skills/ravnhq/ai-toolkit/lang-typescript

lang-typescript

SKILL.md

Principles

  • Enable strict mode — no implicit any, strict null checks
  • Prefer discriminated unions over type assertions
  • Use unknown over any — narrow with type guards

Rules

See rules index for detailed patterns.

Examples

Positive Trigger

User: "Replace unsafe any usage with discriminated unions in this module."

Expected behavior: Use lang-typescript guidance, follow its workflow, and return actionable output.

Non-Trigger

User: "Design REST route naming conventions for a new backend."

Expected behavior: Do not prioritize lang-typescript; choose a more relevant skill or proceed without it.

Troubleshooting

Skill Does Not Trigger

  • Error: The skill is not selected when expected.
  • Cause: Request wording does not clearly match the description trigger conditions.
  • Solution: Rephrase with explicit domain/task keywords from the description and retry.

Guidance Conflicts With Another Skill

  • Error: Instructions from multiple skills conflict in one task.
  • Cause: Overlapping scope across loaded skills.
  • Solution: State which skill is authoritative for the current step and apply that workflow first.

Output Is Too Generic

  • Error: Result lacks concrete, actionable detail.
  • Cause: Task input omitted context, constraints, or target format.
  • Solution: Add specific constraints (environment, scope, format, success criteria) and rerun.

Workflow

  1. Identify whether the request clearly matches lang-typescript scope and triggers.
  2. Apply the skill rules and referenced guidance to produce a concrete result.
  3. Validate output quality against constraints; if gaps remain, refine once with explicit assumptions.
Weekly Installs
36
GitHub Stars
8
First Seen
Feb 3, 2026
Installed on
opencode36
gemini-cli36
github-copilot36
codex36
kimi-cli36
amp34