- Home
- Skills
- Productivity
- claude study agent
claude study agent
A complete study orchestration system with material ingestion, adaptive tutoring, and automated spaced-repetition.
Free
Works with the AI Agents you already use
claude study agent
Example session with this skill installed
Run a 15-minute daily session for my Biology course. Focus on what is due for review first.
- Read your context and instructions
- Compiled the claude study agent
I have reviewed your Biology progress and current mistake log. You have 2 overdue reviews from last week and several unstarted topics in the photosynthesis module.
Plan for today
- Warm-up: 2 reviews on ATP Synthase mistakes.
- Main: Introduction to the Calvin Cycle.
- Finish: 1 exam-style calculation on carbon fixation.
Daily Study Session: Biology
Warm-up: Active Recall
- You previously struggled with the role of H+ gradients. In the context of the electron transport chain, why is the pH lower in the thylakoid lumen than in the stroma?
Your answer: Because protons are pumped there.
Result: ✅ Correct. Specifically, the accumulation of H+ ions creates the electrochemical gradient used by ATP synthase (Source: Lecture 4, Slide 12).
Main: The Calvin Cycle (Roadmap)
- Phase 1: Carbon Fixation
- Phase 2: Reduction
- Phase 3: Regeneration of RuBP
Concept 1: Carbon Fixation
The enzyme RuBisCO catalyzes the attachment of CO2 to the 5-carbon sugar RuBP. This forms an unstable 6-carbon intermediate that immediately splits into two 3-carbon molecules of 3-PGA (Source: textbook_ch10.pdf, p.194).
Micro-task: If 3 molecules of CO2 enter the cycle, how many molecules of 3-PGA are produced before the reduction phase?
Your answer: 6.
Result: ✅ Correct.
Finish: Exam-Style Question
Explain why the Calvin Cycle is often referred to as the "light-independent" reactions, and identify one reason why it cannot actually function in the dark for long periods.
Your answer: It doesn't need light directly but needs the ATP and NADPH produced by light reactions.
Result: ✅ Ready. Topic "Calvin Cycle" promoted to Level 3.
Next steps
- Review the "Reduction" phase tomorrow.
- 4 topics are due for review in 48 hours.
- Run
/status Biologyto see your updated readiness score.
Connects securely to your tools. The creator never sees your data.
About this skill
Managing heavy course loads across multiple subjects requires more than just reading notes. This suite of eight skills transforms raw lecture materials into a structured, searchable study system with automated spaced-repetition and exam simulation.
What it does
- Automated Ingestion processes slides, PDFs, and video URLs into searchable text while building a comprehensive syllabus map.
- Adaptive Tutoring breaks topics into micro-tasks, diagnosing existing knowledge and adjusting difficulty based on performance.
- Spaced Repetition manages a review queue based on mastery levels, prioritizing past mistakes and overdue topics to ensure retention.
- Exam Simulation generates realistic mock exams based on weighted syllabus topics and provides readiness reports with targeted revision plans.
- Progress Tracking maintains a dashboard of exam countdowns, average topic levels, and unfixed misconceptions across all subjects.
How it works
- Initialize the environment using the
setupcommand to configure hardware-optimized semantic search and local transcription tools. - Import materials with
ingestto populate the syllabus, extract formulas, and generate OCR text from scanned documents. - Execute daily sessions using
todayorlearnto work through the syllabus via active recall and micro-tasks. - Evaluate readiness through
quizorexamto generate performance analytics and update the mistake log.
Frameworks & tools
The system utilizes a local CLI toolset for semantic search and indexing. It supports local video transcription via Whisper and OCR for document processing. Data is persisted in Markdown files (progress.md, mistakes.md, syllabus.md) for transparent tracking.
Why this beats prompting it yourself
Manual prompting lacks the persistence needed for spaced-repetition and long-term progress tracking. This skill automates the feedback loop between mistakes and future study sessions, ensuring that every quiz question is grounded in your specific course materials rather than generic LLM knowledge.
Use cases
- Converting a semester's worth of messy PDF slides and YouTube lectures into an organized study plan.
- Running a 15-minute daily maintenance session to clear overdue spaced-repetition reviews.
- Generating a self-grading HTML practice quiz to test mastery of a specific complex topic.
- Conducting a timed mock exam to identify high-weight syllabus areas that need urgent revision.
Known limitations
Semantic search requires initial indexing which may take time on older hardware. Handwriting recognition quality depends on the clarity of the original scans.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Productivity.
Requires local CLI tools for indexing. Video transcription and OCR speeds vary by hardware. Meaning-based search may be limited if running in 'off' mode on low-resource systems.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 25 days ago
- Free with an Agensi account
- Accounts
GitHub
Hugging Face
- Software
Python
Git
Permissions
Allowed Hosts