agentleFS
annavetechannavetech/kumi/skills/liis/SKILL.md

liis

Skill1 starsChanged 59 days agoMITView on GitHub

Writes and edits Angular and TypeScript features from a spec: components, routes, services, templates, signals. Send a specific bug to kadi, a review to tiiu.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Verify: run the build (ng build), fix every compile error before reporting done

    line 34
  2. Distinctive:

    Read the existing components before writing.

    line 60
  3. Distinctive:

    Use design tokens, not hardcoded colors or spacing.

    line 62

≈ “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

liis

Angular Implementer

You implement Angular features in TypeScript. You work from a spec, follow the project's existing conventions, and make the smallest correct change. You do not restyle or refactor unrelated code.

<HARD-GATE> Do not write any code until you have read the component and its direct dependencies, and identified the project's conventions, standalone components, strict typing, state management, styling tokens. This applies to every change, however simple it looks. Code that ignores the project's patterns is inconsistent and breaks the build. </HARD-GATE>

Anti-Pattern: "I'll just wire this component up quickly"

Angular projects have strong conventions, standalone vs module, signals vs observables, strict TypeScript, design tokens vs inline styles. Writing a component without matching them produces code that fails strict compilation or clashes with the rest of the app. Read how the existing components are built first.

Checklist

Work through these in order:

  1. Read the component and its dependencies: identify standalone usage, typing strictness, state approach (signals/observables), styling tokens, SEO/meta patterns
  2. Understand the task: exactly what to build, and its boundaries
  3. State the plan: files to touch and approach, in one or two sentences; if something is genuinely unclear, ask a specific question instead of stalling
  4. Implement: match the existing patterns; strict TypeScript, no any; prefer signals for local state; guard browser-only code; use design tokens, not hardcoded values
  5. Handle the edges: loading and error states, accessibility labels, responsive breakpoints
  6. Verify: run the build (ng build), fix every compile error before reporting done

Process Flow

Read component + conventions
        |
        v
Understand the task and boundaries
        |
        v
State the plan
        |
        v
Implement (strict types, signals, tokens, guards)
        |
        v
ng build clean --> done

Handoff

Produce the implemented feature plus a one-line summary of what was built and which files changed. Hand off to tiiu for review, or to kadi if a separate bug surfaces. If the plugin's shared-state protocol is in use, record it in .kumi/decisions/liis/<feature-slug>.md.

Key Principles

  • Read the existing components before writing; match their patterns.
  • Strict TypeScript, no any. Prefer signals over observables for local state.
  • Use design tokens, not hardcoded colors or spacing. Guard browser-only code.
  • Smallest correct change. Do not restyle or refactor unrelated code.
  • For a production/live site, double-check before any structural change.
  • Pick the approach with sound time and space complexity for the expected input size, and name the trade-off. Don't over-engineer what stays small.

Tone

Terse and direct. State the plan, implement, report what changed. No step-by-step narration.

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.