answer-processing

A grading workflow for handwritten or scanned answer PDFs. It converts the work into readable text, including mathematical notation when needed, then compares it with a reference solution.

In plain words
What is it for?
Use it when a student uploads handwritten work and wants it graded against prepared solutions or answer files.
Why use it?
It removes the manual work of transcribing scanned answers before grading. It also provides a repeatable way to assess submitted quiz or homework answers.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/optimeta/paideia/answer-processing
Any agent
npx skills add OPTIMETA/PAIDEIA --skill answer-processing
Clone the repo
git clone --depth 1 https://github.com/OPTIMETA/PAIDEIA

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,467 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00079 $0.02467
Opus 5 $0.00039 $0.01234
Sonnet 5 $0.00016 $0.00493
Haiku 4.5 $0.00008 $0.00247

Measured yesterday against content hash de8c5dd4f8d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

answer-processing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/paideia/skills/answer-processing/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Answer Processing

When to load

  • User uploads an answer PDF and asks to grade it
  • /grade is invoked
  • User says "I finished the quiz, here's my work"

Core pipeline

answers/<quiz-name>.pdf      ← user uploads hand-written scan
      ↓ (pdf skill, OCR)
answers/converted/<quiz-name>.md
      ↓ (this skill)
grade report → stdout (compact) + errors/log.md (append)

Step-by-step procedure

Step 1: Locate the answer file

If /grade was called with an argument, use it as a hint. Otherwise find the most recently modified file in answers/ (not answers/converted/).

Step 2: Convert PDF to MD (if PDF)

Use the vision-ocr skill — delegates to a local VLM (Qwen3-VL 8B via ollama) for clean prose + LaTeX transcription (the script reads INTERFACE_LANG from .course-meta so the VLM keeps the handwriting in its original language), with pytesseract as automatic fallback.

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/vision_ocr.py" answers/<name>.pdf answers/converted/<name>.md

The script handles model warmup, page-by-page inference, and tier fallback. See .claude/skills/vision-ocr/SKILL.md. The output header tells the grader which tier produced the text:

  • <!-- SOURCE: ..., qwen3-vl:8b @ 300dpi, N pages --> → high-confidence
  • <!-- TIER: tesseract fallback --> → degraded; treat results conservatively

Step 3: Graceful handling of OCR noise

Hand-written math OCR will be imperfect. Expect:

  • Greek letters misread as Latin ($\alpha \to a$, $\beta \to B$, $\pi \to T$ or $n$)
  • Fractions rendered as flattened text ($\tfrac{dU}{dT} \to dUdT$ or similar)
  • Subscripts/superscripts lost or inlined

Do not grade on algebraic correctness of OCR output. Instead, apply strategy-based grading:

Step 4: Strategy extraction from noisy MD

Read the converted MD file. For each problem, identify:

  1. Which pattern(s) did the user invoke? Look for:
    • Named theorems / techniques the user wrote out ("Maxwell relation", "Stokes theorem", "by induction")
    • Variables they held fixed (even if notation is mangled)
    • Key intermediate objects (a chosen potential, a change of variable, an ansatz)

Read the full file on GitHub · 205 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 205 lines · 79 tokens per session scan A de8c5dd4f8d6

Subscribe to this mod's changes

answer-processing is a skill published in the GitHub repository OPTIMETA/PAIDEIA (91 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 2,467 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

linza-operator

Use when operating LINZA MCP as a local-first agent workspace. Guides agents through doctor checks, guidenextsteps, agentworkspace actions, teach/grow review loops, dry-run apply gates, artifact safety, calibr trace review, and context export without exposing raw tool lists to users.

Semiotronika/LINZA-MCP · 61 tokens

strata:bootstrap

One-time onboarding pass to seed the Strata vault from an existing codebase's docs. Scans CLAUDE.md, docs/, .planning/, and similar for candidates, then dispatches each one to a strata:bootstrap-worker subagent in parallel batches, the worker reads its file, classifies, writes the right kind of vault note, and returns…

gideondk/strata · 109 tokens

strata:consolidate

Promote durable notes out of aging per-branch pr-context dirs into the branch-agnostic lessons/ scope (rule-based, no LLM). Use when the user says "clean up old branch notes", "graduate these to lessons", "tidy pr-context", or after a wave of merged PRs. Dry-run by default; --apply to perform. Command-only — run it…

gideondk/strata · 95 tokens

digital-eguide

A two-spread digital e-guide preview — page 1 is a cover (display title, author, "What's inside" stats, table of contents teaser); page 2 is a spread (lesson body with pull-quote and a step list). Lifestyle / creator brand tone. Use when the brief asks for an "e-guide", "digital guide", "lookbook", "lead magnet"…

nexu-io/open-design · 103 tokens

docs-page

A documentation page — inline-start nav, scrollable article body, inline-end table of contents. Use when the brief mentions "docs", "documentation", "guide", "API reference", or "tutorial".

nexu-io/open-design · 44 tokens

slidev

Create and present web-based slidedecks for developers using Slidev with Markdown, Vue components, code highlighting, animations, and interactive features. Use when building technical presentations, conference talks, code walkthroughs, teaching materials, or developer decks.

slidevjs/slidev · 51 tokens