auditing-canon
Skill2 starsChanged 7 months agoMITView on GitHub
Verifies canon status, naming compliance, frontmatter completeness, writing standards, and cross-reference validity across worldbuilding files. Use when checking naming consistency, verifying frontmatter, auditing prose standards, or when user says "canon audit", "check names", "verify frontmatter", "writing standards check", or "naming audit". Does NOT check physics equations — use /auditing-physics for that.
In this repository19 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- auditing-human-assumptionsSkill
- auditing-physicsSkill
- 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
9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Verify naming, frontmatter, writing standards, and cross-references.
- Distinctive: line 20
Read CLAUDE.md for locked spellings, naming conventions, and writing rules.
- Distinctive: line 38
Every file has YAML frontmatter: title, tags, status
- Distinctive: line 43
No meta-commentary ("This section establishes...")
- Distinctive: line 44
No narrative content in science directories
- Distinctive: line 48
All markdown links resolve to existing files
- Distinctive: line 59
Do NOT fix anything. Report only.
- Distinctive: line 63
Does NOT check physics consistency or equations (use /auditing-physics).
- Distinctive: line 64
Does NOT treat cross-civilization differences as contradictions.
≈ “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 Canon
Verify naming, frontmatter, writing standards, and cross-references.
Prerequisites
Read CLAUDE.md for locked spellings, naming conventions, and writing rules.
Chain of Draft Mode
Name check. Human term found. Science dir. #### VIOLATION.
Frontmatter. status field missing. #### VIOLATION.
Spelling. Variant found. #### VIOLATION: use canonical form.
Cross-ref. Link resolves. #### PASS.Checks
Naming
- In-universe terminology used correctly per directory type
- Locked spellings match CLAUDE.md table
Frontmatter
- Every file has YAML frontmatter: title, tags, status
- Status is one of: canon, draft, needs-review, superseded
Writing Standards (science files only)
- Academic third-person prose throughout
- No meta-commentary ("This section establishes...")
- No narrative content in science directories
- Citations use consistent format with ## References section
Cross-References
- All markdown links resolve to existing files
- GLOSSARY.md entries exist for key terms
Output
- STYLE — writing standard violation
- META — self-referential document language
- DRIFT — spelling or naming inconsistency
- ORPHAN — referenced entity has no file
- BROKEN-REF — link to nonexistent file
Do NOT fix anything. Report only.
Out of Scope
Does NOT check physics consistency or equations (use /auditing-physics). Does NOT treat cross-civilization differences as contradictions.
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.

