TanStack/aiGitHub

https://github.com/TanStack/ai

Stars:: 2.6k
Default branch:: main
Last scored:: 4h ago

80.6

Overall

Strengths

AGENTS.md / CLAUDE.md
CI configuration
Dependency manifest
License file
Linter / formatter config

Gaps

CONTRIBUTING guide
Pre-commit / git hooks

Suggestions to improve for a specific model

1
CONTRIBUTING guide
Add CONTRIBUTING.md describing branch naming, commit style, test commands, and the PR process.
+4.2 pts
2
Pre-commit / git hooks
Set up pre-commit (.pre-commit-config.yaml), husky, or lefthook to run format+lint on every commit.
+4.2 pts
3
Test suite
Add a tests/ (or test/, __tests__/, spec/) directory with runnable tests. Document how to run them in AGENTS.md.
+3.0 pts

Per-model scores

Claude Code

Weights AGENTS.md and tests heavily — Claude Code leans on an instructions file and a fast feedback loop.

79.5

Cursor

Weights type config and a detailed README highly — Cursor's inline edits benefit from static types and skim-readable docs.

84.6

Devin

Weights CI and reproducible envs highly — Devin runs in a sandboxed VM and needs end-to-end automation.

77.6

GPT-5 Codex

Balanced profile as a reference point.

80.5

Signal breakdown

AGENTS.md / CLAUDE.md· 100% pass

Substantive (11479 chars)

CLAUDE.md

CI configuration· 100% pass

5 GitHub Actions workflow(s)

.github/workflows

CONTRIBUTING guide· 0% pass

No CONTRIBUTING file

Dependency manifest· 100% pass

Manifest present

package.json

Reproducible dev env· 60% pass

package.json has 28 scripts

package.json

License file· 100% pass

License present

LICENSE

Linter / formatter config· 100% pass

Config detected

eslint.config.js

Pre-commit / git hooks· 0% pass

No pre-commit / husky / lefthook found

README· 100% pass

README detailed (5805 chars)

README.md

Manageable size· 80% pass

1708 files

Test suite· 70% pass

Test files detected (testing/e2e/tests/abort.spec.ts)

testing/e2e/tests/abort.spec.ts

Type configuration· 100% pass

Type config present

tsconfig.json