auditing-physics
Skill2 starsChanged 7 months agoMITView on GitHub
Checks science files for cross-layer contradictions, inconsistent equations, broken derivation chains, and violations of the universe's foundational axiom. Use when promoting drafts to canon, after writing new science content, after restructuring, or when user says "audit the science", "physics audit", "check for contradictions", "does this break anything", "verify the science", or "cross-layer check". Does NOT check frontmatter or writing standards — use /auditing-canon for that.
In this repository19 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- auditing-canonSkill
- auditing-human-assumptionsSkill
- canon-rulesSkill
- compiling-entitiesSkill
- cross-checkingSkill
- deep-readingSkill
- deriving-social-systemsSkill
- designing-loreSkill
- designing-worldsSkill
- extracting-entitiesSkill
- integrating-researchSkill
- interrogating-designSkill
- planning-worldbuildingSkill
- researching-papersSkill
- verifying-completionSkill
- writing-scienceSkill
- writing-styleSkill
- writing-worldbuildingSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Check science files for cross-layer consistency against the universe's foundational rules.
- Very specific: line 22
Read CLAUDE.md for the universe's foundational axiom and locked rules.
- Very specific: line 23
If the project has reference files in references/, read those instead of the full science backend.
- Distinctive: line 54
Do NOT fix anything. Report only.
- Distinctive: line 58
Does NOT check frontmatter, naming, or writing standards (use /auditing-canon).
- Distinctive: line 59
Does NOT verify a single term across the repo (use /cross-checking).
- Distinctive: line 60
Does NOT write new content (use /writing-science).
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Auditing Physics
Check science files for cross-layer consistency against the universe's foundational rules.
Prerequisites
Read CLAUDE.md for the universe's foundational axiom and locked rules.
If the project has reference files in references/, read those instead
of the full science backend.
Chain of Draft Mode
Compress each reasoning step to ≤5 words. Mark conclusions with ####.
Axiom check. Signal exchange present. #### PASS.
Layer dependency. Upstream rule holds. #### PASS.
Equation check. Variable collision found. #### VIOLATION.Checks
For each file:
- Foundational Axiom Compliance — does the mechanism reduce to the universe's core principle?
- Cross-Layer Consistency — claims don't contradict upstream science
- Equation Consistency — variables, constants, and formulas don't collide
- Derivation Chains — each claim traces to a specific upstream principle
Output
- CONTRADICTION — two files disagree on a rule
- BROKEN-REF — cross-reference to nonexistent file
- COLLISION — duplicate constants or numbering
- DRIFT — terminology inconsistency
- GAP — missing section that downstream files depend on
Do NOT fix anything. Report only.
Out of Scope
Does NOT check frontmatter, naming, or writing standards (use /auditing-canon). Does NOT verify a single term across the repo (use /cross-checking). Does NOT write new content (use /writing-science).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

