libretto
CLAUDE.md883 starsChanged 3 months agoMITView on GitHub
Never manually edit packages/libretto/package.json version. Use the release script: This bumps the version, updates all SKILL.md files, syncs mirrors, validates parity, commits, pushes a release-v* branch, and opens a PR. The release CI workflow triggers automatically when the PR merges to main. Temporarily set a pre-release version in packages/libretto/package.json and replace its workspace: and catalog: dependency ranges with published ranges. Then run: Approve npm's browser passkey prompt and verify the exact version installs in a clean project. Do not commit…
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 35
After any change to source skill files or READMEs:
≈ “Common” is an estimate: at least 1 in 5 of the 25,680 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
Libretto Monorepo
Releasing a New Version
Never manually edit packages/libretto/package.json version. Use the release script:
pnpm prepare-release [patch|minor|major]This bumps the version, updates all SKILL.md files, syncs mirrors, validates parity, commits, pushes a release-v* branch, and opens a PR. The release CI workflow triggers automatically when the PR merges to main.
Publishing an Experimental Version
Temporarily set a pre-release version in packages/libretto/package.json and replace its workspace: and catalog: dependency ranges with published ranges. Then run:
pnpm publish:experimentalApprove npm's browser passkey prompt and verify the exact version installs in a clean project. Do not commit the temporary manifest edits.
Mirror System
Skill files and READMEs are mirrored across multiple locations. Do not hand-edit the mirrored copies. Edit source files only, then sync.
Source directories:
packages/libretto/skills/libretto/— interactive Libretto skill (source of truth)packages/libretto/skills/libretto-readonly/— read-only diagnosis skill (source of truth)
Mirror targets (generated — never edit directly):
.agents/skills/libretto/and.agents/skills/libretto-readonly/.claude/skills/libretto/and.claude/skills/libretto-readonly/
After any change to source skill files or READMEs:
pnpm sync:mirrors # sync all mirrored files
pnpm check:mirrors # validate everything is in syncOther versions1 project uses a version of this.
Word for word · 1
- cashew-labs/libretto★ 898100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository30 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .deepsec/AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- .opencode/AGENTS.mdAGENTS.md
- docs/CLAUDE.mdCLAUDE.md
- address-reviewSkill
- cli-developmentSkill
- erroreSkill
- external-electron-appsSkill
- fix-merge-conflictsSkill
- generate-specSkill
- generate-spec-v2Skill
- get-pr-reviewsSkill
- glimpse-changesSkill
- implement-specSkill
- improve-codebase-architectureSkill
- libretto-readonlySkill
- librettoSkill
- promptingSkill
- push-everythingSkill
- pushSkill
- reviewSkill
- spec-reviewSkill
- summarizeSkill
- technical-writingSkill
- turborepoSkill
- update-docsSkill
- writing-testsSkill
- libretto-readonlySkill
- librettoSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

