claude

paper-forge

Generate final exams, class tests, practice sheets, and quizzes from course material (text, images, or PDFs)

0 on GitHubby Niki KothariMITupdated 3 months agoeducation
/

Plugin paper-forge from marketplace teaching-tools in nikikothari/teaching-tools. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (4)

  • class-test

    Generate a short graded class test on one or two recently taught topics, typically 20 marks in 30 minutes. Use when the user asks for a class test, unit test, weekly test, surprise test, chapter test, or a quick graded assessment on specific topics. Do not use for full syllabus final exams or ungrad

  • final-exam

    Generate a summative final examination paper covering a full syllabus, with sections, internal choice, and a marking scheme. Use when the user asks for a final exam, term-end paper, board-pattern paper, semester exam, annual exam, or a high-stakes graded paper from their course material. Do not use

  • practice-sheet

    Generate an ungraded practice sheet or worksheet with a difficulty ladder and an answer key. Use when the user asks for a practice sheet, worksheet, homework sheet, drill sheet, revision questions, or practice problems for students to work through. Do not use for graded exams or tests.

  • quick-quiz

    Generate a fast 5-minute recall quiz on a single concept, mostly multiple choice and true/false, for use at the start or end of a class. Use when the user asks for a quick quiz, warm-up questions, exit ticket, bell-ringer, oral quiz, or a handful of rapid recall questions. Do not use for graded test

Subagents (3)

  • blueprint-architect

    Designs the structural blueprint of any Paper Forge output — slots, marks, Bloom levels, topic weightage — before question text exists. Invoke after the topic map exists and the profile is loaded. Shared across all four paper skills.

  • item-writer

    Writes question text for blueprint slots, with answers and source anchors. Invoke once per question type, in parallel. Behaviour varies by item_writer_mode. Never invoke before a blueprint exists. Shared across all four paper skills.

  • paper-critic

    Reviews a generated item set for groundedness, ambiguity, duplication, difficulty mislabeling, distractor quality, and time budget. Returns a per-item verdict. Invoke after item-writer, before assembly. Strictness varies by profile. Shared across all four paper skills.

View source on GitHub

Similar plugins

explanatory-output-style

claude

Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)

hooks

anthropics/claude-code 155,476

code-modernization

claude

Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).

13 commands · 8 agents · hooks

anthropics/claude-plugins-official 47,076

performance-testing-review

claude

Performance analysis, test coverage review, and AI-powered code quality assessment

2 commands · 2 agents

wshobson/agents 42,461

memory-engineering

claude

Engineer an agent's forgetting, not just its remembering. Four deterministic stdlib scripts implement the four lenses of agent memory: a cost profiler that splits construction from query spend and reports cost per correct answer (construction energy exceeds total query energy across 300 queries in the Stanford characterization); an architecture picker that scores the four paradigm families — long-context, flat RAG, structure-augmented RAG, agentic — disqualifies on hard constraints, names the cost the winning choice makes you pay, and refuses to pick when the top two tie; a density auditor that classifies every record in a memory directory or JSONL export as FACT / SKILL / LOG / PROSE, finds near-duplicates, and flags stale wording; and a forgetting-policy linter that fails any design with no forgetting rule. Ships cs-memory-engineer agent, /cs-memory-engineering and /cs-forgetting-audit commands, 4 references, and a seven-question forcing worksheet.

1 skill · 2 commands · 1 agent

alirezarezvani/claude-skills 29,725

pascal-agent-skills

claudecodex

Create, inspect, validate, and assess furniture layouts with bounded next actions in Pascal through MCP.

3 skills · 2 MCP servers

pascalorg/editor 25,479

AI Governance Legal

claude

Triages proposed AI use cases against your registry, runs impact assessments across the regimes in scope, reviews vendor AI terms for training-on-data and liability gaps, and keeps your AI policy current with practice.

10 skills · 2 MCP servers

anthropics/claude-for-legal 9,991

Maintain paper-forge?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted