business-ontology
CLAUDE.md3 starsChanged 4 months agoMITView on GitHub
This repository is the Business Ontology Resident package. Before product, architecture, documentation, or workflow changes, read: For ontology work, use the primary skill: The root SKILL.md is a package router, not the resident analyst operating skill. - Keep root files as package/bootstrap/rules entrypoints. - Keep all installable or resident analyst skills under skills/. - Keep host-specific instructions under adapters/. - Keep generated workspace files under templates/workspace/. - Keep model repository templates under templates/model-repo/. - Do not store secrets, raw private…
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- business-ontology-packageSkill
- build-brainSkill
- business-ontologySkill
- connect-sourceSkill
- daily-ingestSkill
- decide-like-moduleSkill
- drift-flagSkill
- drift-sweepSkill
- extract-from-inputSkill
- grill-gapsSkill
- interaction-contractSkill
- interpretSkill
- meeting-recorderSkill
- meeting-transcript-ingestSkill
- mine-materialsSkill
- onboard-contourSkill
- package-updateSkill
- promote-digestSkill
- propose-changeSkill
- show-modelSkill
- synthesize-digestSkill
- system-analysisSkill
The file
We split this CLAUDE.md into the rules it gives an agent
9 rules. About 0 are common, 4 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 5
Before product, architecture, documentation, or workflow changes, read:
- Very specific: line 24
Keep root files as package/bootstrap/rules entrypoints.
- Very specific: line 25
Keep all installable or resident analyst skills under skills/.
- Very specific: line 26
Keep host-specific instructions under adapters/.
- Very specific: line 27
Keep generated workspace files under templates/workspace/.
- Very specific: line 28
Keep model repository templates under templates/model-repo/.
- Distinctive: line 29
Do not store secrets, raw private messages, raw transcript payloads, OAuth tokens, bearer headers, or personal contact data.
- Distinctive: line 33
Before finalizing, run the relevant unittest files and review git diff.
- Distinctive: line 37
Use dense, concrete writing.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
Claude Code instructions
This repository is the Business Ontology Resident package.
Before product, architecture, documentation, or workflow changes, read:
BOOTSTRAP.mdagent-package.yamlAGENTS.mdspecs/BUSINESS-ONTOLOGY-RESIDENT.mdagent-os/README.md
For ontology work, use the primary skill:
skills/business-ontology/SKILL.mdThe root SKILL.md is a package router, not the resident analyst operating
skill.
Repository rules
- Keep root files as package/bootstrap/rules entrypoints.
- Keep all installable or resident analyst skills under
skills/. - Keep host-specific instructions under
adapters/. - Keep generated workspace files under
templates/workspace/. - Keep model repository templates under
templates/model-repo/. - Do not store secrets, raw private messages, raw transcript payloads, OAuth tokens, bearer headers, or personal contact data.
- For material docs changes, update
README.md,CHANGELOG.md, and affected specs or agent-os files. - Before finalizing, run the relevant unittest files and review
git diff.
Quality gate
Use dense, concrete writing. Avoid generic agent language, fake completeness, and claims that do not name the implemented file, command, or missing runtime piece. If a capability is only a contract, call it a contract. If it is implemented, name the implementation file.
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.

