agentleFS
LeonardoTrapaniLeonardoTrapani/better-skills/AGENTS.md

better-skills

AGENTS.md11 starsChanged 9 months agoMITView on GitHub

better-skills is an agent second brain: authenticated users manage a graph of reusable skills from a CLI and a web app, backed by a Hono API.

  • Reads credentials

The file

We split this AGENTS.md into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Use root Turbo scripts for cross-workspace tasks.

    line 8
  2. Very specific:

    Default validation after code changes: bun run check-types then bun run check.

    line 9
  3. Distinctive:

    No shared test runner is defined yet.

    line 10
  4. Very specific:

    Never commit secrets or .env files.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 AGENTS.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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md

better-skills is an agent second brain: authenticated users manage a graph of reusable skills from a CLI and a web app, backed by a Hono API.

Essentials

  • Package manager is Bun workspaces (bun@1.3.5); use bun, not npm/pnpm/yarn.
  • Use root Turbo scripts for cross-workspace tasks.
  • Default validation after code changes: bun run check-types then bun run check.
  • No shared test runner is defined yet; add package-local tests when introducing new behavior.
  • Never commit secrets or .env files.

Workspace map

  • apps/cli: command-line interface built with @clack/prompts, connected to the server via tRPC.
  • apps/web: Next.js web console for managing skills, graph links, and account state.
  • apps/server: Hono host for Better Auth and tRPC endpoints.
  • packages/api: shared tRPC router and context.
  • packages/auth: Better Auth configuration and adapter wiring.
  • packages/db: Drizzle schema and migration workflows for Neon Postgres.
  • packages/env: typed runtime env contracts for server, web, and CLI.
  • packages/config: shared TypeScript config.

Canonical commands

  • bun run dev, bun run dev:web, bun run dev:server, bun run dev:cli
  • bun cli (runs the CLI directly without turbo)
  • bun run build, bun run check-types, bun run check
  • bun run db:push, bun run db:generate, bun run db:migrate, bun run db:studio

Required env shape

  • Server env: DATABASE_URL, BETTER_AUTH_SECRET, BETTER_AUTH_URL, CORS_ORIGIN.
  • Web env: NEXT_PUBLIC_SERVER_URL.
  • CLI env: SERVER_URL (defaults to http://localhost:3000).

Progressive disclosure

  • apps/web/AGENTS.md
  • apps/server/AGENTS.md
  • apps/cli/AGENTS.md
  • packages/api/AGENTS.md
  • packages/db/AGENTS.md
  • resources/default-skills/AGENTS.md
  • docs/mention-link-sync-flow.md
  • docs/skills-schema.md
  • .agents/skills/turborepo/SKILL.md
  • .agents/skills/hono/SKILL.md
  • .agents/skills/next-best-practices/SKILL.md
  • .agents/skills/better-auth-best-practices/SKILL.md
  • .agents/skills/neon-postgres/SKILL.md

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.