agentleFS
Sign inStart free
vpeetla-aivpeetla-ai/multi-agent-system-pattern/.cursor/skills/agentic-engineering/SKILL.md

agentic-engineering

Skill2 starsChanged 5 months agoMITView on GitHub

Apply Karpathy agentic engineering discipline: think before coding, minimal diffs, surgical changes, test-verified completion. Use for any implementation task in vpeetla-ai repos when quality bar matters.

32 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use nuxt4-patterns, dart-flutter-patterns and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • loulanyueSkill

    nuxt4-patterns

    Nuxt 4 app patterns for hydration safety, performance, route rules, lazy loading, and SSR-safe data fetching with useFetch and useAsyncData.

    Also in 10 projects that use this

  • RojiosSkill

    dart-flutter-patterns

    Production-ready Dart and Flutter patterns covering null safety, immutable state, async composition, widget architecture, popular state management frameworks (BLoC, Riverpod, Provider), GoRouter navigation, Dio networking, Freezed code generation, and clean architecture.

    Also in 7 projects that use this

  • TironFoxSkill

    agent-payment-x402

    Add x402 payment execution to AI agents — per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents need to pay for APIs, services, or other agents.

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 25 edited versions we read keep these.

  • 3

    Distinctive

    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
  1. Distinctive:

    Not vibe coding — preserve professional quality while moving faster.

    line 11
  2. Distinctive:

    Read surrounding files — match naming, types, error handling

    line 17
  3. Very specific:

    Run relevant tests (pytest -q, npm test, typecheck)

    line 27
  4. Distinctive:

    No test strategy for new behavior

    line 35

“Common” is measured: kept by at least 6 in 10 of the 25 edited versions of this file we could read. “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
SKILL.md

Agentic Engineering

Not vibe coding — preserve professional quality while moving faster.

Before writing code

  1. State assumptions and success criteria (tests, API response, UI behavior)
  2. Identify smallest change that satisfies the request
  3. Read surrounding files — match naming, types, error handling

While coding

  • Simplicity first — no speculative abstractions or "while I'm here" refactors
  • Surgical diffs — touch only files required for the task
  • Match conventions — see target repo's pyproject.toml, eslint, existing patterns

Before claiming done

  1. Run relevant tests (pytest -q, npm test, typecheck)
  2. For agent graphs: verify routing + at least one happy-path trace
  3. Summarize what changed and what was not changed (scope boundary)

Red flags — stop and ask

  • Request touches governance + orchestration in one PR (split layers)
  • Side effect without gateway/HITL (publish, push, notify)
  • No test strategy for new behavior

Reference

Karpathy: From Vibe Coding to Agentic Engineering

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