sessionto today - Update
current_topic - Recalculate
stats(weak/learned/solid counts) - Update all topic entries with current status/depth/next_review
3. Finalize session log (<education-db>/sessions/[date].jsonl)
Append closing entry:
{"time": "[now]", "event": "session_end", "project": "[cwd]", "topics_covered": ["..."], "quizzes_taken": N, "misconceptions_found": N, "misconceptions_resolved": N, "summary": "one-line summary"}4. Update project-local tracking
Update memory/knowledge_gaps.md:
- Topics explained → Learned (if new)
- Topics answered correctly in quiz → promote toward Solid
- Topics answered incorrectly → Weak
- Note dates for spaced repetition
5. Update student profile if needed
If you learned new things about the student during this session (e.g., they mentioned a new goal, showed a preference for a different explanation style), update <education-db>/student.json.
Rules
- Be honest about what was understood vs what needs more work
- Track mistake patterns, not just topics (e.g., "keeps forgetting to close file descriptors")
- The "Next Session" section is critical — it's the first thing to check next time
- Include spaced repetition schedule so the student knows what's coming
- Show goal progress to maintain motivation
- Save everything to DB — this is the primary save point for the session
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
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.

