agentleFS
wtsi-hgiwtsi-hgi/agentskills/skills/nextjs-fastapi-reviewer/SKILL.md

nextjs-fastapi-reviewer

Skill1 starsChanged 40 days agoMITView on GitHub

Review Next.js + FastAPI implementations against spec acceptance tests. References implementation-principles, code-smells, nextjs-fastapi-conventions, testing-principles, and agent-conduct. Launched as a clean-context subagent by orchestrator, bugfix, or pr-reviewer.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  1. Distinctive:

    Read and follow agent-conduct, implementation-principles,

    line 8
  2. Distinctive:

    Run backend and frontend tests per nextjs-fastapi-conventions commands.

    line 21
  3. Distinctive:

    Every spec.md acceptance test must have a corresponding test (pytest for backend, Vitest for frontend).

    line 26
  4. Distinctive:

    Check against nextjs-fastapi-conventions architecture:

    line 32
  5. Very specific:

    Contracts: every new endpoint has Pydantic model + Zod schema + contract test.

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
SKILL.md

Next.js + FastAPI Reviewer Skill

Read and follow agent-conduct, implementation-principles, testing-principles, code-smells, and nextjs-fastapi-conventions before starting.

You are a review subagent with clean context. Independently verify that code meets the spec and quality standards.

Review Procedure

1. Read spec.md and all source/test files for the item(s).

2. Run tests

Run backend and frontend tests per nextjs-fastapi-conventions commands. All must pass.

3. Verify acceptance test coverage

Every spec.md acceptance test must have a corresponding test (pytest for backend, Vitest for frontend). Reject missing, stubbed, circumvented, or hardcoded-result tests. Apply the testing-principles review rule.

4. Verify implementation correctness

Check against nextjs-fastapi-conventions architecture:

  • BFF: browser never calls FastAPI directly. Server Actions use 'use server'. Client components use 'use client' and don't import server-only modules. API Routes only for external consumers.
  • Contracts: every new endpoint has Pydantic model + Zod schema + contract test. backendJson() used with schema. Schemas agree.
  • Backend: async def endpoints, response_model declared, lifespan pattern (not @app.on_event).
  • Frontend: useActionState (not useFormState). Tailwind v4 semantic tokens. Runtime theme handling matches the project's Tailwind v4 setup (@theme, @theme inline, @custom-variant dark, and next-themes).
  • Visual regressions: apply testing-principles § Perceptual Requirements. Reject a perceptual claim proven only from source CSS, class names, or isolated computed properties. The real app stylesheet and the production dark-mode mechanism are part of what the assertion must exercise.

5. Verify code quality

Apply all rules from implementation-principles and nextjs-fastapi-conventions (Python and TypeScript sections).

Match the changed code against code-smells. Report each hit as a judgement call with the hunk quoted, unless a convention or an implementation-principles rule makes it blocking.

6. Run linters

Per conventions commands. No issues for modified files.

7. Verdict

  • PASS - optionally note minor non-blocking suggestions.
  • FAIL - specific, actionable feedback: missing tests, unmet spec requirements, architecture violations, quality violations, lint issues.

Batch Reviews

  • Single-item: review that item.
  • Parallel batch: review ALL items together; return per-item verdict.

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.