// Use when the user wants to review what they've learned, see progress on their gaps, get a summary of recent learning sessions, or wants article ideas based on learnings. Triggers on: "learning report", "what have I learned", "progress report", "summarize my learning", or "learning summary for the last month".
Use when the user is done learning for the day, wants to save progress, or wants to wrap up a lesson. Also triggered by /learn when postponing or abandoning. Updates the learning intelligence layer (insights.md) after each session. Triggers on: "end session", "done learning", "save progress", "wrap up", "end-learn", "I'm done for today".
Use when the user wants to sit down and learn, continue a lesson, practice a skill, or work through a learning project. Triggers on: "let's learn", "continue my lesson", "start learning", "practice", "I have time to learn", or "pick up where I left off".
Internal-only skill — never called directly by users. Provides the Learning Intelligence Layer. Two modes: "build context" (called by /learn at session start) reads learning history and produces a learner context; "update insights" (called by /end-learn after session close) updates the persistent insights.md summary.
Use when the user wants a fast status check on their learning without a full report. Triggers on: "learning status", "where am I", "what's my learning state", "how's my learning going", or "check my progress".
Use when the user wants to find what to learn next, explore learning topics, get project ideas for a skill gap, or add a learning idea to their backlog. Triggers on: "what should I learn", "suggest learning projects", "I want to learn X", "add to my learning backlog", or "find me resources on X".
Use at the end of a Claude Code session to capture project-specific friction as proposed CLAUDE.md edits. Triggered by /debrief (no args) to scan the full session, or /debrief <hint> to focus on a specific area (e.g., /debrief the API naming convention thing). Returning "session looks clean" with no proposals is a first-class outcome, not a fallback. Triggers on: "/debrief", "debrief the session", "wrap up this session", "what did we learn", "any rules to capture", "should we update CLAUDE.md".
| name | learning-report |
| description | Use when the user wants to review what they've learned, see progress on their gaps, get a summary of recent learning sessions, or wants article ideas based on learnings. Triggers on: "learning report", "what have I learned", "progress report", "summarize my learning", or "learning summary for the last month". |
| license | MIT |
| version | 0.1.0 |
| metadata | {"author":"david","tags":"learning, report, progress, summary, review, growth, gaps, articles"} |
Aggregate learning logs, archived lessons, and profile data into a progress report over a given timeframe. Highlight growth, identify patterns, and suggest next steps.
Profile must exist at ~/.claude/learning/profile.md. At least one session log
should exist in ~/.claude/learning/logs/ for the report to be meaningful.
Accept an argument for the timeframe. Default: 2 weeks.
Supported formats:
2w — 2 weeks1m — 1 month3d — 3 days2wCalculate the start date from today minus the timeframe.
~/.claude/learning/profile.md — gaps for comparison~/.claude/learning/logs/ — all session logs within the timeframe~/.claude/learning/lessons/archive/ — lessons closed within the timeframe~/.claude/learning/lessons/current.md — active lesson (if any)~/.claude/learning/insights.md — learning intelligence data (may not exist)Structure the report with these sections:
Summary
duration_approx from logs)Topics Covered
Key Learnings
Recurring Struggles
Gap Progress
Patterns
Learning Intelligence (only if insights.md exists)
Suggested Next Steps
Example output:
# Learning Report — Mar 17 to Mar 31, 2026
## Summary
- **Sessions:** 6 sessions over 2 weeks
- **Time invested:** ~9 hours
- **Lessons:** 1 completed, 1 in progress
## Topics Covered
- React Dashboard (completed) — 4/4 milestones
- GraphQL API Design (in progress) — 1/3 milestones
## Key Learnings
**React:**
- Components are functions returning JSX; state drives re-renders
- useEffect cleanup prevents memory leaks on unmount
**GraphQL:**
- Schema-first design prevents client/server drift
## Recurring Struggles
- State management patterns (came up in 3 sessions)
- Async error handling (2 sessions)
## Gap Progress
- Frontend: addressed (React dashboard completed)
- Backend APIs: in progress (GraphQL)
- Infrastructure: untouched
## Learning Intelligence
- **Confirmed strengths:** LCEL chain composition, prompt templating
- **Recurring struggles:** async error handling (4 sessions), state management (3 sessions)
- **Difficulty progression:** backend APIs: intermediate → advanced, AI/orchestration: beginner → intermediate
## Suggested Next Steps
- Revisit state management — still fuzzy after multiple sessions
- Continue GraphQL lesson (1 milestone left this week)
- Consider starting an infrastructure topic next
Write to ~/.claude/learning/reports/YYYY-MM-DD-<period>.md
2026-03-31-2w.mdShow the full report to the user in the conversation. Mention where it was saved.