Mathematical Artifact Validation
SkillDev toolsRun fail-closed deterministic validation for mathematical and LaTeX artifacts
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Mathematical Artifact Validation skill
What this skill tells your AI
The instructions your AI receives, as published by a5c-ai/babysitter in library/specializations/domains/science/mathematics/skills/mathematical-artifact-validation/SKILL.md and read by ahel’s review.
Purpose
Produce reproducible source, structure, and reference evidence. Static validation is not mathematical proof verification.
Inputs
Source paths, LaTeX artifact, optional BibTeX files, required sections, registry, tool policy, and output manifest paths.
Shell-only gates
validate_sources.py: strict UTF-8, nonempty files, noU+FFFD, SHA-256 manifest.validate_math_artifact.py: braces/environments, required sections, labels, references, theorem target numbering/type, citations.validate_registry.py: durable evidence and coverage invariants.validate_grade.py: rubric arithmetic/current hashes.- Optional compiler command: execute a locally available TeX tool in a run-owned output directory and preserve version, argv, exit code, stdout/stderr, and output hash.
Every task declares expectedExitCode: 0. Required-tool unavailability follows policy and is never represented as pass. An agent may classify diagnostics but may not override a failed shell result.
Security and portability
Use structured file paths, a run-owned workspace, Python standard library, and no Node. Never use lossy decoding. Never overwrite source or prior round artifacts.
Output
Machine-readable gate manifest with pass|fail|unavailable, command/tool version where applicable, exit code, findings, evidence paths, and an explicit claim boundary.
Signals
- GitHub stars
- 2k
- Forks
- 112
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
mathematical-artifact-validation- Source
- github.com/a5c-ai/babysitter
Related picks
Skill · wshobson
The pick for Pythonpython-pro
Skill · jeffallan
The pick for Pythonlatex-posters
Skill · k-dense-ai
The pick for LaTeXlatex-drawing-guide
Skill · brycewang-stanford
The pick for LaTeXteach
Skill · mattpocock
More in Dev toolsimplement
Skill · mattpocock
More in Dev tools