Stats
Actions
Available In
Tags
Plugin
agentic-study-environment
A Claude Code learning harness: structured tutor sessions over your own source materials, in any domain.
What's Inside
Skills5
adjust-level
/adjust-level
Adjust the difficulty level of a learning sub-project's curriculum — simplify a too-advanced curriculum into a gentler on-ramp, or deepen a too-introductory one into something with real teeth. Use whenever the user signals the curriculum's level doesn't match their starting point — phrases like "this paper is too hard, can we build up to it?", "simplify the curriculum", "make it easier", "go more advanced", "I want a more rigorous version", "this is too basic, push deeper", "I need an intro version of this", or "create a simpler/harder curriculum from this material". The skill is allowed to pull in external materials and training knowledge to fill the gap between the source's natural level and the target level, but every external addition is explicitly labeled — the user always knows what came from their own source materials and what came from elsewhere.
bootstrap
/bootstrap
Scaffold a new learning sub-project under the agentic-study-environment harness — create the directory, generate per-project CLAUDE.md and PROGRESS.md from templates, and register the new project in the root PROGRESS.md. Use this skill whenever the user wants to start studying a new topic, paper, book, language, or domain with the tutor harness — phrases like "bootstrap a new project to learn X", "start a new sub-project for Y", "set up a learning project on Z", or "create a sub-project to study W" should all trigger this skill. Do not use for general project scaffolding outside the agentic-study-environment harness.
set-curriculum
/set-curriculum
Build or update the teaching curriculum for a learning sub-project from its source materials. Use whenever the user wants to plan, structure, or refresh the learning path for a sub-project — phrases like "set curriculum for X", "update the curriculum", "plan the teaching path", "build a curriculum from these materials", or general intent to organize source material into an ordered teaching plan. This skill reads the sub-project's source materials and writes ai-agent-materials/curriculum.md. It does not start a session and does not update PROGRESS.md.
start-session
/start-session
Begin a bracketed learning session inside a agentic-study-environment sub-project — pick a topic, propose theory vs. practice (or simulation, for speech-therapy), and conduct it per the sub-project's domain overlay. Use whenever the user signals they want to actively study, work an exercise, role-play a clinical case, or review theory inside a sub-project — phrases like "start session", "let's work on X", "begin a practice session", "ok let's study Y", or "I want to do an exercise on Z" should trigger this skill. A session is the harness's unit of work and ends with the stop-session skill.
stop-session
/stop-session
End the current learning session — update the sub-project's PROGRESS.md (topics + journal), mirror status changes into the root PROGRESS.md, and produce a concise summary of what was covered. Use whenever the user signals the session is over — phrases like "stop session", "let's wrap up", "end session", "we're done for today", or any out-of-character debrief signal (for speech-therapy simulations — "debrief", "end simulation"). Do not invoke this skill proactively at the end of a long conversation unless the user signals it.
Stats
Version0.1.0
Stars1
MaintenanceGood
LicenseMIT
Last Commit
Added
Available In
Tags
Categories
