consult-user-mcp
CLAUDE.md39 starsChanged 4 months agoMITView on GitHub
The SvelteKit site for the project — landing page, changelog, comparison, and a screenshot-generation harness. It also holds releases.json, which is the release source of truth for the whole repo, not just for this site. src/lib/data/releases.json is upstream of two things: the /changelog route renders it, and bun run changelog generates the repo's CHANGELOG.md from it. Nothing else writes release history. The /screenshots routes are a rendering harness, not documentation. They take type and platform params (/screenshots/[type]/[platform], /screenshots/dual/[left]/[right]) and render…
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- container/CLAUDE.mdCLAUDE.md
- dialog-cli/CLAUDE.mdCLAUDE.md
- dialog-cli-windows/CLAUDE.mdCLAUDE.md
- macos-app/CLAUDE.mdCLAUDE.md
- mcp-server/CLAUDE.mdCLAUDE.md
- sketch-cli/CLAUDE.mdCLAUDE.md
- test-cases/CLAUDE.mdCLAUDE.md
- windows-app/CLAUDE.mdCLAUDE.md
- beadsSkill
- release-appSkill
- windows-buildSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 35
If the generated CHANGELOG.md diff contains anything you did not put in releases.json, something else edited it by hand.
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 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
Docs Site
What this is
The SvelteKit site for the project — landing page, changelog, comparison, and a screenshot-generation harness. It also holds releases.json, which is the release source of truth for the whole repo, not just for this site.
Mental model
src/lib/data/releases.json is upstream of two things: the /changelog route renders it, and bun run changelog generates the repo's CHANGELOG.md from it. Nothing else writes release history.
The /screenshots routes are a rendering harness, not documentation. They take type and platform params (/screenshots/[type]/[platform], /screenshots/dual/[left]/[right]) and render dialog mockups for capture by bun run screenshots. They exist to produce marketing images, so changing their layout changes published assets.
Everything else under routes/ is ordinary content.
Important invariants
CHANGELOG.mdis generated. Never hand-edit it. Changereleases.jsonand runbun run changelog.releases.jsonrecords app changes only. A docs-only change gets no entry.- Entries are user-facing benefits, not commit messages. Full guidance with examples:
.claude/rules/release-notes.md. - Validate against
src/lib/data/releases.schema.json.
Common change patterns
Adding a release → an entry in releases.json, then bun run changelog. Usually part of the release-app skill rather than a standalone edit.
Regenerating screenshots → bun run screenshots. Check what changed before committing; these are published assets.
Verification
cd docs && bun run dev # local site
bun run changelog # from repo root — regenerate and diff CHANGELOG.mdIf the generated CHANGELOG.md diff contains anything you did not put in releases.json, something else edited it by hand.
Related context
.claude/rules/release-notes.md— how to phrase entries.claude/skills/release-app/SKILL.md— wherereleases.jsonfits in a releasesrc/lib/data/releases.schema.json
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.

