silo-codesilo-code/silo/CLAUDE.md

silo

CLAUDE.md62 starsChanged 59 days agoMITView on GitHub

- The workflows referenced above under .agents/skills/*/SKILL.md (silo-testing, silo-docs-sync, silo-domain-modeling) are registered Claude Code skills — invoke them via the Skill tool rather than reading them manually; Claude Code also surfaces them proactively when a task matches their description. Claude Code only discovers skills under .claude/skills/, not the canonical .agents/skills/ (the Codex-native, agentskills.io-spec-aligned location) — each skill's real content lives in .agents/skills/<name>/, and .claude/skills/<name> is a symlink to it, so both tools read the same file with nothing to keep…

In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs-screenshotSkill
- silo-architecture-review-orchestratorSkill
- silo-architecture-reviewSkill
- silo-docs-syncSkill
- silo-domain-modelingSkill
- silo-release-publishSkill
- silo-testingSkill
- verifier-guiSkill
- graftSkill
- silo-extension-builderSkill

The file

Create a free account to mount

Files

CLAUDE.md

@AGENTS.md

Claude Code

The workflows referenced above under .agents/skills/*/SKILL.md (silo-testing, silo-docs-sync, silo-domain-modeling) are registered Claude Code skills — invoke them via the Skill tool rather than reading them manually; Claude Code also surfaces them proactively when a task matches their description. Claude Code only discovers skills under .claude/skills/, not the canonical .agents/skills/ (the Codex-native, agentskills.io-spec-aligned location) — each skill's real content lives in .agents/skills/<name>/, and .claude/skills/<name> is a symlink to it, so both tools read the same file with nothing to keep in sync.
silo-domain-modeling is a repo-local fork of the personal domain-modeling skill, adapted to this repo's actual doc layout and format (docs/domain-language.md, docs/decisions/, docs/proposals/), rather than that skill's generic CONTEXT.md/docs/adr/ defaults.
Other externally-installed skills: improve-codebase-architecture and grill-with-docs (from mattpocock/skills) still hardcode CONTEXT.md and docs/adr/ in their own instructions and have no concept of docs/proposals/ (RFCs). When running them: treat docs/adr/ as docs/decisions/ (read/write there, continuing the existing numbering — never create a separate docs/adr/ directory), and CONTEXT.md as docs/domain-language.md. Don't expect either skill to read or write docs/proposals/.

Download now (ZIP)

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free