agentleFS
Thirumalai-Tech-DeveloperThirumalai-Tech-Developer/Kratos_Agent/skills/build-web-apps/SKILL.md

build-web-apps

Skill1 starsChanged 47 days agoMITView on GitHub

Build and review usable web apps across frontend behavior, backend data, accessibility, deployment, and operational readiness.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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
  1. Distinctive:

    Use for web app features, new web projects, UI debugging, database-backed behavior, and deployment preparation.

    line 9
  2. Distinctive:

    Keep data access server-side where appropriate.

    line 14
  3. Distinctive:

    Use the configured Kratos model only.

    line 18

≈ “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

Build and prepare web apps

Use for web app features, new web projects, UI debugging, database-backed behavior, and deployment preparation.

  1. Inspect the existing framework, routes, scripts, UI conventions, data layer, and deployment target before choosing an implementation.
  2. Define the user flow and visible states: loading, empty, success, validation, and failure. Reuse the project's design system and keep responsive and accessible behavior in scope.
  3. For framework APIs that may have changed, use the context7 workflow and the installed dependency version. For React or Next.js, load the existing vercel-react-best-practices skill when relevant.
  4. Keep data access server-side where appropriate. Validate inputs at boundaries, use parameterized queries, minimize stored data, and design schema changes with safe migrations and rollback considerations.
  5. For deployment, inspect the existing platform and build pipeline. Keep secrets in the platform's secret store, verify environment-variable names without printing values, and call out migrations, domains, permissions, and rollback steps.
  6. Review the final UI and data flow against the requested outcome. Report what can be observed locally and what would require a deployed environment.

Use the configured Kratos model only. Do not add another model provider unless the user explicitly changes that constraint. Do not deploy, publish, or alter production data without the user's direct request and the required approval.

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.