Yotta School Doc — AI skill for Claude Code
Local, deterministic school-document skeleton and validation skill for AI agents: versioned rule packs + structured facts -> reproducible skeletons with checks for missing fields, dates, attachments.
How to install Yotta School Doc
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open YottaMeta/yotta-school-doc and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Yotta School Doc does
Local, deterministic school-document skeleton and validation skill for AI agents: versioned rule packs + structured facts -> reproducible skeletons with checks for missing fields, dates, attachments, placeholders, student data exposure, overclaims and meeting action items. Zero-dependency, no network, no fabricated facts.
Alternatives in AI
- Internal Safety Collapse — We built an adversarial codespace setup 1.2k ★
- STS2 AI Agent — https://github.com/user-attachments/assets/89353468-a299-4315-9516-e520bcbfbd4b English README: README.md STS2 191 ★
- Mnem — Git for AI Agent Knowledge 144 ★
README
Language: English · 中文
yotta-school-doc · 元公 (YuanGong)
YottaMeta's deterministic drafting-skeleton and validation skill for school documents: turn a versioned document-type rule pack and a structured facts file into a reproducible skeleton, then check an existing draft for missing fields, date issues, attachment mismatches, placeholders, student personal data, overclaims, sensitive wording and incomplete meeting action items.
Pure Python 3.8+ standard library, zero dependencies; local-only — no network, no model calls, no upload, no fabricated facts.
Why
School documents are repetitive, but they are also high-stakes: wrong dates, missing attachments, unfilled placeholders or student personal data can become real problems. Generic writing assistants optimize for fluent prose. 元公 optimizes for a smaller, verifiable job:
- make missing facts visible as
〔待补〕; - make structural gaps reproducible and reviewable;
- keep school drafts and context on the local machine.
Features
- Eight built-in document types: notice, parents letter, request, report, work summary, meeting minutes, work plan and briefing.
draft: turn structured facts into a Markdown or JSON skeleton.check: validate an existing draft with evidence lines.types: list, show and validate built-in or custom rule packs.- `
Related Skills
Yotta Compliance
Deterministic, local compliance-clause review skill for AI agents: versioned JSON rule packs, evidence-anchore
Skill Skeleton Generator
One-command generator for LGD-compliant AI skill skeletons (SKILL.md + AGENTS.md + dirs). 一键生成符合 LGD 三律的 AI 技能
Memory Wiki
File-layer wiki for AI agent markdown memory: ingest with automatic dating, keyword query, structural lint (or
Adg
One CLI to manage AI agent plugins and skills — author once in a single manifest, adapt to Claude Code, Codex
LLMs Txt Checker
Validates llms.txt files for AI agent discoverability. Checks structure, format, required fields, and best pra
Token Saver
Zero-cost token optimization engine for AI coding assistants (Claude Code, Cursor, Antigravity, Windsurf). Sav
Related Agents
ContestGate
Reads one contest's official notice and attachments (PDF/HWP), captures their actual bytes as immutable rule s
Feynman
Audit investment-research facts, figures, dates, periods, and quotes against traceable primary sources. Use be
Selfish Research Evidence
Verify external facts, statistics, specifications, dates, quotations, and claims; preserve provenance and unce